diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..e51dad9a8c05accb6bfdd5c97b654a27265a4852 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/progress.png filter=lfs diff=lfs merge=lfs -text +Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/progress.png filter=lfs diff=lfs merge=lfs -text +Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/progress.png filter=lfs diff=lfs merge=lfs -text diff --git a/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/dataset.json b/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/dataset.json new file mode 100644 index 0000000000000000000000000000000000000000..cc4fbecccdefaf960c81cc2f2c7e2ea247071c4f --- /dev/null +++ b/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/dataset.json @@ -0,0 +1,14 @@ +{ + "labels": { + "label_001": "1", + "background": 0 + }, + "channel_names": { + "0": "CT_zscore_synthrad" + }, + "numTraining": 309, + "file_ending": ".nii.gz", + "test_set": [ + "case_0000" + ] +} \ No newline at end of file diff --git a/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/dataset_fingerprint.json b/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/dataset_fingerprint.json new file mode 100644 index 0000000000000000000000000000000000000000..b0f5e56b08233470185d7c001d03dd89fed3f25a --- /dev/null +++ b/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/dataset_fingerprint.json @@ -0,0 +1,3108 @@ +{ + "foreground_intensity_properties_per_channel": { + "0": { + "max": 3071.0, + "mean": -239.3903045654297, + "median": -185.0, + "min": -1024.0, + "percentile_00_5": -1024.0, + "percentile_99_5": 479.0, + "std": 328.2787170410156 + } + }, + "median_relative_size_after_cropping": 1.0, + "shapes_after_crop": [ + [ + 88, + 309, + 310 + ], + [ + 88, + 309, + 289 + ], + [ + 87, + 310, + 312 + ], + [ + 86, + 308, + 315 + ], + [ + 87, + 313, + 311 + ], + [ + 82, + 309, + 308 + ], + [ + 87, + 310, + 311 + ], + [ + 88, + 308, + 309 + ], + [ + 82, + 310, + 308 + ], + [ + 81, + 448, + 449 + ], + [ + 85, + 317, + 309 + ], + [ + 86, + 311, + 314 + ], + [ + 76, + 459, + 455 + ], + [ + 88, + 308, + 310 + ], + [ + 50, + 510, + 510 + ], + [ + 86, + 310, + 311 + ], + [ + 78, + 311, + 309 + ], + [ + 87, + 290, + 291 + ], + [ + 87, + 309, + 308 + ], + [ + 94, + 393, + 393 + ], + [ + 87, + 311, + 308 + ], + [ + 87, + 314, + 309 + ], + [ + 87, + 309, + 309 + ], + [ + 100, + 368, + 370 + ], + [ + 88, + 308, + 307 + ], + [ + 100, + 498, + 499 + ], + [ + 87, + 308, + 313 + ], + [ + 87, + 313, + 310 + ], + [ + 86, + 314, + 311 + ], + [ + 88, + 309, + 309 + ], + [ + 87, + 312, + 309 + ], + [ + 80, + 308, + 313 + ], + [ + 87, + 309, + 310 + ], + [ + 86, + 309, + 308 + ], + [ + 88, + 308, + 309 + ], + [ + 88, + 307, + 308 + ], + [ + 79, + 311, + 310 + ], + [ + 115, + 560, + 560 + ], + [ + 79, + 450, + 451 + ], + [ + 85, + 308, + 309 + ], + [ + 87, + 308, + 307 + ], + [ + 88, + 310, + 305 + ], + [ + 86, + 313, + 311 + ], + [ + 87, + 310, + 308 + ], + [ + 85, + 316, + 308 + ], + [ + 73, + 314, + 313 + ], + [ + 86, + 312, + 311 + ], + [ + 87, + 309, + 310 + ], + [ + 86, + 311, + 308 + ], + [ + 87, + 306, + 307 + ], + [ + 82, + 308, + 307 + ], + [ + 87, + 310, + 308 + ], + [ + 80, + 288, + 303 + ], + [ + 81, + 450, + 428 + ], + [ + 86, + 308, + 311 + ], + [ + 87, + 311, + 310 + ], + [ + 86, + 310, + 317 + ], + [ + 87, + 311, + 310 + ], + [ + 87, + 309, + 307 + ], + [ + 77, + 453, + 456 + ], + [ + 100, + 374, + 405 + ], + [ + 80, + 310, + 312 + ], + [ + 87, + 308, + 308 + ], + [ + 81, + 430, + 449 + ], + [ + 78, + 452, + 433 + ], + [ + 80, + 454, + 450 + ], + [ + 82, + 450, + 451 + ], + [ + 80, + 432, + 450 + ], + [ + 80, + 448, + 452 + ], + [ + 81, + 451, + 450 + ], + [ + 80, + 451, + 449 + ], + [ + 80, + 449, + 453 + ], + [ + 81, + 448, + 412 + ], + [ + 80, + 449, + 433 + ], + [ + 81, + 449, + 449 + ], + [ + 81, + 452, + 421 + ], + [ + 77, + 458, + 450 + ], + [ + 81, + 450, + 451 + ], + [ + 73, + 453, + 412 + ], + [ + 77, + 452, + 417 + ], + [ + 80, + 449, + 431 + ], + [ + 81, + 451, + 442 + ], + [ + 81, + 450, + 413 + ], + [ + 81, + 450, + 450 + ], + [ + 79, + 451, + 454 + ], + [ + 80, + 449, + 453 + ], + [ + 80, + 452, + 431 + ], + [ + 80, + 455, + 451 + ], + [ + 56, + 451, + 450 + ], + [ + 81, + 452, + 448 + ], + [ + 80, + 452, + 450 + ], + [ + 74, + 452, + 418 + ], + [ + 68, + 454, + 449 + ], + [ + 51, + 449, + 427 + ], + [ + 70, + 456, + 393 + ], + [ + 80, + 454, + 450 + ], + [ + 78, + 439, + 450 + ], + [ + 82, + 449, + 431 + ], + [ + 79, + 451, + 445 + ], + [ + 80, + 430, + 455 + ], + [ + 82, + 449, + 447 + ], + [ + 82, + 400, + 449 + ], + [ + 81, + 402, + 449 + ], + [ + 75, + 451, + 449 + ], + [ + 81, + 452, + 448 + ], + [ + 80, + 452, + 452 + ], + [ + 56, + 451, + 450 + ], + [ + 70, + 455, + 393 + ], + [ + 80, + 451, + 452 + ], + [ + 71, + 451, + 449 + ], + [ + 80, + 421, + 449 + ], + [ + 80, + 448, + 434 + ], + [ + 73, + 454, + 393 + ], + [ + 81, + 449, + 452 + ], + [ + 75, + 452, + 434 + ], + [ + 74, + 449, + 449 + ], + [ + 82, + 427, + 396 + ], + [ + 75, + 398, + 398 + ], + [ + 80, + 454, + 430 + ], + [ + 78, + 451, + 456 + ], + [ + 81, + 450, + 451 + ], + [ + 80, + 449, + 431 + ], + [ + 79, + 448, + 454 + ], + [ + 80, + 451, + 452 + ], + [ + 79, + 452, + 454 + ], + [ + 79, + 450, + 455 + ], + [ + 82, + 449, + 447 + ], + [ + 81, + 450, + 448 + ], + [ + 81, + 451, + 451 + ], + [ + 81, + 449, + 449 + ], + [ + 79, + 408, + 457 + ], + [ + 81, + 449, + 452 + ], + [ + 80, + 451, + 453 + ], + [ + 81, + 448, + 450 + ], + [ + 77, + 449, + 457 + ], + [ + 81, + 450, + 451 + ], + [ + 81, + 450, + 450 + ], + [ + 87, + 310, + 310 + ], + [ + 81, + 449, + 451 + ], + [ + 80, + 453, + 450 + ], + [ + 80, + 448, + 452 + ], + [ + 78, + 451, + 457 + ], + [ + 81, + 430, + 391 + ], + [ + 78, + 449, + 455 + ], + [ + 81, + 452, + 412 + ], + [ + 81, + 449, + 449 + ], + [ + 80, + 444, + 432 + ], + [ + 81, + 449, + 451 + ], + [ + 81, + 432, + 450 + ], + [ + 81, + 448, + 453 + ], + [ + 79, + 455, + 449 + ], + [ + 81, + 449, + 450 + ], + [ + 81, + 450, + 385 + ], + [ + 81, + 434, + 436 + ], + [ + 82, + 416, + 449 + ], + [ + 82, + 442, + 450 + ], + [ + 81, + 439, + 451 + ], + [ + 81, + 447, + 450 + ], + [ + 81, + 415, + 450 + ], + [ + 79, + 450, + 453 + ], + [ + 76, + 430, + 450 + ], + [ + 81, + 450, + 450 + ], + [ + 81, + 448, + 450 + ], + [ + 81, + 448, + 422 + ], + [ + 82, + 448, + 448 + ], + [ + 79, + 454, + 429 + ], + [ + 81, + 451, + 420 + ], + [ + 75, + 449, + 462 + ], + [ + 82, + 450, + 450 + ], + [ + 81, + 450, + 451 + ], + [ + 82, + 448, + 451 + ], + [ + 82, + 448, + 451 + ], + [ + 75, + 449, + 448 + ], + [ + 80, + 451, + 454 + ], + [ + 80, + 449, + 453 + ], + [ + 81, + 449, + 452 + ], + [ + 82, + 450, + 450 + ], + [ + 78, + 450, + 428 + ], + [ + 80, + 442, + 453 + ], + [ + 81, + 440, + 449 + ], + [ + 82, + 441, + 449 + ], + [ + 82, + 450, + 411 + ], + [ + 81, + 430, + 449 + ], + [ + 82, + 413, + 450 + ], + [ + 81, + 448, + 404 + ], + [ + 81, + 450, + 449 + ], + [ + 81, + 449, + 451 + ], + [ + 81, + 450, + 377 + ], + [ + 80, + 455, + 453 + ], + [ + 80, + 454, + 448 + ], + [ + 82, + 447, + 449 + ], + [ + 99, + 452, + 435 + ], + [ + 68, + 450, + 430 + ], + [ + 99, + 314, + 310 + ], + [ + 99, + 453, + 452 + ], + [ + 99, + 312, + 311 + ], + [ + 75, + 459, + 414 + ], + [ + 69, + 432, + 449 + ], + [ + 99, + 452, + 434 + ], + [ + 99, + 456, + 404 + ], + [ + 71, + 453, + 400 + ], + [ + 98, + 310, + 311 + ], + [ + 99, + 311, + 309 + ], + [ + 99, + 309, + 310 + ], + [ + 99, + 315, + 308 + ], + [ + 98, + 308, + 308 + ], + [ + 99, + 450, + 453 + ], + [ + 99, + 383, + 349 + ], + [ + 99, + 314, + 310 + ], + [ + 70, + 452, + 451 + ], + [ + 69, + 452, + 447 + ], + [ + 99, + 452, + 455 + ], + [ + 68, + 433, + 447 + ], + [ + 100, + 308, + 318 + ], + [ + 98, + 319, + 309 + ], + [ + 69, + 452, + 448 + ], + [ + 99, + 435, + 454 + ], + [ + 91, + 315, + 310 + ], + [ + 99, + 450, + 424 + ], + [ + 99, + 452, + 452 + ], + [ + 98, + 450, + 448 + ], + [ + 100, + 455, + 451 + ], + [ + 91, + 435, + 452 + ], + [ + 99, + 313, + 315 + ], + [ + 99, + 308, + 310 + ], + [ + 70, + 450, + 450 + ], + [ + 99, + 448, + 448 + ], + [ + 99, + 309, + 308 + ], + [ + 79, + 311, + 307 + ], + [ + 94, + 312, + 312 + ], + [ + 99, + 326, + 315 + ], + [ + 74, + 467, + 497 + ], + [ + 71, + 465, + 499 + ], + [ + 74, + 467, + 499 + ], + [ + 73, + 472, + 499 + ], + [ + 98, + 448, + 448 + ], + [ + 100, + 314, + 316 + ], + [ + 98, + 431, + 417 + ], + [ + 100, + 315, + 309 + ], + [ + 98, + 307, + 308 + ], + [ + 98, + 312, + 319 + ], + [ + 98, + 308, + 308 + ], + [ + 98, + 310, + 265 + ], + [ + 128, + 390, + 391 + ], + [ + 68, + 492, + 473 + ], + [ + 66, + 497, + 497 + ], + [ + 67, + 497, + 498 + ], + [ + 67, + 474, + 468 + ], + [ + 66, + 460, + 493 + ], + [ + 74, + 445, + 506 + ], + [ + 70, + 485, + 468 + ], + [ + 68, + 501, + 497 + ], + [ + 67, + 497, + 498 + ], + [ + 65, + 498, + 477 + ], + [ + 72, + 470, + 503 + ], + [ + 66, + 498, + 497 + ], + [ + 67, + 479, + 498 + ], + [ + 68, + 499, + 497 + ], + [ + 69, + 499, + 501 + ], + [ + 67, + 497, + 497 + ], + [ + 69, + 498, + 499 + ], + [ + 67, + 497, + 498 + ], + [ + 68, + 478, + 500 + ], + [ + 68, + 501, + 487 + ], + [ + 70, + 484, + 500 + ], + [ + 66, + 473, + 497 + ], + [ + 66, + 497, + 497 + ], + [ + 67, + 499, + 498 + ], + [ + 67, + 498, + 497 + ], + [ + 66, + 498, + 496 + ], + [ + 67, + 490, + 497 + ], + [ + 67, + 498, + 498 + ], + [ + 66, + 497, + 497 + ], + [ + 66, + 479, + 498 + ], + [ + 67, + 482, + 499 + ], + [ + 70, + 478, + 499 + ], + [ + 68, + 499, + 500 + ], + [ + 66, + 497, + 472 + ], + [ + 70, + 499, + 482 + ], + [ + 71, + 479, + 481 + ], + [ + 79, + 454, + 499 + ], + [ + 66, + 497, + 496 + ], + [ + 67, + 485, + 500 + ], + [ + 70, + 499, + 496 + ], + [ + 59, + 501, + 498 + ], + [ + 68, + 471, + 501 + ], + [ + 64, + 499, + 498 + ], + [ + 66, + 498, + 497 + ], + [ + 67, + 452, + 469 + ], + [ + 75, + 435, + 484 + ], + [ + 66, + 486, + 492 + ], + [ + 66, + 467, + 497 + ], + [ + 75, + 486, + 498 + ], + [ + 67, + 498, + 497 + ], + [ + 67, + 497, + 497 + ], + [ + 67, + 498, + 499 + ], + [ + 66, + 497, + 497 + ], + [ + 67, + 498, + 496 + ], + [ + 66, + 466, + 498 + ], + [ + 70, + 482, + 501 + ], + [ + 69, + 478, + 479 + ], + [ + 67, + 500, + 497 + ], + [ + 71, + 469, + 502 + ], + [ + 72, + 466, + 500 + ], + [ + 66, + 486, + 497 + ], + [ + 68, + 497, + 500 + ], + [ + 67, + 498, + 498 + ], + [ + 71, + 481, + 501 + ], + [ + 70, + 501, + 499 + ] + ], + "spacings": [ + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ] + ] +} \ No newline at end of file diff --git a/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/checkpoint_final.pth b/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/checkpoint_final.pth new file mode 100644 index 0000000000000000000000000000000000000000..ce6048ed0609284185655d44d8db71ba185523a5 --- /dev/null +++ b/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/checkpoint_final.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaef86084b37113ab519ff31157a2fdb0ddedf6df7290e480c15b724f6b9f1da +size 815581485 diff --git a/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/debug.json b/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/debug.json new file mode 100644 index 0000000000000000000000000000000000000000..098a4c142ab952c41b4fce8add582d6ebb71cd51 --- /dev/null +++ b/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/debug.json @@ -0,0 +1,58 @@ +{ + "_best_ema": "0.06327102", + "aim_run": ">", + "batch_size": "2", + "configuration_manager": "{'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [40, 224, 192], 'median_image_size_in_voxels': [81.0, 449.0, 449.0], 'spacing': [3.0, 1.0, 1.0], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[1, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [1, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [1, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}, 'deep_supervision': False}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}", + "configuration_name": "3d_fullres", + "cudnn_version": 90501, + "current_epoch": "1000", + "dataloader_train": "", + "dataloader_train.generator": "", + "dataloader_train.num_processes": "12", + "dataloader_train.transform": "Compose ( [RemoveLabelTransform( output_key = 'seg', input_key = 'seg', replace_with = 0, remove_label = -1 ), RenameTransform( delete_old = True, out_key = 'target', in_key = 'seg' ), NumpyToTensor( keys = ['data', 'target', 'mask'], cast_to = 'float' )] )", + "dataloader_val": "", + "dataloader_val.generator": "", + "dataloader_val.num_processes": "6", + "dataloader_val.transform": "Compose ( [RemoveLabelTransform( output_key = 'seg', input_key = 'seg', replace_with = 0, remove_label = -1 ), RenameTransform( delete_old = True, out_key = 'target', in_key = 'seg' ), NumpyToTensor( keys = ['data', 'target', 'mask'], cast_to = 'float' )] )", + "dataset_json": "{'labels': {'label_001': '1', 'background': 0}, 'channel_names': {'0': 'CT_zscore_synthrad'}, 'numTraining': 309, 'file_ending': '.mha'}", + "debug_custom": "{'run_hash': '71a4eb65476745ac89c8118f'}", + "decoder_type": "standard", + "device": "cuda:0", + "disable_checkpointing": "False", + "enable_deep_supervision": "False", + "fold": "0", + "folder_with_segs_from_previous_stage": "None", + "gpu_name": "NVIDIA H100", + "grad_scaler": "", + "hostname": "g020", + "image_loss_weight": "0.5", + "inference_allowed_mirroring_axes": "None", + "initial_lr": "0.01", + "is_cascaded": "False", + "is_ddp": "False", + "label_manager": "", + "local_rank": "0", + "log_file": "/datasets/work/hb-synthrad2023/work/synthrad2025/bw_workplace/data/nnunet_struct/results/Dataset540_synthrad2025_task2_CBCT_AB_pre_v2r_stitched_masked_both/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/training_log_2025_8_15_18_18_19.txt", + "logger": "", + "loss": "SynPerceptionLoss(\n (seg_model): ResidualEncoderUNet(\n (encoder): ResidualEncoder(\n (stem): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(1, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(1, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n (stages): Sequential(\n (0): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (1): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(32, 64, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(32, 64, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[1, 2, 2], stride=[1, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(32, 64, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(32, 64, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (2): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 128, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 128, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[2, 2, 2], stride=[2, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 128, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 128, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (3): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 256, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 256, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[2, 2, 2], stride=[2, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (4): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (5): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (4): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 320, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 320, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[2, 2, 2], stride=[2, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 320, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 320, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (4): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (5): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (5): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[1, 2, 2], stride=[1, 2, 2], padding=0)\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (4): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (5): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n )\n (decoder): UNetDecoder(\n (encoder): ResidualEncoder(\n (stem): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(1, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(1, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n (stages): Sequential(\n (0): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (1): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(32, 64, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(32, 64, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[1, 2, 2], stride=[1, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(32, 64, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(32, 64, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (2): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 128, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 128, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[2, 2, 2], stride=[2, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 128, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 128, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (3): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 256, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 256, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[2, 2, 2], stride=[2, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (4): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (5): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (4): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 320, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 320, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[2, 2, 2], stride=[2, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 320, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 320, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (4): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (5): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (5): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[1, 2, 2], stride=[1, 2, 2], padding=0)\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (4): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (5): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n )\n (stages): ModuleList(\n (0): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(640, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(640, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n (1): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(512, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(512, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n (2): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(256, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n (3): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(128, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n (4): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(64, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n )\n (transpconvs): ModuleList(\n (0): ConvTranspose3d(320, 320, kernel_size=(1, 2, 2), stride=(1, 2, 2))\n (1): ConvTranspose3d(320, 256, kernel_size=(2, 2, 2), stride=(2, 2, 2))\n (2): ConvTranspose3d(256, 128, kernel_size=(2, 2, 2), stride=(2, 2, 2))\n (3): ConvTranspose3d(128, 64, kernel_size=(2, 2, 2), stride=(2, 2, 2))\n (4): ConvTranspose3d(64, 32, kernel_size=(1, 2, 2), stride=(1, 2, 2))\n )\n (seg_layers): ModuleList(\n (0): Conv3d(320, 62, kernel_size=(1, 1, 1), stride=(1, 1, 1))\n (1): Conv3d(256, 62, kernel_size=(1, 1, 1), stride=(1, 1, 1))\n (2): Conv3d(128, 62, kernel_size=(1, 1, 1), stride=(1, 1, 1))\n (3): Conv3d(64, 62, kernel_size=(1, 1, 1), stride=(1, 1, 1))\n (4): Conv3d(32, 62, kernel_size=(1, 1, 1), stride=(1, 1, 1))\n )\n )\n )\n (L1): L1Loss()\n (image_loss): myMaskedMSE(\n (mse): myMSE()\n )\n)", + "lr_scheduler": "", + "my_init_kwargs": "{'plans': {'dataset_name': 'Dataset540_synthrad2025_task2_CBCT_AB_pre_v2r_stitched_masked_both', 'plans_name': 'nnUNetResEncUNetLPlans', 'original_median_spacing_after_transp': [3.0, 1.0, 1.0], 'original_median_shape_after_transp': [81, 449, 449], 'image_reader_writer': 'SimpleITKIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 13, 'patch_size': [512, 448], 'median_image_size_in_voxels': [449.0, 449.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 7, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}, '3d_lowres': {'data_identifier': 'nnUNetResEncUNetLPlans_3d_lowres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [56, 224, 192], 'median_image_size_in_voxels': [81, 297, 297], 'spacing': [3.0, 1.512589724855112, 1.512589724855112], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [2, 2, 2], [2, 2, 2], [2, 2, 2], [1, 2, 2], [1, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': False, 'next_stage': '3d_cascade_fullres'}, '3d_fullres': {'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [40, 224, 192], 'median_image_size_in_voxels': [81.0, 449.0, 449.0], 'spacing': [3.0, 1.0, 1.0], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[1, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [1, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [1, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}, '3d_cascade_fullres': {'inherits_from': '3d_fullres', 'previous_stage': '3d_lowres'}}, 'experiment_planner_used': 'nnUNetPlannerResEncL', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 3071.0, 'mean': -239.3903045654297, 'median': -185.0, 'min': -1024.0, 'percentile_00_5': -1024.0, 'percentile_99_5': 479.0, 'std': 328.2787170410156}}}, 'configuration': '3d_fullres', 'fold': 0, 'dataset_json': {'labels': {'label_001': '1', 'background': 0}, 'channel_names': {'0': 'CT_zscore_synthrad'}, 'numTraining': 309, 'file_ending': '.mha'}, 'unpack_dataset': True, 'device': device(type='cuda')}", + "network": "ResidualEncoderUNet", + "num_epochs": "1000", + "num_input_channels": "1", + "num_iterations_per_epoch": "250", + "num_val_iterations_per_epoch": "50", + "optimizer": "SGD (\nParameter Group 0\n dampening: 0\n differentiable: False\n foreach: None\n fused: None\n initial_lr: 0.01\n lr: 1.995262314968881e-05\n maximize: False\n momentum: 0.99\n nesterov: True\n weight_decay: 3e-05\n)", + "output_folder": "/datasets/work/hb-synthrad2023/work/synthrad2025/bw_workplace/data/nnunet_struct/results/Dataset540_synthrad2025_task2_CBCT_AB_pre_v2r_stitched_masked_both/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0", + "output_folder_base": "/datasets/work/hb-synthrad2023/work/synthrad2025/bw_workplace/data/nnunet_struct/results/Dataset540_synthrad2025_task2_CBCT_AB_pre_v2r_stitched_masked_both/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres", + "oversample_foreground_percent": "0.33", + "perception_masked": "True", + "plans_manager": "{'dataset_name': 'Dataset540_synthrad2025_task2_CBCT_AB_pre_v2r_stitched_masked_both', 'plans_name': 'nnUNetResEncUNetLPlans', 'original_median_spacing_after_transp': [3.0, 1.0, 1.0], 'original_median_shape_after_transp': [81, 449, 449], 'image_reader_writer': 'SimpleITKIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 13, 'patch_size': [512, 448], 'median_image_size_in_voxels': [449.0, 449.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 7, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}, '3d_lowres': {'data_identifier': 'nnUNetResEncUNetLPlans_3d_lowres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [56, 224, 192], 'median_image_size_in_voxels': [81, 297, 297], 'spacing': [3.0, 1.512589724855112, 1.512589724855112], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [2, 2, 2], [2, 2, 2], [2, 2, 2], [1, 2, 2], [1, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': False, 'next_stage': '3d_cascade_fullres'}, '3d_fullres': {'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [40, 224, 192], 'median_image_size_in_voxels': [81.0, 449.0, 449.0], 'spacing': [3.0, 1.0, 1.0], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[1, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [1, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [1, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}, '3d_cascade_fullres': {'inherits_from': '3d_fullres', 'previous_stage': '3d_lowres'}}, 'experiment_planner_used': 'nnUNetPlannerResEncL', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 3071.0, 'mean': -239.3903045654297, 'median': -185.0, 'min': -1024.0, 'percentile_00_5': -1024.0, 'percentile_99_5': 479.0, 'std': 328.2787170410156}}}", + "preprocessed_dataset_folder": "/datasets/work/hb-synthrad2023/work/synthrad2025/bw_workplace/data/nnunet_struct/preprocessed/Dataset540_synthrad2025_task2_CBCT_AB_pre_v2r_stitched_masked_both/nnUNetPlans_3d_fullres", + "preprocessed_dataset_folder_base": "/datasets/work/hb-synthrad2023/work/synthrad2025/bw_workplace/data/nnunet_struct/preprocessed/Dataset540_synthrad2025_task2_CBCT_AB_pre_v2r_stitched_masked_both", + "save_every": "50", + "torch_version": "2.7.1+cu126", + "unpack_dataset": "True", + "was_initialized": "True", + "weight_decay": "3e-05" +} \ No newline at end of file diff --git a/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/progress.png b/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/progress.png new file mode 100644 index 0000000000000000000000000000000000000000..7a4381f4362cc7cf295a4c8c01534ea4b4c7cb3b --- /dev/null +++ b/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/progress.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bd925c152d4d2bc2e3b25a334f6e30e896d0dc1c9edfc5522ef549fcb7f75ed +size 523982 diff --git a/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/validation/summary.json b/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/validation/summary.json new file mode 100644 index 0000000000000000000000000000000000000000..4542dc5a3a38586385be7003edb9fae48b026998 --- /dev/null +++ b/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/validation/summary.json @@ -0,0 +1,52 @@ +{ + "mae": { + "mean": 55.60064848848964, + "std": 14.338210868800594, + "max": 105.47389638122534, + "min": 35.20833348049252, + "25pc": 44.134254115405234, + "50pc": 53.92539230685208, + "75pc": 62.27850375865349, + "count": 62 + }, + "psnr": { + "mean": 30.48458344031393, + "std": 2.38001206819551, + "max": 35.77302372613302, + "min": 25.190641684003367, + "25pc": 28.694927361710747, + "50pc": 29.964147419029842, + "75pc": 32.48056910462868, + "count": 62 + }, + "ms_ssim": { + "mean": 0.9189507095920884, + "std": 0.05408709159150134, + "max": 0.9836779174167589, + "min": 0.715160057895457, + "25pc": 0.8933213351088732, + "50pc": 0.9349496548077856, + "75pc": 0.9545689319733478, + "count": 62 + }, + "DICE": { + "mean": 0.7588220357162053, + "std": 0.15028017475619626, + "max": 0.9240115880966187, + "min": 0.12273936718702316, + "25pc": 0.7277467846870422, + "50pc": 0.8152719140052795, + "75pc": 0.8395445346832275, + "count": 62 + }, + "HD95": { + "mean": 5.62839973168295, + "std": 4.9812358838641115, + "max": 27.221315383911133, + "min": 1.3090169429779053, + "25pc": 2.8109169006347656, + "50pc": 4.001410961151123, + "75pc": 6.309501647949219, + "count": 62 + } +} \ No newline at end of file diff --git a/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/plans.json b/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/plans.json new file mode 100644 index 0000000000000000000000000000000000000000..b1690d28d07e5df93275b0863342443c6ad587ee --- /dev/null +++ b/Dataset540/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/plans.json @@ -0,0 +1,521 @@ +{ + "dataset_name": "Dataset540_synthrad2025_task2_CBCT_AB_pre_v2r_stitched_masked_both", + "plans_name": "nnUNetResEncUNetLPlans", + "original_median_spacing_after_transp": [ + 3.0, + 1.0, + 1.0 + ], + "original_median_shape_after_transp": [ + 81, + 449, + 449 + ], + "image_reader_writer": "SimpleITKIO", + "transpose_forward": [ + 0, + 1, + 2 + ], + "transpose_backward": [ + 0, + 1, + 2 + ], + "configurations": { + "2d": { + "data_identifier": "nnUNetPlans_2d", + "preprocessor_name": "DefaultPreprocessor", + "batch_size": 13, + "patch_size": [ + 512, + 448 + ], + "median_image_size_in_voxels": [ + 449.0, + 449.0 + ], + "spacing": [ + 1.0, + 1.0 + ], + "normalization_schemes": [ + "CTNormalizationClippingSynthrad2025" + ], + "use_mask_for_norm": [ + false + ], + "resampling_fn_data": "resample_data_or_seg_to_shape", + "resampling_fn_seg": "resample_data_or_seg_to_shape", + "resampling_fn_data_kwargs": { + "is_seg": false, + "order": 3, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_seg_kwargs": { + "is_seg": true, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_probabilities": "resample_data_or_seg_to_shape", + "resampling_fn_probabilities_kwargs": { + "is_seg": false, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "architecture": { + "network_class_name": "dynamic_network_architectures.architectures.unet.ResidualEncoderUNet", + "arch_kwargs": { + "n_stages": 7, + "features_per_stage": [ + 32, + 64, + 128, + 256, + 512, + 512, + 512 + ], + "conv_op": "torch.nn.modules.conv.Conv2d", + "kernel_sizes": [ + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ] + ], + "strides": [ + [ + 1, + 1 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ] + ], + "n_blocks_per_stage": [ + 1, + 3, + 4, + 6, + 6, + 6, + 6 + ], + "n_conv_per_stage_decoder": [ + 1, + 1, + 1, + 1, + 1, + 1 + ], + "conv_bias": true, + "norm_op": "torch.nn.modules.instancenorm.InstanceNorm2d", + "norm_op_kwargs": { + "eps": 1e-05, + "affine": true + }, + "dropout_op": null, + "dropout_op_kwargs": null, + "nonlin": "torch.nn.LeakyReLU", + "nonlin_kwargs": { + "inplace": true + } + }, + "_kw_requires_import": [ + "conv_op", + "norm_op", + "dropout_op", + "nonlin" + ] + }, + "batch_dice": true + }, + "3d_lowres": { + "data_identifier": "nnUNetResEncUNetLPlans_3d_lowres", + "preprocessor_name": "DefaultPreprocessor", + "batch_size": 2, + "patch_size": [ + 56, + 224, + 192 + ], + "median_image_size_in_voxels": [ + 81, + 297, + 297 + ], + "spacing": [ + 3.0, + 1.512589724855112, + 1.512589724855112 + ], + "normalization_schemes": [ + "CTNormalizationClippingSynthrad2025" + ], + "use_mask_for_norm": [ + false + ], + "resampling_fn_data": "resample_data_or_seg_to_shape", + "resampling_fn_seg": "resample_data_or_seg_to_shape", + "resampling_fn_data_kwargs": { + "is_seg": false, + "order": 3, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_seg_kwargs": { + "is_seg": true, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_probabilities": "resample_data_or_seg_to_shape", + "resampling_fn_probabilities_kwargs": { + "is_seg": false, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "architecture": { + "network_class_name": "dynamic_network_architectures.architectures.unet.ResidualEncoderUNet", + "arch_kwargs": { + "n_stages": 6, + "features_per_stage": [ + 32, + 64, + 128, + 256, + 320, + 320 + ], + "conv_op": "torch.nn.modules.conv.Conv3d", + "kernel_sizes": [ + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ] + ], + "strides": [ + [ + 1, + 1, + 1 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 1, + 2, + 2 + ], + [ + 1, + 2, + 2 + ] + ], + "n_blocks_per_stage": [ + 1, + 3, + 4, + 6, + 6, + 6 + ], + "n_conv_per_stage_decoder": [ + 1, + 1, + 1, + 1, + 1 + ], + "conv_bias": true, + "norm_op": "torch.nn.modules.instancenorm.InstanceNorm3d", + "norm_op_kwargs": { + "eps": 1e-05, + "affine": true + }, + "dropout_op": null, + "dropout_op_kwargs": null, + "nonlin": "torch.nn.LeakyReLU", + "nonlin_kwargs": { + "inplace": true + } + }, + "_kw_requires_import": [ + "conv_op", + "norm_op", + "dropout_op", + "nonlin" + ] + }, + "batch_dice": false, + "next_stage": "3d_cascade_fullres" + }, + "3d_fullres": { + "data_identifier": "nnUNetPlans_3d_fullres", + "preprocessor_name": "DefaultPreprocessor", + "batch_size": 2, + "patch_size": [ + 40, + 224, + 192 + ], + "median_image_size_in_voxels": [ + 81.0, + 449.0, + 449.0 + ], + "spacing": [ + 3.0, + 1.0, + 1.0 + ], + "normalization_schemes": [ + "CTNormalizationClippingSynthrad2025" + ], + "use_mask_for_norm": [ + false + ], + "resampling_fn_data": "resample_data_or_seg_to_shape", + "resampling_fn_seg": "resample_data_or_seg_to_shape", + "resampling_fn_data_kwargs": { + "is_seg": false, + "order": 3, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_seg_kwargs": { + "is_seg": true, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_probabilities": "resample_data_or_seg_to_shape", + "resampling_fn_probabilities_kwargs": { + "is_seg": false, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "architecture": { + "network_class_name": "dynamic_network_architectures.architectures.unet.ResidualEncoderUNet", + "arch_kwargs": { + "n_stages": 6, + "features_per_stage": [ + 32, + 64, + 128, + 256, + 320, + 320 + ], + "conv_op": "torch.nn.modules.conv.Conv3d", + "kernel_sizes": [ + [ + 1, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ] + ], + "strides": [ + [ + 1, + 1, + 1 + ], + [ + 1, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 1, + 2, + 2 + ] + ], + "n_blocks_per_stage": [ + 1, + 3, + 4, + 6, + 6, + 6 + ], + "n_conv_per_stage_decoder": [ + 1, + 1, + 1, + 1, + 1 + ], + "conv_bias": true, + "norm_op": "torch.nn.modules.instancenorm.InstanceNorm3d", + "norm_op_kwargs": { + "eps": 1e-05, + "affine": true + }, + "dropout_op": null, + "dropout_op_kwargs": null, + "nonlin": "torch.nn.LeakyReLU", + "nonlin_kwargs": { + "inplace": true + } + }, + "_kw_requires_import": [ + "conv_op", + "norm_op", + "dropout_op", + "nonlin" + ] + }, + "batch_dice": true + }, + "3d_cascade_fullres": { + "inherits_from": "3d_fullres", + "previous_stage": "3d_lowres" + } + }, + "experiment_planner_used": "nnUNetPlannerResEncL", + "label_manager": "LabelManager", + "foreground_intensity_properties_per_channel": { + "0": { + "max": 3071.0, + "mean": -239.3903045654297, + "median": -185.0, + "min": -1024.0, + "percentile_00_5": -1024.0, + "percentile_99_5": 479.0, + "std": 328.2787170410156 + } + } +} \ No newline at end of file diff --git a/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/dataset.json b/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/dataset.json new file mode 100644 index 0000000000000000000000000000000000000000..ddd101a2273db276471ade54ba9585bf95a2b4f3 --- /dev/null +++ b/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/dataset.json @@ -0,0 +1,14 @@ +{ + "labels": { + "label_001": "1", + "background": 0 + }, + "channel_names": { + "0": "CT_zscore_synthrad" + }, + "numTraining": 325, + "file_ending": ".nii.gz", + "test_set": [ + "case_0000" + ] +} \ No newline at end of file diff --git a/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/dataset_fingerprint.json b/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/dataset_fingerprint.json new file mode 100644 index 0000000000000000000000000000000000000000..e7eb6ad02ffbc8525e5e2519a5b302baddeff0d3 --- /dev/null +++ b/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/dataset_fingerprint.json @@ -0,0 +1,3268 @@ +{ + "foreground_intensity_properties_per_channel": { + "0": { + "max": 3071.0, + "mean": -215.1082763671875, + "median": -133.0, + "min": -1024.0, + "percentile_00_5": -1024.0, + "percentile_99_5": 1345.0, + "std": 459.63665771484375 + } + }, + "median_relative_size_after_cropping": 1.0, + "shapes_after_crop": [ + [ + 88, + 307, + 309 + ], + [ + 83, + 307, + 311 + ], + [ + 88, + 309, + 308 + ], + [ + 79, + 313, + 314 + ], + [ + 87, + 309, + 310 + ], + [ + 88, + 308, + 308 + ], + [ + 86, + 309, + 312 + ], + [ + 88, + 307, + 308 + ], + [ + 87, + 309, + 309 + ], + [ + 87, + 308, + 309 + ], + [ + 88, + 309, + 308 + ], + [ + 88, + 308, + 307 + ], + [ + 86, + 313, + 313 + ], + [ + 82, + 309, + 309 + ], + [ + 86, + 308, + 313 + ], + [ + 86, + 312, + 307 + ], + [ + 87, + 307, + 309 + ], + [ + 87, + 309, + 309 + ], + [ + 87, + 307, + 308 + ], + [ + 87, + 308, + 309 + ], + [ + 86, + 309, + 314 + ], + [ + 88, + 308, + 310 + ], + [ + 88, + 307, + 308 + ], + [ + 87, + 308, + 307 + ], + [ + 87, + 311, + 314 + ], + [ + 87, + 309, + 309 + ], + [ + 87, + 307, + 306 + ], + [ + 86, + 308, + 310 + ], + [ + 87, + 307, + 312 + ], + [ + 87, + 308, + 311 + ], + [ + 87, + 307, + 307 + ], + [ + 51, + 282, + 311 + ], + [ + 87, + 308, + 310 + ], + [ + 88, + 310, + 309 + ], + [ + 87, + 310, + 308 + ], + [ + 88, + 308, + 308 + ], + [ + 88, + 308, + 308 + ], + [ + 87, + 308, + 309 + ], + [ + 87, + 308, + 309 + ], + [ + 87, + 309, + 310 + ], + [ + 87, + 308, + 312 + ], + [ + 82, + 309, + 310 + ], + [ + 88, + 310, + 308 + ], + [ + 88, + 311, + 308 + ], + [ + 88, + 309, + 309 + ], + [ + 87, + 308, + 312 + ], + [ + 88, + 309, + 310 + ], + [ + 86, + 310, + 312 + ], + [ + 87, + 310, + 309 + ], + [ + 87, + 309, + 310 + ], + [ + 87, + 307, + 308 + ], + [ + 87, + 308, + 310 + ], + [ + 82, + 288, + 273 + ], + [ + 88, + 309, + 309 + ], + [ + 88, + 307, + 307 + ], + [ + 87, + 310, + 307 + ], + [ + 86, + 311, + 309 + ], + [ + 87, + 308, + 311 + ], + [ + 87, + 309, + 309 + ], + [ + 87, + 310, + 308 + ], + [ + 88, + 225, + 308 + ], + [ + 87, + 308, + 307 + ], + [ + 81, + 311, + 308 + ], + [ + 87, + 310, + 310 + ], + [ + 87, + 309, + 307 + ], + [ + 88, + 310, + 308 + ], + [ + 87, + 313, + 311 + ], + [ + 88, + 309, + 309 + ], + [ + 88, + 309, + 307 + ], + [ + 88, + 309, + 308 + ], + [ + 88, + 309, + 309 + ], + [ + 87, + 308, + 312 + ], + [ + 87, + 308, + 310 + ], + [ + 88, + 311, + 309 + ], + [ + 88, + 308, + 308 + ], + [ + 88, + 308, + 308 + ], + [ + 49, + 307, + 307 + ], + [ + 88, + 308, + 309 + ], + [ + 88, + 310, + 307 + ], + [ + 86, + 315, + 315 + ], + [ + 88, + 306, + 307 + ], + [ + 87, + 310, + 311 + ], + [ + 87, + 311, + 308 + ], + [ + 88, + 309, + 308 + ], + [ + 87, + 310, + 309 + ], + [ + 88, + 309, + 309 + ], + [ + 87, + 312, + 309 + ], + [ + 87, + 310, + 311 + ], + [ + 88, + 310, + 311 + ], + [ + 88, + 308, + 309 + ], + [ + 87, + 309, + 310 + ], + [ + 87, + 310, + 311 + ], + [ + 87, + 312, + 311 + ], + [ + 88, + 309, + 311 + ], + [ + 88, + 308, + 310 + ], + [ + 88, + 310, + 309 + ], + [ + 87, + 308, + 310 + ], + [ + 87, + 311, + 308 + ], + [ + 88, + 309, + 308 + ], + [ + 87, + 311, + 311 + ], + [ + 87, + 307, + 309 + ], + [ + 87, + 310, + 311 + ], + [ + 88, + 309, + 309 + ], + [ + 82, + 309, + 308 + ], + [ + 88, + 309, + 309 + ], + [ + 87, + 311, + 308 + ], + [ + 87, + 310, + 313 + ], + [ + 88, + 310, + 309 + ], + [ + 87, + 309, + 311 + ], + [ + 88, + 310, + 309 + ], + [ + 88, + 308, + 308 + ], + [ + 87, + 310, + 309 + ], + [ + 87, + 309, + 310 + ], + [ + 87, + 312, + 312 + ], + [ + 87, + 309, + 311 + ], + [ + 87, + 312, + 311 + ], + [ + 87, + 312, + 310 + ], + [ + 87, + 307, + 309 + ], + [ + 87, + 312, + 308 + ], + [ + 88, + 307, + 309 + ], + [ + 87, + 308, + 312 + ], + [ + 87, + 311, + 307 + ], + [ + 87, + 312, + 311 + ], + [ + 81, + 310, + 311 + ], + [ + 87, + 308, + 312 + ], + [ + 88, + 310, + 308 + ], + [ + 87, + 311, + 309 + ], + [ + 87, + 309, + 310 + ], + [ + 86, + 311, + 317 + ], + [ + 88, + 308, + 308 + ], + [ + 88, + 311, + 309 + ], + [ + 51, + 311, + 311 + ], + [ + 87, + 311, + 309 + ], + [ + 86, + 310, + 307 + ], + [ + 88, + 311, + 308 + ], + [ + 88, + 309, + 309 + ], + [ + 87, + 311, + 312 + ], + [ + 87, + 310, + 307 + ], + [ + 86, + 309, + 311 + ], + [ + 88, + 310, + 311 + ], + [ + 87, + 312, + 308 + ], + [ + 86, + 308, + 311 + ], + [ + 87, + 311, + 312 + ], + [ + 85, + 313, + 314 + ], + [ + 86, + 311, + 311 + ], + [ + 88, + 308, + 309 + ], + [ + 86, + 314, + 313 + ], + [ + 87, + 312, + 312 + ], + [ + 87, + 314, + 311 + ], + [ + 86, + 308, + 312 + ], + [ + 87, + 308, + 312 + ], + [ + 88, + 313, + 308 + ], + [ + 87, + 307, + 309 + ], + [ + 87, + 311, + 308 + ], + [ + 85, + 317, + 311 + ], + [ + 87, + 307, + 311 + ], + [ + 88, + 308, + 312 + ], + [ + 87, + 310, + 310 + ], + [ + 87, + 311, + 311 + ], + [ + 52, + 308, + 310 + ], + [ + 87, + 309, + 307 + ], + [ + 87, + 308, + 311 + ], + [ + 87, + 308, + 310 + ], + [ + 87, + 310, + 309 + ], + [ + 88, + 309, + 309 + ], + [ + 87, + 309, + 309 + ], + [ + 86, + 310, + 314 + ], + [ + 88, + 309, + 308 + ], + [ + 86, + 314, + 312 + ], + [ + 88, + 308, + 309 + ], + [ + 87, + 309, + 310 + ], + [ + 87, + 309, + 310 + ], + [ + 87, + 312, + 309 + ], + [ + 88, + 310, + 310 + ], + [ + 86, + 313, + 311 + ], + [ + 87, + 311, + 310 + ], + [ + 87, + 311, + 309 + ], + [ + 86, + 311, + 312 + ], + [ + 87, + 311, + 310 + ], + [ + 87, + 309, + 307 + ], + [ + 85, + 310, + 311 + ], + [ + 88, + 312, + 308 + ], + [ + 85, + 293, + 319 + ], + [ + 86, + 308, + 308 + ], + [ + 87, + 310, + 309 + ], + [ + 87, + 309, + 310 + ], + [ + 53, + 307, + 310 + ], + [ + 87, + 308, + 312 + ], + [ + 54, + 308, + 307 + ], + [ + 88, + 309, + 307 + ], + [ + 88, + 308, + 307 + ], + [ + 87, + 307, + 310 + ], + [ + 88, + 307, + 308 + ], + [ + 87, + 310, + 307 + ], + [ + 77, + 311, + 311 + ], + [ + 99, + 315, + 316 + ], + [ + 128, + 305, + 307 + ], + [ + 129, + 300, + 305 + ], + [ + 128, + 303, + 305 + ], + [ + 121, + 299, + 300 + ], + [ + 128, + 304, + 301 + ], + [ + 70, + 300, + 298 + ], + [ + 70, + 300, + 303 + ], + [ + 71, + 304, + 305 + ], + [ + 71, + 302, + 303 + ], + [ + 72, + 302, + 299 + ], + [ + 70, + 300, + 301 + ], + [ + 99, + 308, + 312 + ], + [ + 70, + 303, + 299 + ], + [ + 71, + 300, + 300 + ], + [ + 70, + 301, + 299 + ], + [ + 72, + 307, + 306 + ], + [ + 70, + 304, + 304 + ], + [ + 121, + 303, + 306 + ], + [ + 119, + 303, + 303 + ], + [ + 122, + 308, + 301 + ], + [ + 130, + 310, + 301 + ], + [ + 71, + 300, + 300 + ], + [ + 128, + 301, + 301 + ], + [ + 130, + 392, + 400 + ], + [ + 73, + 302, + 302 + ], + [ + 70, + 301, + 302 + ], + [ + 70, + 301, + 301 + ], + [ + 71, + 299, + 301 + ], + [ + 71, + 304, + 303 + ], + [ + 71, + 302, + 298 + ], + [ + 70, + 299, + 300 + ], + [ + 130, + 371, + 394 + ], + [ + 123, + 285, + 306 + ], + [ + 70, + 300, + 299 + ], + [ + 70, + 301, + 299 + ], + [ + 116, + 302, + 302 + ], + [ + 129, + 299, + 302 + ], + [ + 127, + 304, + 303 + ], + [ + 115, + 311, + 311 + ], + [ + 71, + 299, + 302 + ], + [ + 70, + 300, + 301 + ], + [ + 72, + 304, + 300 + ], + [ + 72, + 305, + 300 + ], + [ + 99, + 290, + 313 + ], + [ + 70, + 300, + 299 + ], + [ + 111, + 302, + 303 + ], + [ + 128, + 300, + 298 + ], + [ + 122, + 305, + 302 + ], + [ + 70, + 300, + 299 + ], + [ + 129, + 303, + 301 + ], + [ + 121, + 310, + 305 + ], + [ + 122, + 301, + 302 + ], + [ + 110, + 306, + 298 + ], + [ + 119, + 310, + 308 + ], + [ + 121, + 302, + 304 + ], + [ + 116, + 304, + 303 + ], + [ + 124, + 308, + 313 + ], + [ + 72, + 304, + 303 + ], + [ + 69, + 298, + 299 + ], + [ + 71, + 299, + 301 + ], + [ + 122, + 303, + 299 + ], + [ + 70, + 301, + 300 + ], + [ + 131, + 313, + 310 + ], + [ + 70, + 302, + 301 + ], + [ + 72, + 299, + 298 + ], + [ + 66, + 496, + 498 + ], + [ + 71, + 297, + 298 + ], + [ + 74, + 305, + 304 + ], + [ + 72, + 298, + 297 + ], + [ + 71, + 297, + 297 + ], + [ + 71, + 299, + 297 + ], + [ + 73, + 298, + 299 + ], + [ + 71, + 298, + 297 + ], + [ + 68, + 457, + 498 + ], + [ + 71, + 298, + 297 + ], + [ + 71, + 298, + 296 + ], + [ + 72, + 297, + 298 + ], + [ + 72, + 297, + 301 + ], + [ + 66, + 482, + 498 + ], + [ + 67, + 496, + 498 + ], + [ + 70, + 500, + 498 + ], + [ + 71, + 298, + 296 + ], + [ + 71, + 296, + 295 + ], + [ + 66, + 497, + 497 + ], + [ + 73, + 300, + 299 + ], + [ + 71, + 297, + 297 + ], + [ + 71, + 296, + 297 + ], + [ + 69, + 480, + 499 + ], + [ + 71, + 298, + 298 + ], + [ + 71, + 297, + 297 + ], + [ + 73, + 297, + 303 + ], + [ + 73, + 299, + 299 + ], + [ + 72, + 299, + 298 + ], + [ + 71, + 297, + 295 + ], + [ + 71, + 299, + 299 + ], + [ + 71, + 298, + 296 + ], + [ + 70, + 493, + 499 + ], + [ + 71, + 296, + 297 + ], + [ + 68, + 497, + 500 + ], + [ + 66, + 496, + 496 + ], + [ + 71, + 484, + 501 + ], + [ + 74, + 297, + 301 + ], + [ + 73, + 297, + 297 + ], + [ + 73, + 300, + 298 + ], + [ + 72, + 298, + 298 + ], + [ + 71, + 499, + 470 + ], + [ + 71, + 297, + 298 + ], + [ + 72, + 498, + 503 + ], + [ + 71, + 297, + 296 + ], + [ + 71, + 300, + 298 + ], + [ + 71, + 298, + 296 + ], + [ + 67, + 497, + 497 + ], + [ + 71, + 501, + 499 + ], + [ + 69, + 498, + 501 + ], + [ + 70, + 297, + 297 + ], + [ + 66, + 498, + 477 + ], + [ + 71, + 500, + 500 + ], + [ + 68, + 483, + 499 + ], + [ + 66, + 497, + 498 + ], + [ + 76, + 306, + 301 + ], + [ + 73, + 299, + 298 + ], + [ + 71, + 296, + 298 + ], + [ + 70, + 499, + 498 + ], + [ + 70, + 499, + 499 + ], + [ + 72, + 498, + 504 + ], + [ + 71, + 490, + 502 + ], + [ + 71, + 501, + 500 + ], + [ + 71, + 501, + 499 + ], + [ + 71, + 499, + 501 + ] + ], + "spacings": [ + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ] + ] +} \ No newline at end of file diff --git a/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/checkpoint_final.pth b/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/checkpoint_final.pth new file mode 100644 index 0000000000000000000000000000000000000000..b51e2c70f577f94052efe908683e621310de4014 --- /dev/null +++ b/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/checkpoint_final.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ced0929a6ae2327f388ca4bb74dfca15acc111a68340b10442a2840895b5b5d8 +size 815577709 diff --git a/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/debug.json b/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/debug.json new file mode 100644 index 0000000000000000000000000000000000000000..e9883d8cd823a08a545621cc026089faf51295f7 --- /dev/null +++ b/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/debug.json @@ -0,0 +1,58 @@ +{ + "_best_ema": "0.047194228", + "aim_run": ">", + "batch_size": "2", + "configuration_manager": "{'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [48, 192, 192], 'median_image_size_in_voxels': [87.0, 308.0, 309.0], 'spacing': [3.0, 1.0, 1.0], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[1, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [1, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [1, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}, 'deep_supervision': False}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': False}", + "configuration_name": "3d_fullres", + "cudnn_version": 90501, + "current_epoch": "27", + "dataloader_train": "", + "dataloader_train.generator": "", + "dataloader_train.num_processes": "12", + "dataloader_train.transform": "Compose ( [RemoveLabelTransform( output_key = 'seg', input_key = 'seg', replace_with = 0, remove_label = -1 ), RenameTransform( delete_old = True, out_key = 'target', in_key = 'seg' ), NumpyToTensor( keys = ['data', 'target', 'mask'], cast_to = 'float' )] )", + "dataloader_val": "", + "dataloader_val.generator": "", + "dataloader_val.num_processes": "6", + "dataloader_val.transform": "Compose ( [RemoveLabelTransform( output_key = 'seg', input_key = 'seg', replace_with = 0, remove_label = -1 ), RenameTransform( delete_old = True, out_key = 'target', in_key = 'seg' ), NumpyToTensor( keys = ['data', 'target', 'mask'], cast_to = 'float' )] )", + "dataset_json": "{'labels': {'label_001': '1', 'background': 0}, 'channel_names': {'0': 'CT_zscore_synthrad'}, 'numTraining': 325, 'file_ending': '.mha'}", + "debug_custom": "{'run_hash': 'de0b335742114ac0a04510ad'}", + "decoder_type": "standard", + "device": "cuda:0", + "disable_checkpointing": "False", + "enable_deep_supervision": "False", + "fold": "0", + "folder_with_segs_from_previous_stage": "None", + "gpu_name": "NVIDIA H100", + "grad_scaler": "", + "hostname": "g030", + "image_loss_weight": "0.5", + "inference_allowed_mirroring_axes": "None", + "initial_lr": "0.01", + "is_cascaded": "False", + "is_ddp": "False", + "label_manager": "", + "local_rank": "0", + "log_file": "/datasets/work/hb-synthrad2023/work/synthrad2025/bw_workplace/data/nnunet_struct/results/Dataset542_synthrad2025_task2_CBCT_HN_pre_v2r_stitched_masked_both/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/training_log_2025_8_14_18_25_01.txt", + "logger": "", + "loss": "SynPerceptionLoss(\n (seg_model): ResidualEncoderUNet(\n (encoder): ResidualEncoder(\n (stem): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(1, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(1, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n (stages): Sequential(\n (0): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (1): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(32, 64, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(32, 64, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[1, 2, 2], stride=[1, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(32, 64, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(32, 64, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (2): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 128, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 128, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[2, 2, 2], stride=[2, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 128, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 128, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (3): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 256, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 256, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[2, 2, 2], stride=[2, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (4): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (5): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (4): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 320, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 320, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[2, 2, 2], stride=[2, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 320, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 320, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (4): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (5): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (5): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[1, 2, 2], stride=[1, 2, 2], padding=0)\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (4): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (5): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n )\n (decoder): UNetDecoder(\n (encoder): ResidualEncoder(\n (stem): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(1, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(1, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n (stages): Sequential(\n (0): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (1): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(32, 64, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(32, 64, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[1, 2, 2], stride=[1, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(32, 64, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(32, 64, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (2): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 128, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 128, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[2, 2, 2], stride=[2, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 128, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 128, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (3): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 256, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 256, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[2, 2, 2], stride=[2, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (4): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (5): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (4): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 320, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 320, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[2, 2, 2], stride=[2, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 320, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 320, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (4): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (5): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (5): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[1, 2, 2], stride=[1, 2, 2], padding=0)\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (4): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (5): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n )\n (stages): ModuleList(\n (0): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(640, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(640, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n (1): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(512, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(512, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n (2): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(256, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n (3): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(128, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n (4): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(64, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n )\n (transpconvs): ModuleList(\n (0): ConvTranspose3d(320, 320, kernel_size=(1, 2, 2), stride=(1, 2, 2))\n (1): ConvTranspose3d(320, 256, kernel_size=(2, 2, 2), stride=(2, 2, 2))\n (2): ConvTranspose3d(256, 128, kernel_size=(2, 2, 2), stride=(2, 2, 2))\n (3): ConvTranspose3d(128, 64, kernel_size=(2, 2, 2), stride=(2, 2, 2))\n (4): ConvTranspose3d(64, 32, kernel_size=(1, 2, 2), stride=(1, 2, 2))\n )\n (seg_layers): ModuleList(\n (0): Conv3d(320, 32, kernel_size=(1, 1, 1), stride=(1, 1, 1))\n (1): Conv3d(256, 32, kernel_size=(1, 1, 1), stride=(1, 1, 1))\n (2): Conv3d(128, 32, kernel_size=(1, 1, 1), stride=(1, 1, 1))\n (3): Conv3d(64, 32, kernel_size=(1, 1, 1), stride=(1, 1, 1))\n (4): Conv3d(32, 32, kernel_size=(1, 1, 1), stride=(1, 1, 1))\n )\n )\n )\n (L1): L1Loss()\n (image_loss): myMaskedMSE(\n (mse): myMSE()\n )\n)", + "lr_scheduler": "", + "my_init_kwargs": "{'plans': {'dataset_name': 'Dataset542_synthrad2025_task2_CBCT_HN_pre_v2r_stitched_masked_both', 'plans_name': 'nnUNetResEncUNetLPlans', 'original_median_spacing_after_transp': [3.0, 1.0, 1.0], 'original_median_shape_after_transp': [87, 308, 309], 'image_reader_writer': 'SimpleITKIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 30, 'patch_size': [320, 320], 'median_image_size_in_voxels': [308.0, 309.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 7, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}, '3d_fullres': {'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [48, 192, 192], 'median_image_size_in_voxels': [87.0, 308.0, 309.0], 'spacing': [3.0, 1.0, 1.0], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[1, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [1, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [1, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': False}}, 'experiment_planner_used': 'nnUNetPlannerResEncL', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 3071.0, 'mean': -215.1082763671875, 'median': -133.0, 'min': -1024.0, 'percentile_00_5': -1024.0, 'percentile_99_5': 1345.0, 'std': 459.63665771484375}}}, 'configuration': '3d_fullres', 'fold': 0, 'dataset_json': {'labels': {'label_001': '1', 'background': 0}, 'channel_names': {'0': 'CT_zscore_synthrad'}, 'numTraining': 325, 'file_ending': '.mha'}, 'unpack_dataset': True, 'device': device(type='cuda')}", + "network": "ResidualEncoderUNet", + "num_epochs": "1000", + "num_input_channels": "1", + "num_iterations_per_epoch": "250", + "num_val_iterations_per_epoch": "50", + "optimizer": "SGD (\nParameter Group 0\n dampening: 0\n differentiable: False\n foreach: None\n fused: None\n initial_lr: 0.01\n lr: 0.009765692859724779\n maximize: False\n momentum: 0.99\n nesterov: True\n weight_decay: 3e-05\n)", + "output_folder": "/datasets/work/hb-synthrad2023/work/synthrad2025/bw_workplace/data/nnunet_struct/results/Dataset542_synthrad2025_task2_CBCT_HN_pre_v2r_stitched_masked_both/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0", + "output_folder_base": "/datasets/work/hb-synthrad2023/work/synthrad2025/bw_workplace/data/nnunet_struct/results/Dataset542_synthrad2025_task2_CBCT_HN_pre_v2r_stitched_masked_both/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres", + "oversample_foreground_percent": "0.33", + "perception_masked": "True", + "plans_manager": "{'dataset_name': 'Dataset542_synthrad2025_task2_CBCT_HN_pre_v2r_stitched_masked_both', 'plans_name': 'nnUNetResEncUNetLPlans', 'original_median_spacing_after_transp': [3.0, 1.0, 1.0], 'original_median_shape_after_transp': [87, 308, 309], 'image_reader_writer': 'SimpleITKIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 30, 'patch_size': [320, 320], 'median_image_size_in_voxels': [308.0, 309.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 7, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}, '3d_fullres': {'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [48, 192, 192], 'median_image_size_in_voxels': [87.0, 308.0, 309.0], 'spacing': [3.0, 1.0, 1.0], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[1, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [1, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [1, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': False}}, 'experiment_planner_used': 'nnUNetPlannerResEncL', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 3071.0, 'mean': -215.1082763671875, 'median': -133.0, 'min': -1024.0, 'percentile_00_5': -1024.0, 'percentile_99_5': 1345.0, 'std': 459.63665771484375}}}", + "preprocessed_dataset_folder": "/datasets/work/hb-synthrad2023/work/synthrad2025/bw_workplace/data/nnunet_struct/preprocessed/Dataset542_synthrad2025_task2_CBCT_HN_pre_v2r_stitched_masked_both/nnUNetPlans_3d_fullres", + "preprocessed_dataset_folder_base": "/datasets/work/hb-synthrad2023/work/synthrad2025/bw_workplace/data/nnunet_struct/preprocessed/Dataset542_synthrad2025_task2_CBCT_HN_pre_v2r_stitched_masked_both", + "save_every": "50", + "torch_version": "2.7.1+cu126", + "unpack_dataset": "True", + "was_initialized": "True", + "weight_decay": "3e-05" +} \ No newline at end of file diff --git a/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/progress.png b/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/progress.png new file mode 100644 index 0000000000000000000000000000000000000000..27948462e07664c4e682c23b7dc7fef24cac9722 --- /dev/null +++ b/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/progress.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d87d6b783b54c578c4fb7db56c814d908815889146a7c6aad34673d1790dadc +size 490545 diff --git a/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/validation/summary.json b/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/validation/summary.json new file mode 100644 index 0000000000000000000000000000000000000000..d3133cde063b429e5a6e3942e3f83aac5b83c819 --- /dev/null +++ b/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/validation/summary.json @@ -0,0 +1,52 @@ +{ + "mae": { + "mean": 59.6831403703124, + "std": 13.282268575250406, + "max": 135.26334083952912, + "min": 43.70561993673689, + "25pc": 50.90544320106635, + "50pc": 57.59766416973342, + "75pc": 63.61140017268492, + "count": 65 + }, + "psnr": { + "mean": 30.41879186477032, + "std": 1.7822310331910258, + "max": 33.303479514662435, + "min": 21.938598217631913, + "25pc": 29.489967207335592, + "50pc": 30.549653942101994, + "75pc": 31.678537891293097, + "count": 65 + }, + "ms_ssim": { + "mean": 0.972537866604284, + "std": 0.023400539772748585, + "max": 0.9896922348656185, + "min": 0.8256950304841117, + "25pc": 0.972346153083238, + "50pc": 0.9793511650351168, + "75pc": 0.9834134511089297, + "count": 65 + }, + "DICE": { + "mean": 0.8757181415191063, + "std": 0.04152858997642459, + "max": 0.9331912994384766, + "min": 0.7493325471878052, + "25pc": 0.8536831736564636, + "50pc": 0.885571300983429, + "75pc": 0.907253623008728, + "count": 65 + }, + "HD95": { + "mean": 1.9038109889397254, + "std": 0.8689346520839407, + "max": 4.7832865715026855, + "min": 1.1818181276321411, + "25pc": 1.3928370475769043, + "50pc": 1.54265558719635, + "75pc": 2.0603861808776855, + "count": 65 + } +} \ No newline at end of file diff --git a/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/plans.json b/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/plans.json new file mode 100644 index 0000000000000000000000000000000000000000..6d8e76dc78899b03bf55293afe61fec1c2e6509c --- /dev/null +++ b/Dataset542/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/plans.json @@ -0,0 +1,356 @@ +{ + "dataset_name": "Dataset542_synthrad2025_task2_CBCT_HN_pre_v2r_stitched_masked_both", + "plans_name": "nnUNetResEncUNetLPlans", + "original_median_spacing_after_transp": [ + 3.0, + 1.0, + 1.0 + ], + "original_median_shape_after_transp": [ + 87, + 308, + 309 + ], + "image_reader_writer": "SimpleITKIO", + "transpose_forward": [ + 0, + 1, + 2 + ], + "transpose_backward": [ + 0, + 1, + 2 + ], + "configurations": { + "2d": { + "data_identifier": "nnUNetPlans_2d", + "preprocessor_name": "DefaultPreprocessor", + "batch_size": 30, + "patch_size": [ + 320, + 320 + ], + "median_image_size_in_voxels": [ + 308.0, + 309.0 + ], + "spacing": [ + 1.0, + 1.0 + ], + "normalization_schemes": [ + "CTNormalizationClippingSynthrad2025" + ], + "use_mask_for_norm": [ + false + ], + "resampling_fn_data": "resample_data_or_seg_to_shape", + "resampling_fn_seg": "resample_data_or_seg_to_shape", + "resampling_fn_data_kwargs": { + "is_seg": false, + "order": 3, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_seg_kwargs": { + "is_seg": true, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_probabilities": "resample_data_or_seg_to_shape", + "resampling_fn_probabilities_kwargs": { + "is_seg": false, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "architecture": { + "network_class_name": "dynamic_network_architectures.architectures.unet.ResidualEncoderUNet", + "arch_kwargs": { + "n_stages": 7, + "features_per_stage": [ + 32, + 64, + 128, + 256, + 512, + 512, + 512 + ], + "conv_op": "torch.nn.modules.conv.Conv2d", + "kernel_sizes": [ + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ] + ], + "strides": [ + [ + 1, + 1 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ] + ], + "n_blocks_per_stage": [ + 1, + 3, + 4, + 6, + 6, + 6, + 6 + ], + "n_conv_per_stage_decoder": [ + 1, + 1, + 1, + 1, + 1, + 1 + ], + "conv_bias": true, + "norm_op": "torch.nn.modules.instancenorm.InstanceNorm2d", + "norm_op_kwargs": { + "eps": 1e-05, + "affine": true + }, + "dropout_op": null, + "dropout_op_kwargs": null, + "nonlin": "torch.nn.LeakyReLU", + "nonlin_kwargs": { + "inplace": true + } + }, + "_kw_requires_import": [ + "conv_op", + "norm_op", + "dropout_op", + "nonlin" + ] + }, + "batch_dice": true + }, + "3d_fullres": { + "data_identifier": "nnUNetPlans_3d_fullres", + "preprocessor_name": "DefaultPreprocessor", + "batch_size": 2, + "patch_size": [ + 48, + 192, + 192 + ], + "median_image_size_in_voxels": [ + 87.0, + 308.0, + 309.0 + ], + "spacing": [ + 3.0, + 1.0, + 1.0 + ], + "normalization_schemes": [ + "CTNormalizationClippingSynthrad2025" + ], + "use_mask_for_norm": [ + false + ], + "resampling_fn_data": "resample_data_or_seg_to_shape", + "resampling_fn_seg": "resample_data_or_seg_to_shape", + "resampling_fn_data_kwargs": { + "is_seg": false, + "order": 3, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_seg_kwargs": { + "is_seg": true, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_probabilities": "resample_data_or_seg_to_shape", + "resampling_fn_probabilities_kwargs": { + "is_seg": false, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "architecture": { + "network_class_name": "dynamic_network_architectures.architectures.unet.ResidualEncoderUNet", + "arch_kwargs": { + "n_stages": 6, + "features_per_stage": [ + 32, + 64, + 128, + 256, + 320, + 320 + ], + "conv_op": "torch.nn.modules.conv.Conv3d", + "kernel_sizes": [ + [ + 1, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ] + ], + "strides": [ + [ + 1, + 1, + 1 + ], + [ + 1, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 1, + 2, + 2 + ] + ], + "n_blocks_per_stage": [ + 1, + 3, + 4, + 6, + 6, + 6 + ], + "n_conv_per_stage_decoder": [ + 1, + 1, + 1, + 1, + 1 + ], + "conv_bias": true, + "norm_op": "torch.nn.modules.instancenorm.InstanceNorm3d", + "norm_op_kwargs": { + "eps": 1e-05, + "affine": true + }, + "dropout_op": null, + "dropout_op_kwargs": null, + "nonlin": "torch.nn.LeakyReLU", + "nonlin_kwargs": { + "inplace": true + } + }, + "_kw_requires_import": [ + "conv_op", + "norm_op", + "dropout_op", + "nonlin" + ] + }, + "batch_dice": false + } + }, + "experiment_planner_used": "nnUNetPlannerResEncL", + "label_manager": "LabelManager", + "foreground_intensity_properties_per_channel": { + "0": { + "max": 3071.0, + "mean": -215.1082763671875, + "median": -133.0, + "min": -1024.0, + "percentile_00_5": -1024.0, + "percentile_99_5": 1345.0, + "std": 459.63665771484375 + } + } +} \ No newline at end of file diff --git a/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/dataset.json b/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/dataset.json new file mode 100644 index 0000000000000000000000000000000000000000..eb7b5fafd0abe77d0eaaa20fa981e33fdb34c9ed --- /dev/null +++ b/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/dataset.json @@ -0,0 +1,14 @@ +{ + "labels": { + "label_001": "1", + "background": 0 + }, + "channel_names": { + "0": "CT_zscore_synthrad" + }, + "numTraining": 321, + "file_ending": ".nii.gz", + "test_set": [ + "case_0000" + ] +} \ No newline at end of file diff --git a/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/dataset_fingerprint.json b/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/dataset_fingerprint.json new file mode 100644 index 0000000000000000000000000000000000000000..35b188a77f5820783e8dc6896b87f03b68ef7cf4 --- /dev/null +++ b/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/dataset_fingerprint.json @@ -0,0 +1,3228 @@ +{ + "foreground_intensity_properties_per_channel": { + "0": { + "max": 3071.0, + "mean": -330.8976135253906, + "median": -243.0, + "min": -1024.0, + "percentile_00_5": -1024.0, + "percentile_99_5": 563.0, + "std": 371.2642822265625 + } + }, + "median_relative_size_after_cropping": 1.0, + "shapes_after_crop": [ + [ + 81, + 311, + 310 + ], + [ + 78, + 307, + 308 + ], + [ + 80, + 359, + 451 + ], + [ + 81, + 450, + 450 + ], + [ + 88, + 310, + 311 + ], + [ + 81, + 377, + 451 + ], + [ + 87, + 309, + 309 + ], + [ + 80, + 370, + 451 + ], + [ + 81, + 370, + 451 + ], + [ + 80, + 449, + 453 + ], + [ + 81, + 380, + 448 + ], + [ + 87, + 311, + 311 + ], + [ + 80, + 429, + 448 + ], + [ + 87, + 311, + 307 + ], + [ + 86, + 316, + 311 + ], + [ + 87, + 308, + 311 + ], + [ + 87, + 312, + 308 + ], + [ + 88, + 307, + 308 + ], + [ + 86, + 314, + 310 + ], + [ + 79, + 312, + 310 + ], + [ + 87, + 308, + 311 + ], + [ + 87, + 310, + 312 + ], + [ + 85, + 310, + 319 + ], + [ + 87, + 310, + 309 + ], + [ + 87, + 310, + 309 + ], + [ + 81, + 308, + 309 + ], + [ + 81, + 290, + 285 + ], + [ + 88, + 288, + 291 + ], + [ + 88, + 310, + 310 + ], + [ + 88, + 308, + 297 + ], + [ + 87, + 310, + 309 + ], + [ + 86, + 316, + 309 + ], + [ + 84, + 308, + 309 + ], + [ + 87, + 310, + 311 + ], + [ + 87, + 311, + 308 + ], + [ + 86, + 314, + 309 + ], + [ + 88, + 310, + 299 + ], + [ + 87, + 312, + 309 + ], + [ + 88, + 309, + 309 + ], + [ + 87, + 310, + 289 + ], + [ + 88, + 308, + 309 + ], + [ + 74, + 308, + 313 + ], + [ + 88, + 308, + 309 + ], + [ + 82, + 310, + 308 + ], + [ + 88, + 309, + 307 + ], + [ + 88, + 311, + 309 + ], + [ + 67, + 309, + 312 + ], + [ + 86, + 314, + 309 + ], + [ + 87, + 309, + 313 + ], + [ + 80, + 296, + 286 + ], + [ + 87, + 308, + 309 + ], + [ + 81, + 309, + 311 + ], + [ + 88, + 308, + 307 + ], + [ + 87, + 307, + 309 + ], + [ + 86, + 308, + 313 + ], + [ + 86, + 314, + 309 + ], + [ + 87, + 312, + 308 + ], + [ + 87, + 311, + 311 + ], + [ + 87, + 311, + 309 + ], + [ + 86, + 313, + 312 + ], + [ + 86, + 317, + 311 + ], + [ + 87, + 310, + 312 + ], + [ + 87, + 313, + 310 + ], + [ + 87, + 312, + 309 + ], + [ + 76, + 307, + 293 + ], + [ + 78, + 450, + 434 + ], + [ + 79, + 450, + 456 + ], + [ + 77, + 425, + 446 + ], + [ + 76, + 452, + 432 + ], + [ + 82, + 449, + 449 + ], + [ + 81, + 451, + 448 + ], + [ + 80, + 449, + 425 + ], + [ + 81, + 452, + 451 + ], + [ + 79, + 449, + 455 + ], + [ + 73, + 440, + 456 + ], + [ + 77, + 452, + 442 + ], + [ + 80, + 449, + 453 + ], + [ + 78, + 450, + 436 + ], + [ + 80, + 451, + 454 + ], + [ + 81, + 451, + 450 + ], + [ + 80, + 452, + 453 + ], + [ + 80, + 452, + 449 + ], + [ + 74, + 454, + 433 + ], + [ + 79, + 449, + 455 + ], + [ + 81, + 448, + 452 + ], + [ + 80, + 453, + 450 + ], + [ + 80, + 449, + 449 + ], + [ + 81, + 451, + 450 + ], + [ + 78, + 437, + 438 + ], + [ + 79, + 454, + 429 + ], + [ + 77, + 454, + 457 + ], + [ + 81, + 451, + 433 + ], + [ + 79, + 455, + 450 + ], + [ + 79, + 457, + 452 + ], + [ + 82, + 451, + 449 + ], + [ + 80, + 449, + 455 + ], + [ + 81, + 450, + 449 + ], + [ + 79, + 447, + 448 + ], + [ + 80, + 450, + 452 + ], + [ + 81, + 449, + 451 + ], + [ + 81, + 450, + 446 + ], + [ + 81, + 451, + 450 + ], + [ + 62, + 451, + 449 + ], + [ + 80, + 449, + 454 + ], + [ + 81, + 450, + 450 + ], + [ + 80, + 451, + 453 + ], + [ + 82, + 450, + 447 + ], + [ + 82, + 449, + 449 + ], + [ + 80, + 450, + 425 + ], + [ + 78, + 452, + 457 + ], + [ + 80, + 430, + 423 + ], + [ + 77, + 448, + 429 + ], + [ + 78, + 449, + 458 + ], + [ + 80, + 449, + 451 + ], + [ + 81, + 451, + 449 + ], + [ + 81, + 452, + 442 + ], + [ + 79, + 454, + 456 + ], + [ + 79, + 450, + 402 + ], + [ + 79, + 450, + 456 + ], + [ + 81, + 452, + 449 + ], + [ + 80, + 453, + 449 + ], + [ + 77, + 457, + 453 + ], + [ + 82, + 450, + 449 + ], + [ + 79, + 450, + 442 + ], + [ + 81, + 450, + 450 + ], + [ + 80, + 449, + 432 + ], + [ + 81, + 448, + 454 + ], + [ + 70, + 451, + 457 + ], + [ + 80, + 451, + 454 + ], + [ + 80, + 425, + 449 + ], + [ + 87, + 310, + 298 + ], + [ + 87, + 289, + 309 + ], + [ + 87, + 293, + 309 + ], + [ + 86, + 307, + 314 + ], + [ + 88, + 308, + 309 + ], + [ + 88, + 309, + 308 + ], + [ + 75, + 449, + 462 + ], + [ + 88, + 309, + 309 + ], + [ + 87, + 311, + 308 + ], + [ + 87, + 278, + 315 + ], + [ + 87, + 308, + 312 + ], + [ + 81, + 450, + 451 + ], + [ + 88, + 289, + 308 + ], + [ + 85, + 317, + 314 + ], + [ + 86, + 311, + 315 + ], + [ + 82, + 421, + 450 + ], + [ + 87, + 309, + 284 + ], + [ + 81, + 450, + 447 + ], + [ + 88, + 311, + 311 + ], + [ + 88, + 311, + 312 + ], + [ + 81, + 422, + 394 + ], + [ + 87, + 288, + 312 + ], + [ + 87, + 312, + 300 + ], + [ + 81, + 452, + 451 + ], + [ + 87, + 311, + 311 + ], + [ + 84, + 316, + 318 + ], + [ + 80, + 451, + 452 + ], + [ + 87, + 289, + 311 + ], + [ + 81, + 450, + 451 + ], + [ + 86, + 316, + 309 + ], + [ + 81, + 448, + 449 + ], + [ + 86, + 310, + 302 + ], + [ + 87, + 314, + 310 + ], + [ + 81, + 450, + 448 + ], + [ + 88, + 309, + 309 + ], + [ + 86, + 313, + 314 + ], + [ + 80, + 448, + 453 + ], + [ + 87, + 308, + 314 + ], + [ + 84, + 320, + 310 + ], + [ + 81, + 451, + 451 + ], + [ + 88, + 310, + 306 + ], + [ + 82, + 308, + 309 + ], + [ + 87, + 290, + 312 + ], + [ + 88, + 289, + 280 + ], + [ + 88, + 309, + 308 + ], + [ + 75, + 427, + 452 + ], + [ + 80, + 435, + 433 + ], + [ + 86, + 294, + 310 + ], + [ + 88, + 310, + 304 + ], + [ + 80, + 453, + 451 + ], + [ + 86, + 297, + 315 + ], + [ + 85, + 313, + 314 + ], + [ + 87, + 311, + 308 + ], + [ + 88, + 307, + 309 + ], + [ + 87, + 308, + 311 + ], + [ + 84, + 321, + 315 + ], + [ + 87, + 309, + 310 + ], + [ + 85, + 309, + 299 + ], + [ + 81, + 309, + 314 + ], + [ + 74, + 309, + 308 + ], + [ + 86, + 297, + 313 + ], + [ + 87, + 310, + 298 + ], + [ + 88, + 310, + 310 + ], + [ + 99, + 308, + 308 + ], + [ + 128, + 384, + 392 + ], + [ + 70, + 392, + 393 + ], + [ + 128, + 392, + 393 + ], + [ + 71, + 472, + 499 + ], + [ + 71, + 463, + 499 + ], + [ + 75, + 468, + 494 + ], + [ + 130, + 471, + 499 + ], + [ + 133, + 479, + 499 + ], + [ + 114, + 394, + 406 + ], + [ + 137, + 469, + 499 + ], + [ + 128, + 467, + 499 + ], + [ + 70, + 466, + 498 + ], + [ + 99, + 310, + 311 + ], + [ + 131, + 477, + 499 + ], + [ + 71, + 467, + 499 + ], + [ + 74, + 499, + 496 + ], + [ + 132, + 469, + 499 + ], + [ + 99, + 308, + 307 + ], + [ + 130, + 472, + 499 + ], + [ + 93, + 310, + 309 + ], + [ + 128, + 465, + 499 + ], + [ + 98, + 308, + 315 + ], + [ + 71, + 467, + 499 + ], + [ + 91, + 312, + 307 + ], + [ + 71, + 468, + 499 + ], + [ + 75, + 464, + 499 + ], + [ + 72, + 469, + 499 + ], + [ + 123, + 499, + 499 + ], + [ + 72, + 469, + 499 + ], + [ + 131, + 499, + 499 + ], + [ + 131, + 467, + 499 + ], + [ + 71, + 465, + 499 + ], + [ + 139, + 467, + 499 + ], + [ + 137, + 466, + 499 + ], + [ + 71, + 465, + 495 + ], + [ + 129, + 499, + 499 + ], + [ + 70, + 466, + 494 + ], + [ + 133, + 473, + 499 + ], + [ + 131, + 468, + 499 + ], + [ + 131, + 471, + 499 + ], + [ + 128, + 467, + 499 + ], + [ + 131, + 473, + 499 + ], + [ + 122, + 499, + 498 + ], + [ + 132, + 446, + 499 + ], + [ + 73, + 468, + 499 + ], + [ + 99, + 316, + 308 + ], + [ + 133, + 474, + 499 + ], + [ + 131, + 499, + 487 + ], + [ + 130, + 470, + 496 + ], + [ + 79, + 474, + 499 + ], + [ + 70, + 467, + 499 + ], + [ + 128, + 472, + 499 + ], + [ + 71, + 471, + 499 + ], + [ + 72, + 540, + 539 + ], + [ + 79, + 467, + 499 + ], + [ + 75, + 468, + 492 + ], + [ + 74, + 470, + 492 + ], + [ + 72, + 468, + 499 + ], + [ + 71, + 466, + 499 + ], + [ + 132, + 470, + 499 + ], + [ + 131, + 472, + 499 + ], + [ + 130, + 469, + 499 + ], + [ + 67, + 497, + 499 + ], + [ + 66, + 477, + 497 + ], + [ + 70, + 478, + 502 + ], + [ + 69, + 499, + 500 + ], + [ + 69, + 497, + 486 + ], + [ + 66, + 496, + 498 + ], + [ + 67, + 449, + 498 + ], + [ + 71, + 478, + 503 + ], + [ + 66, + 496, + 497 + ], + [ + 68, + 499, + 499 + ], + [ + 55, + 480, + 501 + ], + [ + 66, + 497, + 498 + ], + [ + 60, + 477, + 500 + ], + [ + 69, + 482, + 479 + ], + [ + 70, + 497, + 503 + ], + [ + 68, + 500, + 495 + ], + [ + 65, + 500, + 499 + ], + [ + 70, + 477, + 502 + ], + [ + 68, + 499, + 499 + ], + [ + 67, + 490, + 497 + ], + [ + 67, + 496, + 499 + ], + [ + 65, + 477, + 497 + ], + [ + 68, + 492, + 498 + ], + [ + 69, + 499, + 498 + ], + [ + 72, + 440, + 494 + ], + [ + 73, + 503, + 501 + ], + [ + 74, + 505, + 502 + ], + [ + 67, + 497, + 478 + ], + [ + 67, + 499, + 482 + ], + [ + 70, + 440, + 482 + ], + [ + 66, + 498, + 496 + ], + [ + 67, + 464, + 499 + ], + [ + 70, + 481, + 501 + ], + [ + 66, + 490, + 478 + ], + [ + 67, + 498, + 497 + ], + [ + 65, + 497, + 496 + ], + [ + 68, + 499, + 497 + ], + [ + 67, + 478, + 498 + ], + [ + 72, + 501, + 504 + ], + [ + 70, + 494, + 507 + ], + [ + 66, + 498, + 496 + ], + [ + 71, + 297, + 296 + ], + [ + 69, + 500, + 498 + ], + [ + 69, + 500, + 501 + ], + [ + 68, + 498, + 500 + ], + [ + 69, + 500, + 499 + ], + [ + 66, + 497, + 498 + ], + [ + 68, + 499, + 498 + ], + [ + 68, + 477, + 500 + ], + [ + 75, + 481, + 500 + ], + [ + 66, + 488, + 497 + ], + [ + 73, + 505, + 500 + ], + [ + 78, + 512, + 503 + ], + [ + 67, + 498, + 499 + ], + [ + 71, + 500, + 503 + ], + [ + 72, + 501, + 502 + ], + [ + 72, + 503, + 499 + ], + [ + 72, + 299, + 297 + ], + [ + 68, + 500, + 500 + ], + [ + 68, + 499, + 499 + ], + [ + 69, + 493, + 501 + ], + [ + 70, + 500, + 501 + ], + [ + 67, + 499, + 498 + ], + [ + 67, + 498, + 497 + ], + [ + 68, + 498, + 498 + ] + ], + "spacings": [ + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ], + [ + 3.0, + 1.0, + 1.0 + ] + ] +} \ No newline at end of file diff --git a/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/checkpoint_final.pth b/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/checkpoint_final.pth new file mode 100644 index 0000000000000000000000000000000000000000..9361bc47780b666da036e89ff7c6944c608b9b34 --- /dev/null +++ b/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/checkpoint_final.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1695e6f921488dbc372d8c7600f748c8d56fcf28cf71ea3c14bcacc78cf2aabf +size 815580525 diff --git a/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/debug.json b/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/debug.json new file mode 100644 index 0000000000000000000000000000000000000000..5409d8d5fbe721ce9b7eec29b96efb1c8ed155b2 --- /dev/null +++ b/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/debug.json @@ -0,0 +1,58 @@ +{ + "_best_ema": "None", + "aim_run": ">", + "batch_size": "2", + "configuration_manager": "{'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [40, 224, 192], 'median_image_size_in_voxels': [81.0, 450.0, 450.0], 'spacing': [3.0, 1.0, 1.0], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[1, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [1, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [1, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}, 'deep_supervision': False}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}", + "configuration_name": "3d_fullres", + "cudnn_version": 90501, + "current_epoch": "0", + "dataloader_train": "", + "dataloader_train.generator": "", + "dataloader_train.num_processes": "12", + "dataloader_train.transform": "Compose ( [RemoveLabelTransform( output_key = 'seg', input_key = 'seg', replace_with = 0, remove_label = -1 ), RenameTransform( delete_old = True, out_key = 'target', in_key = 'seg' ), NumpyToTensor( keys = ['data', 'target', 'mask'], cast_to = 'float' )] )", + "dataloader_val": "", + "dataloader_val.generator": "", + "dataloader_val.num_processes": "6", + "dataloader_val.transform": "Compose ( [RemoveLabelTransform( output_key = 'seg', input_key = 'seg', replace_with = 0, remove_label = -1 ), RenameTransform( delete_old = True, out_key = 'target', in_key = 'seg' ), NumpyToTensor( keys = ['data', 'target', 'mask'], cast_to = 'float' )] )", + "dataset_json": "{'labels': {'label_001': '1', 'background': 0}, 'channel_names': {'0': 'CT_zscore_synthrad'}, 'numTraining': 321, 'file_ending': '.mha'}", + "debug_custom": "{'run_hash': '01a79fd07dfb4718b450ee50'}", + "decoder_type": "standard", + "device": "cuda:0", + "disable_checkpointing": "False", + "enable_deep_supervision": "False", + "fold": "0", + "folder_with_segs_from_previous_stage": "None", + "gpu_name": "NVIDIA H100", + "grad_scaler": "", + "hostname": "g024", + "image_loss_weight": "0.5", + "inference_allowed_mirroring_axes": "None", + "initial_lr": "0.01", + "is_cascaded": "False", + "is_ddp": "False", + "label_manager": "", + "local_rank": "0", + "log_file": "/datasets/work/hb-synthrad2023/work/synthrad2025/bw_workplace/data/nnunet_struct/results/Dataset544_synthrad2025_task2_CBCT_TH_pre_v2r_stitched_masked_both/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/training_log_2025_8_14_18_17_20.txt", + "logger": "", + "loss": "SynPerceptionLoss(\n (seg_model): ResidualEncoderUNet(\n (encoder): ResidualEncoder(\n (stem): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(1, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(1, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n (stages): Sequential(\n (0): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (1): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(32, 64, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(32, 64, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[1, 2, 2], stride=[1, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(32, 64, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(32, 64, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (2): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 128, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 128, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[2, 2, 2], stride=[2, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 128, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 128, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (3): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 256, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 256, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[2, 2, 2], stride=[2, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (4): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (5): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (4): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 320, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 320, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[2, 2, 2], stride=[2, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 320, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 320, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (4): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (5): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (5): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[1, 2, 2], stride=[1, 2, 2], padding=0)\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (4): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (5): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n )\n (decoder): UNetDecoder(\n (encoder): ResidualEncoder(\n (stem): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(1, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(1, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n (stages): Sequential(\n (0): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(32, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (1): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(32, 64, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(32, 64, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[1, 2, 2], stride=[1, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(32, 64, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(32, 64, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (2): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 128, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 128, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[2, 2, 2], stride=[2, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(64, 128, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(64, 128, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (3): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 256, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 256, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[2, 2, 2], stride=[2, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(128, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(128, 256, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (4): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (5): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (4): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 320, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 320, kernel_size=(3, 3, 3), stride=(2, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[2, 2, 2], stride=[2, 2, 2], padding=0)\n (1): ConvDropoutNormReLU(\n (conv): Conv3d(256, 320, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(256, 320, kernel_size=(1, 1, 1), stride=(1, 1, 1), bias=False)\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (4): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (5): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n (5): StackedResidualBlocks(\n (blocks): Sequential(\n (0): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 2, 2), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n (skip): Sequential(\n (0): AvgPool3d(kernel_size=[1, 2, 2], stride=[1, 2, 2], padding=0)\n )\n )\n (1): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (2): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (3): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (4): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n (5): BasicBlockD(\n (conv1): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n (conv2): ConvDropoutNormReLU(\n (conv): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (all_modules): Sequential(\n (0): Conv3d(320, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n )\n )\n (nonlin2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n )\n (stages): ModuleList(\n (0): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(640, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(640, 320, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n (1): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(512, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(512, 256, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n (2): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(256, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(256, 128, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n (3): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(128, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (norm): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(128, 64, kernel_size=(3, 3, 3), stride=(1, 1, 1), padding=(1, 1, 1))\n (1): InstanceNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n (4): StackedConvBlocks(\n (convs): Sequential(\n (0): ConvDropoutNormReLU(\n (conv): Conv3d(64, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (norm): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (nonlin): LeakyReLU(negative_slope=0.01, inplace=True)\n (all_modules): Sequential(\n (0): Conv3d(64, 32, kernel_size=(1, 3, 3), stride=(1, 1, 1), padding=(0, 1, 1))\n (1): InstanceNorm3d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=False)\n (2): LeakyReLU(negative_slope=0.01, inplace=True)\n )\n )\n )\n )\n )\n (transpconvs): ModuleList(\n (0): ConvTranspose3d(320, 320, kernel_size=(1, 2, 2), stride=(1, 2, 2))\n (1): ConvTranspose3d(320, 256, kernel_size=(2, 2, 2), stride=(2, 2, 2))\n (2): ConvTranspose3d(256, 128, kernel_size=(2, 2, 2), stride=(2, 2, 2))\n (3): ConvTranspose3d(128, 64, kernel_size=(2, 2, 2), stride=(2, 2, 2))\n (4): ConvTranspose3d(64, 32, kernel_size=(1, 2, 2), stride=(1, 2, 2))\n )\n (seg_layers): ModuleList(\n (0): Conv3d(320, 62, kernel_size=(1, 1, 1), stride=(1, 1, 1))\n (1): Conv3d(256, 62, kernel_size=(1, 1, 1), stride=(1, 1, 1))\n (2): Conv3d(128, 62, kernel_size=(1, 1, 1), stride=(1, 1, 1))\n (3): Conv3d(64, 62, kernel_size=(1, 1, 1), stride=(1, 1, 1))\n (4): Conv3d(32, 62, kernel_size=(1, 1, 1), stride=(1, 1, 1))\n )\n )\n )\n (L1): L1Loss()\n (image_loss): myMaskedMSE(\n (mse): myMSE()\n )\n)", + "lr_scheduler": "", + "my_init_kwargs": "{'plans': {'dataset_name': 'Dataset544_synthrad2025_task2_CBCT_TH_pre_v2r_stitched_masked_both', 'plans_name': 'nnUNetResEncUNetLPlans', 'original_median_spacing_after_transp': [3.0, 1.0, 1.0], 'original_median_shape_after_transp': [81, 450, 450], 'image_reader_writer': 'SimpleITKIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 13, 'patch_size': [512, 448], 'median_image_size_in_voxels': [450.0, 450.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 7, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}, '3d_lowres': {'data_identifier': 'nnUNetResEncUNetLPlans_3d_lowres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [56, 224, 192], 'median_image_size_in_voxels': [81, 298, 298], 'spacing': [3.0, 1.512589724855112, 1.512589724855112], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [2, 2, 2], [2, 2, 2], [2, 2, 2], [1, 2, 2], [1, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': False, 'next_stage': '3d_cascade_fullres'}, '3d_fullres': {'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [40, 224, 192], 'median_image_size_in_voxels': [81.0, 450.0, 450.0], 'spacing': [3.0, 1.0, 1.0], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[1, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [1, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [1, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}, '3d_cascade_fullres': {'inherits_from': '3d_fullres', 'previous_stage': '3d_lowres'}}, 'experiment_planner_used': 'nnUNetPlannerResEncL', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 3071.0, 'mean': -330.8976135253906, 'median': -243.0, 'min': -1024.0, 'percentile_00_5': -1024.0, 'percentile_99_5': 563.0, 'std': 371.2642822265625}}}, 'configuration': '3d_fullres', 'fold': 0, 'dataset_json': {'labels': {'label_001': '1', 'background': 0}, 'channel_names': {'0': 'CT_zscore_synthrad'}, 'numTraining': 321, 'file_ending': '.mha'}, 'unpack_dataset': True, 'device': device(type='cuda')}", + "network": "ResidualEncoderUNet", + "num_epochs": "1000", + "num_input_channels": "1", + "num_iterations_per_epoch": "250", + "num_val_iterations_per_epoch": "50", + "optimizer": "SGD (\nParameter Group 0\n dampening: 0\n differentiable: False\n foreach: None\n fused: None\n initial_lr: 0.01\n lr: 0.01\n maximize: False\n momentum: 0.99\n nesterov: True\n weight_decay: 3e-05\n)", + "output_folder": "/datasets/work/hb-synthrad2023/work/synthrad2025/bw_workplace/data/nnunet_struct/results/Dataset544_synthrad2025_task2_CBCT_TH_pre_v2r_stitched_masked_both/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0", + "output_folder_base": "/datasets/work/hb-synthrad2023/work/synthrad2025/bw_workplace/data/nnunet_struct/results/Dataset544_synthrad2025_task2_CBCT_TH_pre_v2r_stitched_masked_both/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres", + "oversample_foreground_percent": "0.33", + "perception_masked": "True", + "plans_manager": "{'dataset_name': 'Dataset544_synthrad2025_task2_CBCT_TH_pre_v2r_stitched_masked_both', 'plans_name': 'nnUNetResEncUNetLPlans', 'original_median_spacing_after_transp': [3.0, 1.0, 1.0], 'original_median_shape_after_transp': [81, 450, 450], 'image_reader_writer': 'SimpleITKIO', 'transpose_forward': [0, 1, 2], 'transpose_backward': [0, 1, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 13, 'patch_size': [512, 448], 'median_image_size_in_voxels': [450.0, 450.0], 'spacing': [1.0, 1.0], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 7, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}, '3d_lowres': {'data_identifier': 'nnUNetResEncUNetLPlans_3d_lowres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [56, 224, 192], 'median_image_size_in_voxels': [81, 298, 298], 'spacing': [3.0, 1.512589724855112, 1.512589724855112], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [2, 2, 2], [2, 2, 2], [2, 2, 2], [1, 2, 2], [1, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': False, 'next_stage': '3d_cascade_fullres'}, '3d_fullres': {'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [40, 224, 192], 'median_image_size_in_voxels': [81.0, 450.0, 450.0], 'spacing': [3.0, 1.0, 1.0], 'normalization_schemes': ['CTNormalizationClippingSynthrad2025'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[1, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [1, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [1, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}, '3d_cascade_fullres': {'inherits_from': '3d_fullres', 'previous_stage': '3d_lowres'}}, 'experiment_planner_used': 'nnUNetPlannerResEncL', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 3071.0, 'mean': -330.8976135253906, 'median': -243.0, 'min': -1024.0, 'percentile_00_5': -1024.0, 'percentile_99_5': 563.0, 'std': 371.2642822265625}}}", + "preprocessed_dataset_folder": "/datasets/work/hb-synthrad2023/work/synthrad2025/bw_workplace/data/nnunet_struct/preprocessed/Dataset544_synthrad2025_task2_CBCT_TH_pre_v2r_stitched_masked_both/nnUNetPlans_3d_fullres", + "preprocessed_dataset_folder_base": "/datasets/work/hb-synthrad2023/work/synthrad2025/bw_workplace/data/nnunet_struct/preprocessed/Dataset544_synthrad2025_task2_CBCT_TH_pre_v2r_stitched_masked_both", + "save_every": "50", + "torch_version": "2.7.1+cu126", + "unpack_dataset": "True", + "was_initialized": "True", + "weight_decay": "3e-05" +} \ No newline at end of file diff --git a/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/progress.png b/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/progress.png new file mode 100644 index 0000000000000000000000000000000000000000..e9af218b59918ce87bd27dd891d648d6548ef008 --- /dev/null +++ b/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/progress.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddf72b0f141c0785923ac73f5821c75e7f6d5daa970742590d9792210414ca78 +size 618327 diff --git a/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/validation/summary.json b/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/validation/summary.json new file mode 100644 index 0000000000000000000000000000000000000000..d933cd753b831547bac32060a1341a6e6bd99136 --- /dev/null +++ b/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/fold_0/validation/summary.json @@ -0,0 +1,52 @@ +{ + "mae": { + "mean": 52.80768787193642, + "std": 39.25411217734592, + "max": 349.4295323444315, + "min": 30.53782153506361, + "25pc": 39.67259547669727, + "50pc": 44.417437064864046, + "75pc": 56.57117028196328, + "count": 65 + }, + "psnr": { + "mean": 32.25481819350785, + "std": 2.9858789867732187, + "max": 36.561440579128075, + "min": 17.068229372936194, + "25pc": 30.947542147774367, + "50pc": 32.57369524597034, + "75pc": 34.17962467969445, + "count": 65 + }, + "ms_ssim": { + "mean": 0.9536834487302785, + "std": 0.08019347284318636, + "max": 0.9915810123537975, + "min": 0.3802523438307981, + "25pc": 0.9586479045957355, + "50pc": 0.9741513563984106, + "75pc": 0.9824337046998175, + "count": 65 + }, + "DICE": { + "mean": 0.8256282861416157, + "std": 0.06491444113684663, + "max": 0.9275574088096619, + "min": 0.5898815393447876, + "25pc": 0.7742491364479065, + "50pc": 0.8340623378753662, + "75pc": 0.8758383393287659, + "count": 65 + }, + "HD95": { + "mean": 4.208385368493887, + "std": 3.814029574946056, + "max": 30.388620376586914, + "min": 1.1522142887115479, + "25pc": 2.4057328701019287, + "50pc": 3.2774264812469482, + "75pc": 4.871885299682617, + "count": 65 + } +} \ No newline at end of file diff --git a/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/plans.json b/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/plans.json new file mode 100644 index 0000000000000000000000000000000000000000..50e2c9f3ed7b45a897c4c512d4721da21702777e --- /dev/null +++ b/Dataset544/nnUNetTrainerMRCT_loss_masked_perception_masked__nnUNetResEncUNetLPlans__3d_fullres/plans.json @@ -0,0 +1,521 @@ +{ + "dataset_name": "Dataset544_synthrad2025_task2_CBCT_TH_pre_v2r_stitched_masked_both", + "plans_name": "nnUNetResEncUNetLPlans", + "original_median_spacing_after_transp": [ + 3.0, + 1.0, + 1.0 + ], + "original_median_shape_after_transp": [ + 81, + 450, + 450 + ], + "image_reader_writer": "SimpleITKIO", + "transpose_forward": [ + 0, + 1, + 2 + ], + "transpose_backward": [ + 0, + 1, + 2 + ], + "configurations": { + "2d": { + "data_identifier": "nnUNetPlans_2d", + "preprocessor_name": "DefaultPreprocessor", + "batch_size": 13, + "patch_size": [ + 512, + 448 + ], + "median_image_size_in_voxels": [ + 450.0, + 450.0 + ], + "spacing": [ + 1.0, + 1.0 + ], + "normalization_schemes": [ + "CTNormalizationClippingSynthrad2025" + ], + "use_mask_for_norm": [ + false + ], + "resampling_fn_data": "resample_data_or_seg_to_shape", + "resampling_fn_seg": "resample_data_or_seg_to_shape", + "resampling_fn_data_kwargs": { + "is_seg": false, + "order": 3, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_seg_kwargs": { + "is_seg": true, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_probabilities": "resample_data_or_seg_to_shape", + "resampling_fn_probabilities_kwargs": { + "is_seg": false, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "architecture": { + "network_class_name": "dynamic_network_architectures.architectures.unet.ResidualEncoderUNet", + "arch_kwargs": { + "n_stages": 7, + "features_per_stage": [ + 32, + 64, + 128, + 256, + 512, + 512, + 512 + ], + "conv_op": "torch.nn.modules.conv.Conv2d", + "kernel_sizes": [ + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ] + ], + "strides": [ + [ + 1, + 1 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ] + ], + "n_blocks_per_stage": [ + 1, + 3, + 4, + 6, + 6, + 6, + 6 + ], + "n_conv_per_stage_decoder": [ + 1, + 1, + 1, + 1, + 1, + 1 + ], + "conv_bias": true, + "norm_op": "torch.nn.modules.instancenorm.InstanceNorm2d", + "norm_op_kwargs": { + "eps": 1e-05, + "affine": true + }, + "dropout_op": null, + "dropout_op_kwargs": null, + "nonlin": "torch.nn.LeakyReLU", + "nonlin_kwargs": { + "inplace": true + } + }, + "_kw_requires_import": [ + "conv_op", + "norm_op", + "dropout_op", + "nonlin" + ] + }, + "batch_dice": true + }, + "3d_lowres": { + "data_identifier": "nnUNetResEncUNetLPlans_3d_lowres", + "preprocessor_name": "DefaultPreprocessor", + "batch_size": 2, + "patch_size": [ + 56, + 224, + 192 + ], + "median_image_size_in_voxels": [ + 81, + 298, + 298 + ], + "spacing": [ + 3.0, + 1.512589724855112, + 1.512589724855112 + ], + "normalization_schemes": [ + "CTNormalizationClippingSynthrad2025" + ], + "use_mask_for_norm": [ + false + ], + "resampling_fn_data": "resample_data_or_seg_to_shape", + "resampling_fn_seg": "resample_data_or_seg_to_shape", + "resampling_fn_data_kwargs": { + "is_seg": false, + "order": 3, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_seg_kwargs": { + "is_seg": true, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_probabilities": "resample_data_or_seg_to_shape", + "resampling_fn_probabilities_kwargs": { + "is_seg": false, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "architecture": { + "network_class_name": "dynamic_network_architectures.architectures.unet.ResidualEncoderUNet", + "arch_kwargs": { + "n_stages": 6, + "features_per_stage": [ + 32, + 64, + 128, + 256, + 320, + 320 + ], + "conv_op": "torch.nn.modules.conv.Conv3d", + "kernel_sizes": [ + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ] + ], + "strides": [ + [ + 1, + 1, + 1 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 1, + 2, + 2 + ], + [ + 1, + 2, + 2 + ] + ], + "n_blocks_per_stage": [ + 1, + 3, + 4, + 6, + 6, + 6 + ], + "n_conv_per_stage_decoder": [ + 1, + 1, + 1, + 1, + 1 + ], + "conv_bias": true, + "norm_op": "torch.nn.modules.instancenorm.InstanceNorm3d", + "norm_op_kwargs": { + "eps": 1e-05, + "affine": true + }, + "dropout_op": null, + "dropout_op_kwargs": null, + "nonlin": "torch.nn.LeakyReLU", + "nonlin_kwargs": { + "inplace": true + } + }, + "_kw_requires_import": [ + "conv_op", + "norm_op", + "dropout_op", + "nonlin" + ] + }, + "batch_dice": false, + "next_stage": "3d_cascade_fullres" + }, + "3d_fullres": { + "data_identifier": "nnUNetPlans_3d_fullres", + "preprocessor_name": "DefaultPreprocessor", + "batch_size": 2, + "patch_size": [ + 40, + 224, + 192 + ], + "median_image_size_in_voxels": [ + 81.0, + 450.0, + 450.0 + ], + "spacing": [ + 3.0, + 1.0, + 1.0 + ], + "normalization_schemes": [ + "CTNormalizationClippingSynthrad2025" + ], + "use_mask_for_norm": [ + false + ], + "resampling_fn_data": "resample_data_or_seg_to_shape", + "resampling_fn_seg": "resample_data_or_seg_to_shape", + "resampling_fn_data_kwargs": { + "is_seg": false, + "order": 3, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_seg_kwargs": { + "is_seg": true, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_probabilities": "resample_data_or_seg_to_shape", + "resampling_fn_probabilities_kwargs": { + "is_seg": false, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "architecture": { + "network_class_name": "dynamic_network_architectures.architectures.unet.ResidualEncoderUNet", + "arch_kwargs": { + "n_stages": 6, + "features_per_stage": [ + 32, + 64, + 128, + 256, + 320, + 320 + ], + "conv_op": "torch.nn.modules.conv.Conv3d", + "kernel_sizes": [ + [ + 1, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ] + ], + "strides": [ + [ + 1, + 1, + 1 + ], + [ + 1, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 1, + 2, + 2 + ] + ], + "n_blocks_per_stage": [ + 1, + 3, + 4, + 6, + 6, + 6 + ], + "n_conv_per_stage_decoder": [ + 1, + 1, + 1, + 1, + 1 + ], + "conv_bias": true, + "norm_op": "torch.nn.modules.instancenorm.InstanceNorm3d", + "norm_op_kwargs": { + "eps": 1e-05, + "affine": true + }, + "dropout_op": null, + "dropout_op_kwargs": null, + "nonlin": "torch.nn.LeakyReLU", + "nonlin_kwargs": { + "inplace": true + } + }, + "_kw_requires_import": [ + "conv_op", + "norm_op", + "dropout_op", + "nonlin" + ] + }, + "batch_dice": true + }, + "3d_cascade_fullres": { + "inherits_from": "3d_fullres", + "previous_stage": "3d_lowres" + } + }, + "experiment_planner_used": "nnUNetPlannerResEncL", + "label_manager": "LabelManager", + "foreground_intensity_properties_per_channel": { + "0": { + "max": 3071.0, + "mean": -330.8976135253906, + "median": -243.0, + "min": -1024.0, + "percentile_00_5": -1024.0, + "percentile_99_5": 563.0, + "std": 371.2642822265625 + } + } +} \ No newline at end of file