Update README file

README.md

@@ -6,16 +6,16 @@ tags: []
 ## Original result
 ```
 IoU metric: bbox
- Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.024
- Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.032
- Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.027
- Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.092
- Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.070
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.014
+ Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.023
+ Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.016
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.190
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.037
  Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.074
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.254
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.464
- Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.389
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.006
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.084
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.466
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.393
  Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.552
  Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000
 ```
@@ -23,17 +23,17 @@ IoU metric: bbox
 ## After training result
 ```
 IoU metric: bbox
- Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.452
- Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.566
- Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.515
- Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.461
- Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.521
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.569
+ Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.707
+ Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.680
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.549
+ Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.775
  Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.174
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.636
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.718
- Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.615
- Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.839
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.202
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.640
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.664
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.548
+ Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.800
  Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = -1.000
 ```
 
@@ -43,33 +43,53 @@ IoU metric: bbox
 - lr: 5e-06
 - dropout_rate: 0.1
 - weight_decay: 0.05
-- max_epochs: 20
+- max_epochs: 40
 - train samples: 61
 
 ## Logging
 ### Training process
 ```
-{'validation_loss': tensor(2.7805, device='cuda:0'), 'validation_loss_ce': tensor(0.7506, device='cuda:0'), 'validation_loss_bbox': tensor(0.1834, device='cuda:0'), 'validation_loss_giou': tensor(0.5565, device='cuda:0'), 'validation_cardinality_error': tensor(65.2500, device='cuda:0')}
-{'training_loss': tensor(1.3692, device='cuda:0'), 'train_loss_ce': tensor(0.6425, device='cuda:0'), 'train_loss_bbox': tensor(0.0420, device='cuda:0'), 'train_loss_giou': tensor(0.2583, device='cuda:0'), 'train_cardinality_error': tensor(49., device='cuda:0'), 'validation_loss': tensor(1.9955, device='cuda:0'), 'validation_loss_ce': tensor(0.6964, device='cuda:0'), 'validation_loss_bbox': tensor(0.0949, device='cuda:0'), 'validation_loss_giou': tensor(0.4123, device='cuda:0'), 'validation_cardinality_error': tensor(54.8462, device='cuda:0')}
-{'training_loss': tensor(0.7776, device='cuda:0'), 'train_loss_ce': tensor(0.4950, device='cuda:0'), 'train_loss_bbox': tensor(0.0243, device='cuda:0'), 'train_loss_giou': tensor(0.0805, device='cuda:0'), 'train_cardinality_error': tensor(8., device='cuda:0'), 'validation_loss': tensor(1.6961, device='cuda:0'), 'validation_loss_ce': tensor(0.6763, device='cuda:0'), 'validation_loss_bbox': tensor(0.0584, device='cuda:0'), 'validation_loss_giou': tensor(0.3638, device='cuda:0'), 'validation_cardinality_error': tensor(48.2308, device='cuda:0')}
-{'training_loss': tensor(0.7145, device='cuda:0'), 'train_loss_ce': tensor(0.4630, device='cuda:0'), 'train_loss_bbox': tensor(0.0209, device='cuda:0'), 'train_loss_giou': tensor(0.0735, device='cuda:0'), 'train_cardinality_error': tensor(2., device='cuda:0'), 'validation_loss': tensor(1.5552, device='cuda:0'), 'validation_loss_ce': tensor(0.6569, device='cuda:0'), 'validation_loss_bbox': tensor(0.0531, device='cuda:0'), 'validation_loss_giou': tensor(0.3164, device='cuda:0'), 'validation_cardinality_error': tensor(39.6154, device='cuda:0')}
-{'training_loss': tensor(0.7801, device='cuda:0'), 'train_loss_ce': tensor(0.6306, device='cuda:0'), 'train_loss_bbox': tensor(0.0154, device='cuda:0'), 'train_loss_giou': tensor(0.0363, device='cuda:0'), 'train_cardinality_error': tensor(41., device='cuda:0'), 'validation_loss': tensor(1.4825, device='cuda:0'), 'validation_loss_ce': tensor(0.6332, device='cuda:0'), 'validation_loss_bbox': tensor(0.0563, device='cuda:0'), 'validation_loss_giou': tensor(0.2839, device='cuda:0'), 'validation_cardinality_error': tensor(31.3846, device='cuda:0')}
-{'training_loss': tensor(1.1043, device='cuda:0'), 'train_loss_ce': tensor(0.6572, device='cuda:0'), 'train_loss_bbox': tensor(0.0306, device='cuda:0'), 'train_loss_giou': tensor(0.1471, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.4447, device='cuda:0'), 'validation_loss_ce': tensor(0.6126, device='cuda:0'), 'validation_loss_bbox': tensor(0.0545, device='cuda:0'), 'validation_loss_giou': tensor(0.2798, device='cuda:0'), 'validation_cardinality_error': tensor(25., device='cuda:0')}
-{'training_loss': tensor(0.7144, device='cuda:0'), 'train_loss_ce': tensor(0.5595, device='cuda:0'), 'train_loss_bbox': tensor(0.0076, device='cuda:0'), 'train_loss_giou': tensor(0.0585, device='cuda:0'), 'train_cardinality_error': tensor(10., device='cuda:0'), 'validation_loss': tensor(1.6468, device='cuda:0'), 'validation_loss_ce': tensor(0.5955, device='cuda:0'), 'validation_loss_bbox': tensor(0.0691, device='cuda:0'), 'validation_loss_giou': tensor(0.3530, device='cuda:0'), 'validation_cardinality_error': tensor(20.7692, device='cuda:0')}
-{'training_loss': tensor(0.7055, device='cuda:0'), 'train_loss_ce': tensor(0.5208, device='cuda:0'), 'train_loss_bbox': tensor(0.0134, device='cuda:0'), 'train_loss_giou': tensor(0.0587, device='cuda:0'), 'train_cardinality_error': tensor(4., device='cuda:0'), 'validation_loss': tensor(1.4338, device='cuda:0'), 'validation_loss_ce': tensor(0.5776, device='cuda:0'), 'validation_loss_bbox': tensor(0.0511, device='cuda:0'), 'validation_loss_giou': tensor(0.3002, device='cuda:0'), 'validation_cardinality_error': tensor(15.6154, device='cuda:0')}
-{'training_loss': tensor(0.6106, device='cuda:0'), 'train_loss_ce': tensor(0.3884, device='cuda:0'), 'train_loss_bbox': tensor(0.0299, device='cuda:0'), 'train_loss_giou': tensor(0.0363, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.5870, device='cuda:0'), 'validation_loss_ce': tensor(0.5597, device='cuda:0'), 'validation_loss_bbox': tensor(0.0673, device='cuda:0'), 'validation_loss_giou': tensor(0.3454, device='cuda:0'), 'validation_cardinality_error': tensor(11.7692, device='cuda:0')}
-{'training_loss': tensor(0.7294, device='cuda:0'), 'train_loss_ce': tensor(0.5093, device='cuda:0'), 'train_loss_bbox': tensor(0.0122, device='cuda:0'), 'train_loss_giou': tensor(0.0795, device='cuda:0'), 'train_cardinality_error': tensor(2., device='cuda:0'), 'validation_loss': tensor(1.3645, device='cuda:0'), 'validation_loss_ce': tensor(0.5496, device='cuda:0'), 'validation_loss_bbox': tensor(0.0514, device='cuda:0'), 'validation_loss_giou': tensor(0.2789, device='cuda:0'), 'validation_cardinality_error': tensor(8.9231, device='cuda:0')}
-{'training_loss': tensor(0.7845, device='cuda:0'), 'train_loss_ce': tensor(0.5872, device='cuda:0'), 'train_loss_bbox': tensor(0.0111, device='cuda:0'), 'train_loss_giou': tensor(0.0710, device='cuda:0'), 'train_cardinality_error': tensor(4., device='cuda:0'), 'validation_loss': tensor(1.5335, device='cuda:0'), 'validation_loss_ce': tensor(0.5374, device='cuda:0'), 'validation_loss_bbox': tensor(0.0669, device='cuda:0'), 'validation_loss_giou': tensor(0.3307, device='cuda:0'), 'validation_cardinality_error': tensor(6.6154, device='cuda:0')}
-{'training_loss': tensor(0.3810, device='cuda:0'), 'train_loss_ce': tensor(0.3312, device='cuda:0'), 'train_loss_bbox': tensor(0.0028, device='cuda:0'), 'train_loss_giou': tensor(0.0179, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(1.4720, device='cuda:0'), 'validation_loss_ce': tensor(0.5209, device='cuda:0'), 'validation_loss_bbox': tensor(0.0572, device='cuda:0'), 'validation_loss_giou': tensor(0.3326, device='cuda:0'), 'validation_cardinality_error': tensor(5.7692, device='cuda:0')}
-{'training_loss': tensor(0.9936, device='cuda:0'), 'train_loss_ce': tensor(0.7054, device='cuda:0'), 'train_loss_bbox': tensor(0.0178, device='cuda:0'), 'train_loss_giou': tensor(0.0996, device='cuda:0'), 'train_cardinality_error': tensor(13., device='cuda:0'), 'validation_loss': tensor(1.4543, device='cuda:0'), 'validation_loss_ce': tensor(0.5103, device='cuda:0'), 'validation_loss_bbox': tensor(0.0641, device='cuda:0'), 'validation_loss_giou': tensor(0.3117, device='cuda:0'), 'validation_cardinality_error': tensor(4.7692, device='cuda:0')}
-{'training_loss': tensor(0.5030, device='cuda:0'), 'train_loss_ce': tensor(0.3787, device='cuda:0'), 'train_loss_bbox': tensor(0.0170, device='cuda:0'), 'train_loss_giou': tensor(0.0196, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.6086, device='cuda:0'), 'validation_loss_ce': tensor(0.5086, device='cuda:0'), 'validation_loss_bbox': tensor(0.0739, device='cuda:0'), 'validation_loss_giou': tensor(0.3652, device='cuda:0'), 'validation_cardinality_error': tensor(4.3077, device='cuda:0')}
-{'training_loss': tensor(0.6252, device='cuda:0'), 'train_loss_ce': tensor(0.3750, device='cuda:0'), 'train_loss_bbox': tensor(0.0278, device='cuda:0'), 'train_loss_giou': tensor(0.0556, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.0120, device='cuda:0'), 'validation_loss_ce': tensor(0.4808, device='cuda:0'), 'validation_loss_bbox': tensor(0.0253, device='cuda:0'), 'validation_loss_giou': tensor(0.2022, device='cuda:0'), 'validation_cardinality_error': tensor(3.3077, device='cuda:0')}
-{'training_loss': tensor(1.2132, device='cuda:0'), 'train_loss_ce': tensor(0.7323, device='cuda:0'), 'train_loss_bbox': tensor(0.0422, device='cuda:0'), 'train_loss_giou': tensor(0.1350, device='cuda:0'), 'train_cardinality_error': tensor(11., device='cuda:0'), 'validation_loss': tensor(0.8473, device='cuda:0'), 'validation_loss_ce': tensor(0.4638, device='cuda:0'), 'validation_loss_bbox': tensor(0.0177, device='cuda:0'), 'validation_loss_giou': tensor(0.1475, device='cuda:0'), 'validation_cardinality_error': tensor(2.6923, device='cuda:0')}
-{'training_loss': tensor(0.4347, device='cuda:0'), 'train_loss_ce': tensor(0.3896, device='cuda:0'), 'train_loss_bbox': tensor(0.0037, device='cuda:0'), 'train_loss_giou': tensor(0.0132, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.8593, device='cuda:0'), 'validation_loss_ce': tensor(0.4498, device='cuda:0'), 'validation_loss_bbox': tensor(0.0195, device='cuda:0'), 'validation_loss_giou': tensor(0.1560, device='cuda:0'), 'validation_cardinality_error': tensor(2.6154, device='cuda:0')}
-{'training_loss': tensor(0.4821, device='cuda:0'), 'train_loss_ce': tensor(0.4537, device='cuda:0'), 'train_loss_bbox': tensor(0.0014, device='cuda:0'), 'train_loss_giou': tensor(0.0106, device='cuda:0'), 'train_cardinality_error': tensor(2., device='cuda:0'), 'validation_loss': tensor(0.9156, device='cuda:0'), 'validation_loss_ce': tensor(0.4412, device='cuda:0'), 'validation_loss_bbox': tensor(0.0223, device='cuda:0'), 'validation_loss_giou': tensor(0.1814, device='cuda:0'), 'validation_cardinality_error': tensor(2.6154, device='cuda:0')}
-{'training_loss': tensor(0.5579, device='cuda:0'), 'train_loss_ce': tensor(0.3216, device='cuda:0'), 'train_loss_bbox': tensor(0.0260, device='cuda:0'), 'train_loss_giou': tensor(0.0531, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.8854, device='cuda:0'), 'validation_loss_ce': tensor(0.4308, device='cuda:0'), 'validation_loss_bbox': tensor(0.0209, device='cuda:0'), 'validation_loss_giou': tensor(0.1750, device='cuda:0'), 'validation_cardinality_error': tensor(2.6154, device='cuda:0')}
-{'training_loss': tensor(0.3421, device='cuda:0'), 'train_loss_ce': tensor(0.3072, device='cuda:0'), 'train_loss_bbox': tensor(0.0029, device='cuda:0'), 'train_loss_giou': tensor(0.0103, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.8500, device='cuda:0'), 'validation_loss_ce': tensor(0.4143, device='cuda:0'), 'validation_loss_bbox': tensor(0.0191, device='cuda:0'), 'validation_loss_giou': tensor(0.1700, device='cuda:0'), 'validation_cardinality_error': tensor(2.3846, device='cuda:0')}
-{'training_loss': tensor(0.4960, device='cuda:0'), 'train_loss_ce': tensor(0.3847, device='cuda:0'), 'train_loss_bbox': tensor(0.0085, device='cuda:0'), 'train_loss_giou': tensor(0.0343, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.8550, device='cuda:0'), 'validation_loss_ce': tensor(0.4080, device='cuda:0'), 'validation_loss_bbox': tensor(0.0216, device='cuda:0'), 'validation_loss_giou': tensor(0.1695, device='cuda:0'), 'validation_cardinality_error': tensor(2.3077, device='cuda:0')}
+{'validation_loss': tensor(2.6890, device='cuda:0'), 'validation_loss_ce': tensor(0.7041, device='cuda:0'), 'validation_loss_bbox': tensor(0.1392, device='cuda:0'), 'validation_loss_giou': tensor(0.6446, device='cuda:0'), 'validation_cardinality_error': tensor(68.2500, device='cuda:0')}
+{'training_loss': tensor(0.8197, device='cuda:0'), 'train_loss_ce': tensor(0.6827, device='cuda:0'), 'train_loss_bbox': tensor(0.0069, device='cuda:0'), 'train_loss_giou': tensor(0.0512, device='cuda:0'), 'train_cardinality_error': tensor(28., device='cuda:0'), 'validation_loss': tensor(1.9387, device='cuda:0'), 'validation_loss_ce': tensor(0.6735, device='cuda:0'), 'validation_loss_bbox': tensor(0.0883, device='cuda:0'), 'validation_loss_giou': tensor(0.4118, device='cuda:0'), 'validation_cardinality_error': tensor(40.6154, device='cuda:0')}
+{'training_loss': tensor(1.0182, device='cuda:0'), 'train_loss_ce': tensor(0.6821, device='cuda:0'), 'train_loss_bbox': tensor(0.0331, device='cuda:0'), 'train_loss_giou': tensor(0.0853, device='cuda:0'), 'train_cardinality_error': tensor(19., device='cuda:0'), 'validation_loss': tensor(1.7603, device='cuda:0'), 'validation_loss_ce': tensor(0.6590, device='cuda:0'), 'validation_loss_bbox': tensor(0.0742, device='cuda:0'), 'validation_loss_giou': tensor(0.3652, device='cuda:0'), 'validation_cardinality_error': tensor(37.0769, device='cuda:0')}
+{'training_loss': tensor(2.5174, device='cuda:0'), 'train_loss_ce': tensor(0.6131, device='cuda:0'), 'train_loss_bbox': tensor(0.1633, device='cuda:0'), 'train_loss_giou': tensor(0.5439, device='cuda:0'), 'train_cardinality_error': tensor(7., device='cuda:0'), 'validation_loss': tensor(1.6039, device='cuda:0'), 'validation_loss_ce': tensor(0.6434, device='cuda:0'), 'validation_loss_bbox': tensor(0.0577, device='cuda:0'), 'validation_loss_giou': tensor(0.3360, device='cuda:0'), 'validation_cardinality_error': tensor(25.2308, device='cuda:0')}
+{'training_loss': tensor(0.6921, device='cuda:0'), 'train_loss_ce': tensor(0.5446, device='cuda:0'), 'train_loss_bbox': tensor(0.0102, device='cuda:0'), 'train_loss_giou': tensor(0.0483, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(1.3713, device='cuda:0'), 'validation_loss_ce': tensor(0.6267, device='cuda:0'), 'validation_loss_bbox': tensor(0.0456, device='cuda:0'), 'validation_loss_giou': tensor(0.2582, device='cuda:0'), 'validation_cardinality_error': tensor(18.0769, device='cuda:0')}
+{'training_loss': tensor(4.2869, device='cuda:0'), 'train_loss_ce': tensor(0.6386, device='cuda:0'), 'train_loss_bbox': tensor(0.3740, device='cuda:0'), 'train_loss_giou': tensor(0.8893, device='cuda:0'), 'train_cardinality_error': tensor(2., device='cuda:0'), 'validation_loss': tensor(1.1874, device='cuda:0'), 'validation_loss_ce': tensor(0.6103, device='cuda:0'), 'validation_loss_bbox': tensor(0.0346, device='cuda:0'), 'validation_loss_giou': tensor(0.2020, device='cuda:0'), 'validation_cardinality_error': tensor(13.7692, device='cuda:0')}
+{'training_loss': tensor(0.7044, device='cuda:0'), 'train_loss_ce': tensor(0.4590, device='cuda:0'), 'train_loss_bbox': tensor(0.0204, device='cuda:0'), 'train_loss_giou': tensor(0.0716, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.5443, device='cuda:0'), 'validation_loss_ce': tensor(0.5929, device='cuda:0'), 'validation_loss_bbox': tensor(0.0645, device='cuda:0'), 'validation_loss_giou': tensor(0.3144, device='cuda:0'), 'validation_cardinality_error': tensor(10.4615, device='cuda:0')}
+{'training_loss': tensor(0.9410, device='cuda:0'), 'train_loss_ce': tensor(0.6810, device='cuda:0'), 'train_loss_bbox': tensor(0.0120, device='cuda:0'), 'train_loss_giou': tensor(0.0999, device='cuda:0'), 'train_cardinality_error': tensor(11., device='cuda:0'), 'validation_loss': tensor(1.3133, device='cuda:0'), 'validation_loss_ce': tensor(0.5824, device='cuda:0'), 'validation_loss_bbox': tensor(0.0444, device='cuda:0'), 'validation_loss_giou': tensor(0.2544, device='cuda:0'), 'validation_cardinality_error': tensor(8.6923, device='cuda:0')}
+{'training_loss': tensor(0.5475, device='cuda:0'), 'train_loss_ce': tensor(0.4755, device='cuda:0'), 'train_loss_bbox': tensor(0.0040, device='cuda:0'), 'train_loss_giou': tensor(0.0261, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.2459, device='cuda:0'), 'validation_loss_ce': tensor(0.5700, device='cuda:0'), 'validation_loss_bbox': tensor(0.0413, device='cuda:0'), 'validation_loss_giou': tensor(0.2347, device='cuda:0'), 'validation_cardinality_error': tensor(8., device='cuda:0')}
+{'training_loss': tensor(1.1077, device='cuda:0'), 'train_loss_ce': tensor(0.6080, device='cuda:0'), 'train_loss_bbox': tensor(0.0200, device='cuda:0'), 'train_loss_giou': tensor(0.1999, device='cuda:0'), 'train_cardinality_error': tensor(3., device='cuda:0'), 'validation_loss': tensor(1.1507, device='cuda:0'), 'validation_loss_ce': tensor(0.5592, device='cuda:0'), 'validation_loss_bbox': tensor(0.0325, device='cuda:0'), 'validation_loss_giou': tensor(0.2146, device='cuda:0'), 'validation_cardinality_error': tensor(6.4615, device='cuda:0')}
+{'training_loss': tensor(0.4938, device='cuda:0'), 'train_loss_ce': tensor(0.4045, device='cuda:0'), 'train_loss_bbox': tensor(0.0035, device='cuda:0'), 'train_loss_giou': tensor(0.0358, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.1810, device='cuda:0'), 'validation_loss_ce': tensor(0.5480, device='cuda:0'), 'validation_loss_bbox': tensor(0.0335, device='cuda:0'), 'validation_loss_giou': tensor(0.2327, device='cuda:0'), 'validation_cardinality_error': tensor(5.0769, device='cuda:0')}
+{'training_loss': tensor(0.5889, device='cuda:0'), 'train_loss_ce': tensor(0.4328, device='cuda:0'), 'train_loss_bbox': tensor(0.0169, device='cuda:0'), 'train_loss_giou': tensor(0.0357, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.0876, device='cuda:0'), 'validation_loss_ce': tensor(0.5336, device='cuda:0'), 'validation_loss_bbox': tensor(0.0303, device='cuda:0'), 'validation_loss_giou': tensor(0.2014, device='cuda:0'), 'validation_cardinality_error': tensor(4.1538, device='cuda:0')}
+{'training_loss': tensor(0.6849, device='cuda:0'), 'train_loss_ce': tensor(0.5288, device='cuda:0'), 'train_loss_bbox': tensor(0.0162, device='cuda:0'), 'train_loss_giou': tensor(0.0375, device='cuda:0'), 'train_cardinality_error': tensor(2., device='cuda:0'), 'validation_loss': tensor(1.1762, device='cuda:0'), 'validation_loss_ce': tensor(0.5274, device='cuda:0'), 'validation_loss_bbox': tensor(0.0358, device='cuda:0'), 'validation_loss_giou': tensor(0.2349, device='cuda:0'), 'validation_cardinality_error': tensor(3.9231, device='cuda:0')}
+{'training_loss': tensor(0.5448, device='cuda:0'), 'train_loss_ce': tensor(0.4532, device='cuda:0'), 'train_loss_bbox': tensor(0.0034, device='cuda:0'), 'train_loss_giou': tensor(0.0373, device='cuda:0'), 'train_cardinality_error': tensor(2., device='cuda:0'), 'validation_loss': tensor(1.0657, device='cuda:0'), 'validation_loss_ce': tensor(0.5102, device='cuda:0'), 'validation_loss_bbox': tensor(0.0320, device='cuda:0'), 'validation_loss_giou': tensor(0.1978, device='cuda:0'), 'validation_cardinality_error': tensor(3.3846, device='cuda:0')}
+{'training_loss': tensor(0.4614, device='cuda:0'), 'train_loss_ce': tensor(0.3967, device='cuda:0'), 'train_loss_bbox': tensor(0.0038, device='cuda:0'), 'train_loss_giou': tensor(0.0228, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.0666, device='cuda:0'), 'validation_loss_ce': tensor(0.5024, device='cuda:0'), 'validation_loss_bbox': tensor(0.0282, device='cuda:0'), 'validation_loss_giou': tensor(0.2115, device='cuda:0'), 'validation_cardinality_error': tensor(3.0769, device='cuda:0')}
+{'training_loss': tensor(0.8316, device='cuda:0'), 'train_loss_ce': tensor(0.6080, device='cuda:0'), 'train_loss_bbox': tensor(0.0217, device='cuda:0'), 'train_loss_giou': tensor(0.0576, device='cuda:0'), 'train_cardinality_error': tensor(6., device='cuda:0'), 'validation_loss': tensor(1.1255, device='cuda:0'), 'validation_loss_ce': tensor(0.4948, device='cuda:0'), 'validation_loss_bbox': tensor(0.0333, device='cuda:0'), 'validation_loss_giou': tensor(0.2321, device='cuda:0'), 'validation_cardinality_error': tensor(3., device='cuda:0')}
+{'training_loss': tensor(0.3968, device='cuda:0'), 'train_loss_ce': tensor(0.3305, device='cuda:0'), 'train_loss_bbox': tensor(0.0058, device='cuda:0'), 'train_loss_giou': tensor(0.0186, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(1.0655, device='cuda:0'), 'validation_loss_ce': tensor(0.4890, device='cuda:0'), 'validation_loss_bbox': tensor(0.0280, device='cuda:0'), 'validation_loss_giou': tensor(0.2183, device='cuda:0'), 'validation_cardinality_error': tensor(2.6923, device='cuda:0')}
+{'training_loss': tensor(0.4433, device='cuda:0'), 'train_loss_ce': tensor(0.3818, device='cuda:0'), 'train_loss_bbox': tensor(0.0059, device='cuda:0'), 'train_loss_giou': tensor(0.0159, device='cuda:0'), 'train_cardinality_error': tensor(2., device='cuda:0'), 'validation_loss': tensor(1.1138, device='cuda:0'), 'validation_loss_ce': tensor(0.4814, device='cuda:0'), 'validation_loss_bbox': tensor(0.0361, device='cuda:0'), 'validation_loss_giou': tensor(0.2258, device='cuda:0'), 'validation_cardinality_error': tensor(2.3846, device='cuda:0')}
+{'training_loss': tensor(0.7553, device='cuda:0'), 'train_loss_ce': tensor(0.5547, device='cuda:0'), 'train_loss_bbox': tensor(0.0123, device='cuda:0'), 'train_loss_giou': tensor(0.0696, device='cuda:0'), 'train_cardinality_error': tensor(5., device='cuda:0'), 'validation_loss': tensor(1.1168, device='cuda:0'), 'validation_loss_ce': tensor(0.4722, device='cuda:0'), 'validation_loss_bbox': tensor(0.0374, device='cuda:0'), 'validation_loss_giou': tensor(0.2289, device='cuda:0'), 'validation_cardinality_error': tensor(2.3846, device='cuda:0')}
+{'training_loss': tensor(0.3290, device='cuda:0'), 'train_loss_ce': tensor(0.3057, device='cuda:0'), 'train_loss_bbox': tensor(0.0025, device='cuda:0'), 'train_loss_giou': tensor(0.0053, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.1099, device='cuda:0'), 'validation_loss_ce': tensor(0.4635, device='cuda:0'), 'validation_loss_bbox': tensor(0.0369, device='cuda:0'), 'validation_loss_giou': tensor(0.2309, device='cuda:0'), 'validation_cardinality_error': tensor(2.2308, device='cuda:0')}
+{'training_loss': tensor(0.5072, device='cuda:0'), 'train_loss_ce': tensor(0.4575, device='cuda:0'), 'train_loss_bbox': tensor(0.0043, device='cuda:0'), 'train_loss_giou': tensor(0.0142, device='cuda:0'), 'train_cardinality_error': tensor(2., device='cuda:0'), 'validation_loss': tensor(1.0318, device='cuda:0'), 'validation_loss_ce': tensor(0.4618, device='cuda:0'), 'validation_loss_bbox': tensor(0.0296, device='cuda:0'), 'validation_loss_giou': tensor(0.2111, device='cuda:0'), 'validation_cardinality_error': tensor(2.2308, device='cuda:0')}
+{'training_loss': tensor(0.4039, device='cuda:0'), 'train_loss_ce': tensor(0.2866, device='cuda:0'), 'train_loss_bbox': tensor(0.0154, device='cuda:0'), 'train_loss_giou': tensor(0.0202, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.0966, device='cuda:0'), 'validation_loss_ce': tensor(0.4515, device='cuda:0'), 'validation_loss_bbox': tensor(0.0376, device='cuda:0'), 'validation_loss_giou': tensor(0.2285, device='cuda:0'), 'validation_cardinality_error': tensor(2.2308, device='cuda:0')}
+{'training_loss': tensor(0.3389, device='cuda:0'), 'train_loss_ce': tensor(0.2745, device='cuda:0'), 'train_loss_bbox': tensor(0.0094, device='cuda:0'), 'train_loss_giou': tensor(0.0088, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.9492, device='cuda:0'), 'validation_loss_ce': tensor(0.4383, device='cuda:0'), 'validation_loss_bbox': tensor(0.0267, device='cuda:0'), 'validation_loss_giou': tensor(0.1888, device='cuda:0'), 'validation_cardinality_error': tensor(2.3077, device='cuda:0')}
+{'training_loss': tensor(0.4502, device='cuda:0'), 'train_loss_ce': tensor(0.4224, device='cuda:0'), 'train_loss_bbox': tensor(0.0011, device='cuda:0'), 'train_loss_giou': tensor(0.0112, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.0500, device='cuda:0'), 'validation_loss_ce': tensor(0.4322, device='cuda:0'), 'validation_loss_bbox': tensor(0.0350, device='cuda:0'), 'validation_loss_giou': tensor(0.2213, device='cuda:0'), 'validation_cardinality_error': tensor(2.1538, device='cuda:0')}
+{'training_loss': tensor(0.3770, device='cuda:0'), 'train_loss_ce': tensor(0.2961, device='cuda:0'), 'train_loss_bbox': tensor(0.0093, device='cuda:0'), 'train_loss_giou': tensor(0.0172, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.1149, device='cuda:0'), 'validation_loss_ce': tensor(0.4247, device='cuda:0'), 'validation_loss_bbox': tensor(0.0386, device='cuda:0'), 'validation_loss_giou': tensor(0.2485, device='cuda:0'), 'validation_cardinality_error': tensor(2.0769, device='cuda:0')}
+{'training_loss': tensor(0.4584, device='cuda:0'), 'train_loss_ce': tensor(0.3948, device='cuda:0'), 'train_loss_bbox': tensor(0.0064, device='cuda:0'), 'train_loss_giou': tensor(0.0158, device='cuda:0'), 'train_cardinality_error': tensor(2., device='cuda:0'), 'validation_loss': tensor(1.1380, device='cuda:0'), 'validation_loss_ce': tensor(0.4232, device='cuda:0'), 'validation_loss_bbox': tensor(0.0378, device='cuda:0'), 'validation_loss_giou': tensor(0.2628, device='cuda:0'), 'validation_cardinality_error': tensor(2.0769, device='cuda:0')}
+{'training_loss': tensor(0.3421, device='cuda:0'), 'train_loss_ce': tensor(0.2475, device='cuda:0'), 'train_loss_bbox': tensor(0.0112, device='cuda:0'), 'train_loss_giou': tensor(0.0192, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(1.1390, device='cuda:0'), 'validation_loss_ce': tensor(0.4207, device='cuda:0'), 'validation_loss_bbox': tensor(0.0380, device='cuda:0'), 'validation_loss_giou': tensor(0.2642, device='cuda:0'), 'validation_cardinality_error': tensor(2.0769, device='cuda:0')}
+{'training_loss': tensor(0.4257, device='cuda:0'), 'train_loss_ce': tensor(0.3720, device='cuda:0'), 'train_loss_bbox': tensor(0.0057, device='cuda:0'), 'train_loss_giou': tensor(0.0126, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(1.0459, device='cuda:0'), 'validation_loss_ce': tensor(0.4058, device='cuda:0'), 'validation_loss_bbox': tensor(0.0358, device='cuda:0'), 'validation_loss_giou': tensor(0.2307, device='cuda:0'), 'validation_cardinality_error': tensor(1.6923, device='cuda:0')}
+{'training_loss': tensor(0.2241, device='cuda:0'), 'train_loss_ce': tensor(0.2102, device='cuda:0'), 'train_loss_bbox': tensor(0.0016, device='cuda:0'), 'train_loss_giou': tensor(0.0030, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(1.0909, device='cuda:0'), 'validation_loss_ce': tensor(0.3993, device='cuda:0'), 'validation_loss_bbox': tensor(0.0399, device='cuda:0'), 'validation_loss_giou': tensor(0.2460, device='cuda:0'), 'validation_cardinality_error': tensor(1.6923, device='cuda:0')}
+{'training_loss': tensor(0.4053, device='cuda:0'), 'train_loss_ce': tensor(0.3580, device='cuda:0'), 'train_loss_bbox': tensor(0.0042, device='cuda:0'), 'train_loss_giou': tensor(0.0131, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(1.0366, device='cuda:0'), 'validation_loss_ce': tensor(0.3996, device='cuda:0'), 'validation_loss_bbox': tensor(0.0336, device='cuda:0'), 'validation_loss_giou': tensor(0.2344, device='cuda:0'), 'validation_cardinality_error': tensor(1.7692, device='cuda:0')}
+{'training_loss': tensor(0.2177, device='cuda:0'), 'train_loss_ce': tensor(0.1971, device='cuda:0'), 'train_loss_bbox': tensor(0.0008, device='cuda:0'), 'train_loss_giou': tensor(0.0083, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.8821, device='cuda:0'), 'validation_loss_ce': tensor(0.3821, device='cuda:0'), 'validation_loss_bbox': tensor(0.0261, device='cuda:0'), 'validation_loss_giou': tensor(0.1848, device='cuda:0'), 'validation_cardinality_error': tensor(1.4615, device='cuda:0')}
+{'training_loss': tensor(0.2556, device='cuda:0'), 'train_loss_ce': tensor(0.1958, device='cuda:0'), 'train_loss_bbox': tensor(0.0075, device='cuda:0'), 'train_loss_giou': tensor(0.0110, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.9517, device='cuda:0'), 'validation_loss_ce': tensor(0.3761, device='cuda:0'), 'validation_loss_bbox': tensor(0.0307, device='cuda:0'), 'validation_loss_giou': tensor(0.2111, device='cuda:0'), 'validation_cardinality_error': tensor(1.8462, device='cuda:0')}
+{'training_loss': tensor(0.2276, device='cuda:0'), 'train_loss_ce': tensor(0.1822, device='cuda:0'), 'train_loss_bbox': tensor(0.0026, device='cuda:0'), 'train_loss_giou': tensor(0.0163, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.9540, device='cuda:0'), 'validation_loss_ce': tensor(0.3651, device='cuda:0'), 'validation_loss_bbox': tensor(0.0308, device='cuda:0'), 'validation_loss_giou': tensor(0.2175, device='cuda:0'), 'validation_cardinality_error': tensor(1.7692, device='cuda:0')}
+{'training_loss': tensor(0.2031, device='cuda:0'), 'train_loss_ce': tensor(0.1681, device='cuda:0'), 'train_loss_bbox': tensor(0.0015, device='cuda:0'), 'train_loss_giou': tensor(0.0138, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.9900, device='cuda:0'), 'validation_loss_ce': tensor(0.3618, device='cuda:0'), 'validation_loss_bbox': tensor(0.0332, device='cuda:0'), 'validation_loss_giou': tensor(0.2310, device='cuda:0'), 'validation_cardinality_error': tensor(1.4615, device='cuda:0')}
+{'training_loss': tensor(0.6779, device='cuda:0'), 'train_loss_ce': tensor(0.4923, device='cuda:0'), 'train_loss_bbox': tensor(0.0074, device='cuda:0'), 'train_loss_giou': tensor(0.0742, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.9209, device='cuda:0'), 'validation_loss_ce': tensor(0.3567, device='cuda:0'), 'validation_loss_bbox': tensor(0.0315, device='cuda:0'), 'validation_loss_giou': tensor(0.2033, device='cuda:0'), 'validation_cardinality_error': tensor(1.4615, device='cuda:0')}
+{'training_loss': tensor(2.5319, device='cuda:0'), 'train_loss_ce': tensor(0.4393, device='cuda:0'), 'train_loss_bbox': tensor(0.1542, device='cuda:0'), 'train_loss_giou': tensor(0.6607, device='cuda:0'), 'train_cardinality_error': tensor(2., device='cuda:0'), 'validation_loss': tensor(1.0136, device='cuda:0'), 'validation_loss_ce': tensor(0.3559, device='cuda:0'), 'validation_loss_bbox': tensor(0.0335, device='cuda:0'), 'validation_loss_giou': tensor(0.2451, device='cuda:0'), 'validation_cardinality_error': tensor(1.4615, device='cuda:0')}
+{'training_loss': tensor(0.2293, device='cuda:0'), 'train_loss_ce': tensor(0.1921, device='cuda:0'), 'train_loss_bbox': tensor(0.0033, device='cuda:0'), 'train_loss_giou': tensor(0.0104, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.8533, device='cuda:0'), 'validation_loss_ce': tensor(0.3347, device='cuda:0'), 'validation_loss_bbox': tensor(0.0281, device='cuda:0'), 'validation_loss_giou': tensor(0.1891, device='cuda:0'), 'validation_cardinality_error': tensor(1.3846, device='cuda:0')}
+{'training_loss': tensor(0.1696, device='cuda:0'), 'train_loss_ce': tensor(0.1435, device='cuda:0'), 'train_loss_bbox': tensor(0.0009, device='cuda:0'), 'train_loss_giou': tensor(0.0108, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.9884, device='cuda:0'), 'validation_loss_ce': tensor(0.3382, device='cuda:0'), 'validation_loss_bbox': tensor(0.0360, device='cuda:0'), 'validation_loss_giou': tensor(0.2352, device='cuda:0'), 'validation_cardinality_error': tensor(1.3846, device='cuda:0')}
+{'training_loss': tensor(0.5900, device='cuda:0'), 'train_loss_ce': tensor(0.3056, device='cuda:0'), 'train_loss_bbox': tensor(0.0299, device='cuda:0'), 'train_loss_giou': tensor(0.0675, device='cuda:0'), 'train_cardinality_error': tensor(0., device='cuda:0'), 'validation_loss': tensor(0.8545, device='cuda:0'), 'validation_loss_ce': tensor(0.3202, device='cuda:0'), 'validation_loss_bbox': tensor(0.0306, device='cuda:0'), 'validation_loss_giou': tensor(0.1908, device='cuda:0'), 'validation_cardinality_error': tensor(1.3077, device='cuda:0')}
+{'training_loss': tensor(0.1700, device='cuda:0'), 'train_loss_ce': tensor(0.1408, device='cuda:0'), 'train_loss_bbox': tensor(0.0015, device='cuda:0'), 'train_loss_giou': tensor(0.0109, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.8922, device='cuda:0'), 'validation_loss_ce': tensor(0.3169, device='cuda:0'), 'validation_loss_bbox': tensor(0.0319, device='cuda:0'), 'validation_loss_giou': tensor(0.2080, device='cuda:0'), 'validation_cardinality_error': tensor(1.3846, device='cuda:0')}
+{'training_loss': tensor(0.4513, device='cuda:0'), 'train_loss_ce': tensor(0.3160, device='cuda:0'), 'train_loss_bbox': tensor(0.0127, device='cuda:0'), 'train_loss_giou': tensor(0.0360, device='cuda:0'), 'train_cardinality_error': tensor(1., device='cuda:0'), 'validation_loss': tensor(0.8982, device='cuda:0'), 'validation_loss_ce': tensor(0.3177, device='cuda:0'), 'validation_loss_bbox': tensor(0.0301, device='cuda:0'), 'validation_loss_giou': tensor(0.2150, device='cuda:0'), 'validation_cardinality_error': tensor(1.3077, device='cuda:0')}
 ```
 
 ## Examples