| /opt/venv/lib/python3.10/site-packages/apex/transformer/functional/fused_rope.py:49: UserWarning: Aiter backend is selected for fused RoPE. This has lower precision. To disable aiter, export USE_ROCM_AITER_ROPE_BACKEND=0 |
| warnings.warn("Aiter backend is selected for fused RoPE. This has lower precision. To disable aiter, export USE_ROCM_AITER_ROPE_BACKEND=0", UserWarning) |
| /opt/venv/lib/python3.10/site-packages/timm/models/layers/__init__.py:49: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers |
| warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning) |
| /opt/venv/lib/python3.10/site-packages/torch/functional.py:554: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /pytorch/aten/src/ATen/native/TensorShape.cpp:4317.) |
| return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] |
|
|
| [1m[96m══════════════════════════════════════════════════════════════════════[0m |
| [1m[96m AgriFM × PASTIS — Fold 2 | 2026-04-17 07:32:42[0m |
| [1m[96m══════════════════════════════════════════════════════════════════════[0m |
|
|
| Device : |
| VRAM : 191.7 GB |
| Model size : small (~14M) |
| AMP : True |
| Batch size : 16 |
| Epochs : 100 |
| LR : 5e-05 |
| Weight decay : 0.05 |
| Warmup iters : 500 |
| Augmentation : True (flip + rotate) |
| Class weights : True |
| Work dir : ./work_dirs/fold2_small |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Building Datasets[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| PASTIS fold=2 split=train: 1465 patches (augment=True) |
| PASTIS fold=2 split=val: 474 patches (augment=False) |
| PASTIS fold=2 split=test: 494 patches (augment=False) |
|
|
| Train: 1465 Val: 474 Test: 494 |
| Train batches: 91 Val batches: 30 |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Building Model[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Total params : 39.6M |
| Trainable params : 39.6M |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Computing Class Weights[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Class weights (fold=2, sampled 300 patches): |
| Class Count Weight |
| ────────────────────────────── ────────── ──────── |
| Background 1583909 0.012 |
| Meadow 921794 0.021 |
| Soft winter wheat 555099 0.034 |
| Corn 691569 0.028 |
| Winter barley 132214 0.144 |
| Winter rapeseed 126795 0.150 |
| Spring barley 60763 0.313 |
| Sunflower 29433 0.647 |
| Grapevine 23120 0.824 |
| Beet 90111 0.211 |
| Winter triticale 41293 0.461 |
| Winter durum wheat 3181 5.986 |
| Fruits vegetables flowers 29185 0.652 |
| Potatoes 15283 1.246 |
| Leguminous fodder 59106 0.322 |
| Soybeans 24576 0.775 |
| Orchard 10572 1.801 |
| Mixed cereal 28288 0.673 |
| Sorghum 4052 4.699 |
|
|
| [1m[96m══════════════════════════════════════════════════════════════════════[0m |
| [1m[96m Training | 100 epochs | model=small (~14M) | fold=2[0m |
| [1m[96m══════════════════════════════════════════════════════════════════════[0m |
|
|
| [1mTraining[0m |
| MIOpen(HIP): Error [Init] Not found :31-DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3> |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.9470 lr=5.90e-06 eta=0:00:11 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.8761 lr=9.92e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.8761 time=0:00:19[0m |
|
|
| [1mValidating...[0m |
| MIOpen(HIP): Error [Init] Not found :31-DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3> |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 001 / 100 | Elapsed: 0:00:30[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.8761 |
| Val Loss 0.6193 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 3.11%[0m |
| [92m[1mmIoU [0m [92m[1m 2.29%[0m |
| [92m[1mmFscore [0m [92m[1m 4.12%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 3.96%[0m |
| [0m[1mmRecall [0m [0m[1m 14.08%[0m |
| [0m[1mKappa [0m [0m[1m 2.48%[0m |
| ────────────────── ────────── |
| Best mFscore 0.00% |
| Val Time 9.6s |
|
|
| [92m[1m★ New best mFscore: 4.12% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.6608 lr=1.48e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.6182 lr=1.88e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.6182 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 002 / 100 | Elapsed: 0:00:49[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.6182 |
| Val Loss 0.5279 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 6.12%[0m |
| [92m[1mmIoU [0m [92m[1m 4.09%[0m |
| [92m[1mmFscore [0m [92m[1m 7.38%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 9.10%[0m |
| [0m[1mmRecall [0m [0m[1m 26.05%[0m |
| [0m[1mKappa [0m [0m[1m 5.12%[0m |
| ────────────────── ────────── |
| Best mFscore 4.12% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 7.38% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.5431 lr=2.37e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.5203 lr=2.78e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.5203 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 003 / 100 | Elapsed: 0:01:09[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.5203 |
| Val Loss 0.4754 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 8.44%[0m |
| [92m[1mmIoU [0m [92m[1m 5.96%[0m |
| [92m[1mmFscore [0m [92m[1m 10.62%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 7.71%[0m |
| [0m[1mmRecall [0m [0m[1m 33.61%[0m |
| [0m[1mKappa [0m [0m[1m 7.14%[0m |
| ────────────────── ────────── |
| Best mFscore 7.38% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 10.62% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.4676 lr=3.27e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.4548 lr=3.67e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.4548 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 004 / 100 | Elapsed: 0:01:28[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.4548 |
| Val Loss 0.4418 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 8.86%[0m |
| [92m[1mmIoU [0m [92m[1m 7.38%[0m |
| [92m[1mmFscore [0m [92m[1m 12.94%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 16.27%[0m |
| [0m[1mmRecall [0m [0m[1m 36.81%[0m |
| [0m[1mKappa [0m [0m[1m 7.74%[0m |
| ────────────────── ────────── |
| Best mFscore 10.62% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 12.94% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.4311 lr=4.16e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.4332 lr=4.56e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.4332 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 005 / 100 | Elapsed: 0:01:48[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.4332 |
| Val Loss 0.4106 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.75%[0m |
| [92m[1mmIoU [0m [92m[1m 9.38%[0m |
| [92m[1mmFscore [0m [92m[1m 15.96%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 19.61%[0m |
| [0m[1mmRecall [0m [0m[1m 41.76%[0m |
| [0m[1mKappa [0m [0m[1m 9.36%[0m |
| ────────────────── ────────── |
| Best mFscore 12.94% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 15.96% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.4154 lr=5.00e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.4029 lr=5.00e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.4029 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 006 / 100 | Elapsed: 0:02:08[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.4029 |
| Val Loss 0.3948 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 11.27%[0m |
| [92m[1mmIoU [0m [92m[1m 9.89%[0m |
| [92m[1mmFscore [0m [92m[1m 16.71%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 20.22%[0m |
| [0m[1mmRecall [0m [0m[1m 43.25%[0m |
| [0m[1mKappa [0m [0m[1m 9.89%[0m |
| ────────────────── ────────── |
| Best mFscore 15.96% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 16.71% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.3615 lr=5.00e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.3666 lr=5.00e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.3666 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 007 / 100 | Elapsed: 0:02:27[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3666 |
| Val Loss 0.3651 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 11.25%[0m |
| [92m[1mmIoU [0m [92m[1m 11.49%[0m |
| [92m[1mmFscore [0m [92m[1m 18.91%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 22.95%[0m |
| [0m[1mmRecall [0m [0m[1m 41.70%[0m |
| [0m[1mKappa [0m [0m[1m 9.71%[0m |
| ────────────────── ────────── |
| Best mFscore 16.71% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 18.91% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.3773 lr=4.99e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.3668 lr=4.99e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.3668 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 008 / 100 | Elapsed: 0:02:46[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3668 |
| Val Loss 0.3895 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 13.50%[0m |
| [92m[1mmIoU [0m [92m[1m 14.16%[0m |
| [92m[1mmFscore [0m [92m[1m 22.70%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 33.86%[0m |
| [0m[1mmRecall [0m [0m[1m 44.21%[0m |
| [0m[1mKappa [0m [0m[1m 11.43%[0m |
| ────────────────── ────────── |
| Best mFscore 18.91% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 22.70% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.3336 lr=4.99e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.3274 lr=4.98e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.3274 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 009 / 100 | Elapsed: 0:03:06[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3274 |
| Val Loss 0.3604 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 14.10%[0m |
| [92m[1mmIoU [0m [92m[1m 15.11%[0m |
| [92m[1mmFscore [0m [92m[1m 23.59%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 33.45%[0m |
| [0m[1mmRecall [0m [0m[1m 44.99%[0m |
| [0m[1mKappa [0m [0m[1m 11.82%[0m |
| ────────────────── ────────── |
| Best mFscore 22.70% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 23.59% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.3207 lr=4.98e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.3210 lr=4.97e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.3210 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 010 / 100 | Elapsed: 0:03:26[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3210 |
| Val Loss 0.3351 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 16.09%[0m |
| [92m[1mmIoU [0m [92m[1m 16.35%[0m |
| [92m[1mmFscore [0m [92m[1m 25.97%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 33.09%[0m |
| [0m[1mmRecall [0m [0m[1m 48.61%[0m |
| [0m[1mKappa [0m [0m[1m 13.60%[0m |
| ────────────────── ────────── |
| Best mFscore 23.59% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 25.97% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.3078 lr=4.97e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.3007 lr=4.96e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.3007 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 011 / 100 | Elapsed: 0:03:45[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3007 |
| Val Loss 0.3163 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 19.87%[0m |
| [92m[1mmIoU [0m [92m[1m 16.31%[0m |
| [92m[1mmFscore [0m [92m[1m 26.27%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 31.50%[0m |
| [0m[1mmRecall [0m [0m[1m 52.00%[0m |
| [0m[1mKappa [0m [0m[1m 16.59%[0m |
| ────────────────── ────────── |
| Best mFscore 25.97% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 26.27% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.2936 lr=4.95e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.2927 lr=4.94e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2927 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 012 / 100 | Elapsed: 0:04:05[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2927 |
| Val Loss 0.3181 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 18.31%[0m |
| [92m[1mmIoU [0m [92m[1m 17.62%[0m |
| [92m[1mmFscore [0m [92m[1m 27.51%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 36.13%[0m |
| [0m[1mmRecall [0m [0m[1m 51.55%[0m |
| [0m[1mKappa [0m [0m[1m 15.26%[0m |
| ────────────────── ────────── |
| Best mFscore 26.27% |
| Val Time 3.7s |
|
|
| [92m[1m★ New best mFscore: 27.51% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.2712 lr=4.93e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.2848 lr=4.92e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2848 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 013 / 100 | Elapsed: 0:04:24[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2848 |
| Val Loss 0.3356 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 22.49%[0m |
| [92m[1mmIoU [0m [92m[1m 18.45%[0m |
| [92m[1mmFscore [0m [92m[1m 29.25%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 33.59%[0m |
| [0m[1mmRecall [0m [0m[1m 52.13%[0m |
| [0m[1mKappa [0m [0m[1m 18.40%[0m |
| ────────────────── ────────── |
| Best mFscore 27.51% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 29.25% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.2671 lr=4.91e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.2724 lr=4.90e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2724 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 014 / 100 | Elapsed: 0:04:44[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2724 |
| Val Loss 0.3666 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 21.20%[0m |
| [92m[1mmIoU [0m [92m[1m 20.27%[0m |
| [92m[1mmFscore [0m [92m[1m 31.05%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 36.95%[0m |
| [0m[1mmRecall [0m [0m[1m 51.80%[0m |
| [0m[1mKappa [0m [0m[1m 17.63%[0m |
| ────────────────── ────────── |
| Best mFscore 29.25% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 31.05% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.2661 lr=4.89e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.2688 lr=4.88e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2688 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 015 / 100 | Elapsed: 0:05:03[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2688 |
| Val Loss 0.3551 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 23.76%[0m |
| [92m[1mmIoU [0m [92m[1m 18.45%[0m |
| [92m[1mmFscore [0m [92m[1m 28.86%[0m |
| [0m[1mmPrecision [0m [0m[1m 33.04%[0m |
| [0m[1mmRecall [0m [0m[1m 52.68%[0m |
| [0m[1mKappa [0m [0m[1m 20.00%[0m |
| ────────────────── ────────── |
| Best mFscore 31.05% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.2427 lr=4.86e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.2487 lr=4.85e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2487 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 016 / 100 | Elapsed: 0:05:22[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2487 |
| Val Loss 0.3077 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 25.08%[0m |
| [92m[1mmIoU [0m [92m[1m 21.28%[0m |
| [92m[1mmFscore [0m [92m[1m 32.48%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 36.48%[0m |
| [0m[1mmRecall [0m [0m[1m 55.17%[0m |
| [0m[1mKappa [0m [0m[1m 20.41%[0m |
| ────────────────── ────────── |
| Best mFscore 31.05% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 32.48% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.2245 lr=4.84e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.2328 lr=4.82e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2328 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 017 / 100 | Elapsed: 0:05:42[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2328 |
| Val Loss 0.3358 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 26.99%[0m |
| [92m[1mmIoU [0m [92m[1m 20.89%[0m |
| [92m[1mmFscore [0m [92m[1m 32.17%[0m |
| [0m[1mmPrecision [0m [0m[1m 36.12%[0m |
| [0m[1mmRecall [0m [0m[1m 54.33%[0m |
| [0m[1mKappa [0m [0m[1m 22.21%[0m |
| ────────────────── ────────── |
| Best mFscore 32.48% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.2277 lr=4.81e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.2270 lr=4.79e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2270 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 018 / 100 | Elapsed: 0:06:01[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2270 |
| Val Loss 0.3143 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 26.45%[0m |
| [92m[1mmIoU [0m [92m[1m 21.98%[0m |
| [92m[1mmFscore [0m [92m[1m 33.06%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 36.88%[0m |
| [0m[1mmRecall [0m [0m[1m 55.22%[0m |
| [0m[1mKappa [0m [0m[1m 22.21%[0m |
| ────────────────── ────────── |
| Best mFscore 32.48% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 33.06% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.2082 lr=4.77e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.2181 lr=4.76e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2181 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 019 / 100 | Elapsed: 0:06:20[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2181 |
| Val Loss 0.3071 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 29.32%[0m |
| [92m[1mmIoU [0m [92m[1m 22.96%[0m |
| [92m[1mmFscore [0m [92m[1m 34.51%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 37.80%[0m |
| [0m[1mmRecall [0m [0m[1m 58.04%[0m |
| [0m[1mKappa [0m [0m[1m 24.54%[0m |
| ────────────────── ────────── |
| Best mFscore 33.06% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 34.51% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.2036 lr=4.74e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.2056 lr=4.72e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2056 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 020 / 100 | Elapsed: 0:06:40[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2056 |
| Val Loss 0.3121 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 30.31%[0m |
| [92m[1mmIoU [0m [92m[1m 23.48%[0m |
| [92m[1mmFscore [0m [92m[1m 35.35%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 37.28%[0m |
| [0m[1mmRecall [0m [0m[1m 58.06%[0m |
| [0m[1mKappa [0m [0m[1m 25.78%[0m |
| ────────────────── ────────── |
| Best mFscore 34.51% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 35.35% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.2098 lr=4.70e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.2151 lr=4.68e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2151 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 021 / 100 | Elapsed: 0:06:59[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2151 |
| Val Loss 0.3490 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 34.36%[0m |
| [92m[1mmIoU [0m [92m[1m 24.85%[0m |
| [92m[1mmFscore [0m [92m[1m 36.62%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 37.58%[0m |
| [0m[1mmRecall [0m [0m[1m 57.11%[0m |
| [0m[1mKappa [0m [0m[1m 29.07%[0m |
| ────────────────── ────────── |
| Best mFscore 35.35% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 36.62% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.2201 lr=4.66e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.2187 lr=4.64e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2187 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 022 / 100 | Elapsed: 0:07:19[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2187 |
| Val Loss 0.3113 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 31.68%[0m |
| [92m[1mmIoU [0m [92m[1m 24.58%[0m |
| [92m[1mmFscore [0m [92m[1m 36.81%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 38.51%[0m |
| [0m[1mmRecall [0m [0m[1m 57.80%[0m |
| [0m[1mKappa [0m [0m[1m 26.58%[0m |
| ────────────────── ────────── |
| Best mFscore 36.62% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 36.81% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1959 lr=4.62e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1967 lr=4.60e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1967 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 023 / 100 | Elapsed: 0:07:39[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1967 |
| Val Loss 0.3081 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 35.88%[0m |
| [92m[1mmIoU [0m [92m[1m 24.97%[0m |
| [92m[1mmFscore [0m [92m[1m 37.41%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 38.48%[0m |
| [0m[1mmRecall [0m [0m[1m 59.76%[0m |
| [0m[1mKappa [0m [0m[1m 30.02%[0m |
| ────────────────── ────────── |
| Best mFscore 36.81% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 37.41% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1957 lr=4.57e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1934 lr=4.55e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1934 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 024 / 100 | Elapsed: 0:07:58[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1934 |
| Val Loss 0.2964 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 38.05%[0m |
| [92m[1mmIoU [0m [92m[1m 27.57%[0m |
| [92m[1mmFscore [0m [92m[1m 40.03%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 40.66%[0m |
| [0m[1mmRecall [0m [0m[1m 61.22%[0m |
| [0m[1mKappa [0m [0m[1m 32.18%[0m |
| ────────────────── ────────── |
| Best mFscore 37.41% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 40.03% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1833 lr=4.52e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1859 lr=4.50e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1859 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 025 / 100 | Elapsed: 0:08:18[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1859 |
| Val Loss 0.3141 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 34.85%[0m |
| [92m[1mmIoU [0m [92m[1m 24.18%[0m |
| [92m[1mmFscore [0m [92m[1m 36.34%[0m |
| [0m[1mmPrecision [0m [0m[1m 38.06%[0m |
| [0m[1mmRecall [0m [0m[1m 59.97%[0m |
| [0m[1mKappa [0m [0m[1m 29.16%[0m |
| ────────────────── ────────── |
| Best mFscore 40.03% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1870 lr=4.48e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1815 lr=4.45e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1815 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 026 / 100 | Elapsed: 0:08:37[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1815 |
| Val Loss 0.2972 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 39.99%[0m |
| [92m[1mmIoU [0m [92m[1m 26.24%[0m |
| [92m[1mmFscore [0m [92m[1m 38.96%[0m |
| [0m[1mmPrecision [0m [0m[1m 38.03%[0m |
| [0m[1mmRecall [0m [0m[1m 63.10%[0m |
| [0m[1mKappa [0m [0m[1m 33.97%[0m |
| ────────────────── ────────── |
| Best mFscore 40.03% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1682 lr=4.42e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1713 lr=4.40e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1713 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 027 / 100 | Elapsed: 0:08:56[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1713 |
| Val Loss 0.2984 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 43.08%[0m |
| [92m[1mmIoU [0m [92m[1m 28.63%[0m |
| [92m[1mmFscore [0m [92m[1m 41.01%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 40.69%[0m |
| [0m[1mmRecall [0m [0m[1m 63.61%[0m |
| [0m[1mKappa [0m [0m[1m 36.59%[0m |
| ────────────────── ────────── |
| Best mFscore 40.03% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 41.01% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1635 lr=4.37e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1663 lr=4.35e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1663 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 028 / 100 | Elapsed: 0:09:16[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1663 |
| Val Loss 0.3038 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 36.56%[0m |
| [92m[1mmIoU [0m [92m[1m 27.78%[0m |
| [92m[1mmFscore [0m [92m[1m 40.07%[0m |
| [0m[1mmPrecision [0m [0m[1m 41.18%[0m |
| [0m[1mmRecall [0m [0m[1m 60.77%[0m |
| [0m[1mKappa [0m [0m[1m 31.04%[0m |
| ────────────────── ────────── |
| Best mFscore 41.01% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1666 lr=4.32e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1683 lr=4.29e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1683 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 029 / 100 | Elapsed: 0:09:35[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1683 |
| Val Loss 0.3049 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 40.32%[0m |
| [92m[1mmIoU [0m [92m[1m 28.76%[0m |
| [92m[1mmFscore [0m [92m[1m 41.54%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 41.76%[0m |
| [0m[1mmRecall [0m [0m[1m 62.27%[0m |
| [0m[1mKappa [0m [0m[1m 34.14%[0m |
| ────────────────── ────────── |
| Best mFscore 41.01% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 41.54% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1572 lr=4.26e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1587 lr=4.23e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1587 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 030 / 100 | Elapsed: 0:09:54[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1587 |
| Val Loss 0.3244 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 41.89%[0m |
| [92m[1mmIoU [0m [92m[1m 29.04%[0m |
| [92m[1mmFscore [0m [92m[1m 41.92%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 40.97%[0m |
| [0m[1mmRecall [0m [0m[1m 63.14%[0m |
| [0m[1mKappa [0m [0m[1m 35.64%[0m |
| ────────────────── ────────── |
| Best mFscore 41.54% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 41.92% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1538 lr=4.20e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1576 lr=4.17e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1576 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 031 / 100 | Elapsed: 0:10:14[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1576 |
| Val Loss 0.3173 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 42.44%[0m |
| [92m[1mmIoU [0m [92m[1m 29.18%[0m |
| [92m[1mmFscore [0m [92m[1m 41.71%[0m |
| [0m[1mmPrecision [0m [0m[1m 40.61%[0m |
| [0m[1mmRecall [0m [0m[1m 63.75%[0m |
| [0m[1mKappa [0m [0m[1m 36.05%[0m |
| ────────────────── ────────── |
| Best mFscore 41.92% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1472 lr=4.14e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1580 lr=4.11e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1580 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 032 / 100 | Elapsed: 0:10:33[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1580 |
| Val Loss 0.3371 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 43.00%[0m |
| [92m[1mmIoU [0m [92m[1m 30.09%[0m |
| [92m[1mmFscore [0m [92m[1m 43.04%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 41.23%[0m |
| [0m[1mmRecall [0m [0m[1m 63.98%[0m |
| [0m[1mKappa [0m [0m[1m 36.57%[0m |
| ────────────────── ────────── |
| Best mFscore 41.92% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 43.04% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1435 lr=4.07e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1464 lr=4.05e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1464 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 033 / 100 | Elapsed: 0:10:53[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1464 |
| Val Loss 0.2988 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 49.16%[0m |
| [92m[1mmIoU [0m [92m[1m 32.31%[0m |
| [92m[1mmFscore [0m [92m[1m 45.33%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 43.12%[0m |
| [0m[1mmRecall [0m [0m[1m 65.43%[0m |
| [0m[1mKappa [0m [0m[1m 42.13%[0m |
| ────────────────── ────────── |
| Best mFscore 43.04% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 45.33% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1370 lr=4.01e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1473 lr=3.98e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1473 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 034 / 100 | Elapsed: 0:11:13[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1473 |
| Val Loss 0.2988 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 44.07%[0m |
| [92m[1mmIoU [0m [92m[1m 30.20%[0m |
| [92m[1mmFscore [0m [92m[1m 42.95%[0m |
| [0m[1mmPrecision [0m [0m[1m 41.59%[0m |
| [0m[1mmRecall [0m [0m[1m 64.64%[0m |
| [0m[1mKappa [0m [0m[1m 37.65%[0m |
| ────────────────── ────────── |
| Best mFscore 45.33% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1372 lr=3.94e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1368 lr=3.91e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1368 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 035 / 100 | Elapsed: 0:11:32[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1368 |
| Val Loss 0.3052 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 45.52%[0m |
| [92m[1mmIoU [0m [92m[1m 32.31%[0m |
| [92m[1mmFscore [0m [92m[1m 45.16%[0m |
| [0m[1mmPrecision [0m [0m[1m 43.55%[0m |
| [0m[1mmRecall [0m [0m[1m 64.74%[0m |
| [0m[1mKappa [0m [0m[1m 39.08%[0m |
| ────────────────── ────────── |
| Best mFscore 45.33% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1331 lr=3.88e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1330 lr=3.84e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1330 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 036 / 100 | Elapsed: 0:11:51[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1330 |
| Val Loss 0.2930 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 46.09%[0m |
| [92m[1mmIoU [0m [92m[1m 32.45%[0m |
| [92m[1mmFscore [0m [92m[1m 45.48%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 43.47%[0m |
| [0m[1mmRecall [0m [0m[1m 65.98%[0m |
| [0m[1mKappa [0m [0m[1m 39.51%[0m |
| ────────────────── ────────── |
| Best mFscore 45.33% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 45.48% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1161 lr=3.81e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1272 lr=3.77e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1272 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 037 / 100 | Elapsed: 0:12:10[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1272 |
| Val Loss 0.3138 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 51.64%[0m |
| [92m[1mmIoU [0m [92m[1m 33.79%[0m |
| [92m[1mmFscore [0m [92m[1m 46.97%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 43.84%[0m |
| [0m[1mmRecall [0m [0m[1m 66.42%[0m |
| [0m[1mKappa [0m [0m[1m 44.50%[0m |
| ────────────────── ────────── |
| Best mFscore 45.48% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 46.97% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1271 lr=3.74e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1277 lr=3.70e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1277 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 038 / 100 | Elapsed: 0:12:30[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1277 |
| Val Loss 0.3288 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 48.50%[0m |
| [92m[1mmIoU [0m [92m[1m 32.55%[0m |
| [92m[1mmFscore [0m [92m[1m 45.67%[0m |
| [0m[1mmPrecision [0m [0m[1m 43.11%[0m |
| [0m[1mmRecall [0m [0m[1m 66.20%[0m |
| [0m[1mKappa [0m [0m[1m 41.57%[0m |
| ────────────────── ────────── |
| Best mFscore 46.97% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1202 lr=3.66e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1222 lr=3.63e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1222 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 039 / 100 | Elapsed: 0:12:49[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1222 |
| Val Loss 0.3467 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 52.58%[0m |
| [92m[1mmIoU [0m [92m[1m 33.85%[0m |
| [92m[1mmFscore [0m [92m[1m 47.04%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 44.09%[0m |
| [0m[1mmRecall [0m [0m[1m 65.74%[0m |
| [0m[1mKappa [0m [0m[1m 45.13%[0m |
| ────────────────── ────────── |
| Best mFscore 46.97% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 47.04% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1214 lr=3.59e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1173 lr=3.56e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1173 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 040 / 100 | Elapsed: 0:13:09[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1173 |
| Val Loss 0.3471 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 49.04%[0m |
| [92m[1mmIoU [0m [92m[1m 33.27%[0m |
| [92m[1mmFscore [0m [92m[1m 46.19%[0m |
| [0m[1mmPrecision [0m [0m[1m 43.77%[0m |
| [0m[1mmRecall [0m [0m[1m 64.11%[0m |
| [0m[1mKappa [0m [0m[1m 42.23%[0m |
| ────────────────── ────────── |
| Best mFscore 47.04% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1209 lr=3.52e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1215 lr=3.48e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1215 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 041 / 100 | Elapsed: 0:13:28[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1215 |
| Val Loss 0.3493 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 48.72%[0m |
| [92m[1mmIoU [0m [92m[1m 32.58%[0m |
| [92m[1mmFscore [0m [92m[1m 45.54%[0m |
| [0m[1mmPrecision [0m [0m[1m 43.52%[0m |
| [0m[1mmRecall [0m [0m[1m 64.27%[0m |
| [0m[1mKappa [0m [0m[1m 41.90%[0m |
| ────────────────── ────────── |
| Best mFscore 47.04% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1309 lr=3.44e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1236 lr=3.41e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1236 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 042 / 100 | Elapsed: 0:13:47[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1236 |
| Val Loss 0.3408 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 52.13%[0m |
| [92m[1mmIoU [0m [92m[1m 33.85%[0m |
| [92m[1mmFscore [0m [92m[1m 47.06%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 43.36%[0m |
| [0m[1mmRecall [0m [0m[1m 66.27%[0m |
| [0m[1mKappa [0m [0m[1m 45.07%[0m |
| ────────────────── ────────── |
| Best mFscore 47.04% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 47.06% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1088 lr=3.36e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1100 lr=3.33e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1100 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 043 / 100 | Elapsed: 0:14:07[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1100 |
| Val Loss 0.3214 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 54.74%[0m |
| [92m[1mmIoU [0m [92m[1m 34.76%[0m |
| [92m[1mmFscore [0m [92m[1m 48.13%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 43.70%[0m |
| [0m[1mmRecall [0m [0m[1m 67.49%[0m |
| [0m[1mKappa [0m [0m[1m 47.47%[0m |
| ────────────────── ────────── |
| Best mFscore 47.06% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 48.13% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1188 lr=3.29e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1222 lr=3.25e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1222 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 044 / 100 | Elapsed: 0:14:26[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1222 |
| Val Loss 0.3174 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 47.62%[0m |
| [92m[1mmIoU [0m [92m[1m 31.93%[0m |
| [92m[1mmFscore [0m [92m[1m 44.88%[0m |
| [0m[1mmPrecision [0m [0m[1m 43.17%[0m |
| [0m[1mmRecall [0m [0m[1m 64.84%[0m |
| [0m[1mKappa [0m [0m[1m 40.78%[0m |
| ────────────────── ────────── |
| Best mFscore 48.13% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1156 lr=3.21e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1179 lr=3.17e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1179 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 045 / 100 | Elapsed: 0:14:45[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1179 |
| Val Loss 0.3329 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 52.95%[0m |
| [92m[1mmIoU [0m [92m[1m 34.50%[0m |
| [92m[1mmFscore [0m [92m[1m 47.94%[0m |
| [0m[1mmPrecision [0m [0m[1m 44.32%[0m |
| [0m[1mmRecall [0m [0m[1m 67.59%[0m |
| [0m[1mKappa [0m [0m[1m 45.75%[0m |
| ────────────────── ────────── |
| Best mFscore 48.13% |
| Val Time 3.7s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1178 lr=3.13e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1135 lr=3.09e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1135 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 046 / 100 | Elapsed: 0:15:04[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1135 |
| Val Loss 0.3213 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 53.86%[0m |
| [92m[1mmIoU [0m [92m[1m 35.22%[0m |
| [92m[1mmFscore [0m [92m[1m 48.67%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 44.66%[0m |
| [0m[1mmRecall [0m [0m[1m 68.00%[0m |
| [0m[1mKappa [0m [0m[1m 46.79%[0m |
| ────────────────── ────────── |
| Best mFscore 48.13% |
| Val Time 3.7s |
|
|
| [92m[1m★ New best mFscore: 48.67% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1056 lr=3.05e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.1041 lr=3.02e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1041 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 047 / 100 | Elapsed: 0:15:24[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1041 |
| Val Loss 0.3364 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 54.47%[0m |
| [92m[1mmIoU [0m [92m[1m 34.39%[0m |
| [92m[1mmFscore [0m [92m[1m 47.90%[0m |
| [0m[1mmPrecision [0m [0m[1m 44.18%[0m |
| [0m[1mmRecall [0m [0m[1m 66.09%[0m |
| [0m[1mKappa [0m [0m[1m 47.10%[0m |
| ────────────────── ────────── |
| Best mFscore 48.67% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.1028 lr=2.97e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0988 lr=2.94e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0988 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 048 / 100 | Elapsed: 0:15:43[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0988 |
| Val Loss 0.3641 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 57.53%[0m |
| [92m[1mmIoU [0m [92m[1m 36.74%[0m |
| [92m[1mmFscore [0m [92m[1m 50.51%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 45.80%[0m |
| [0m[1mmRecall [0m [0m[1m 68.54%[0m |
| [0m[1mKappa [0m [0m[1m 50.21%[0m |
| ────────────────── ────────── |
| Best mFscore 48.67% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 50.51% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0907 lr=2.89e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0959 lr=2.85e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0959 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 049 / 100 | Elapsed: 0:16:03[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0959 |
| Val Loss 0.3787 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 53.16%[0m |
| [92m[1mmIoU [0m [92m[1m 34.23%[0m |
| [92m[1mmFscore [0m [92m[1m 47.39%[0m |
| [0m[1mmPrecision [0m [0m[1m 43.20%[0m |
| [0m[1mmRecall [0m [0m[1m 66.96%[0m |
| [0m[1mKappa [0m [0m[1m 46.00%[0m |
| ────────────────── ────────── |
| Best mFscore 50.51% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0927 lr=2.81e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0932 lr=2.77e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0932 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 050 / 100 | Elapsed: 0:16:22[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0932 |
| Val Loss 0.3845 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 57.87%[0m |
| [92m[1mmIoU [0m [92m[1m 36.68%[0m |
| [92m[1mmFscore [0m [92m[1m 50.37%[0m |
| [0m[1mmPrecision [0m [0m[1m 45.88%[0m |
| [0m[1mmRecall [0m [0m[1m 67.28%[0m |
| [0m[1mKappa [0m [0m[1m 50.34%[0m |
| ────────────────── ────────── |
| Best mFscore 50.51% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0860 lr=2.73e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0911 lr=2.69e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0911 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 051 / 100 | Elapsed: 0:16:41[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0911 |
| Val Loss 0.3720 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 53.87%[0m |
| [92m[1mmIoU [0m [92m[1m 33.85%[0m |
| [92m[1mmFscore [0m [92m[1m 47.37%[0m |
| [0m[1mmPrecision [0m [0m[1m 43.25%[0m |
| [0m[1mmRecall [0m [0m[1m 67.18%[0m |
| [0m[1mKappa [0m [0m[1m 46.63%[0m |
| ────────────────── ────────── |
| Best mFscore 50.51% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0881 lr=2.65e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0902 lr=2.61e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0902 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 052 / 100 | Elapsed: 0:17:00[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0902 |
| Val Loss 0.3693 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 56.83%[0m |
| [92m[1mmIoU [0m [92m[1m 36.61%[0m |
| [92m[1mmFscore [0m [92m[1m 50.04%[0m |
| [0m[1mmPrecision [0m [0m[1m 45.62%[0m |
| [0m[1mmRecall [0m [0m[1m 68.18%[0m |
| [0m[1mKappa [0m [0m[1m 49.57%[0m |
| ────────────────── ────────── |
| Best mFscore 50.51% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0847 lr=2.57e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0875 lr=2.53e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0875 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 053 / 100 | Elapsed: 0:17:19[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0875 |
| Val Loss 0.3981 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 58.24%[0m |
| [92m[1mmIoU [0m [92m[1m 36.86%[0m |
| [92m[1mmFscore [0m [92m[1m 50.37%[0m |
| [0m[1mmPrecision [0m [0m[1m 45.85%[0m |
| [0m[1mmRecall [0m [0m[1m 67.79%[0m |
| [0m[1mKappa [0m [0m[1m 50.85%[0m |
| ────────────────── ────────── |
| Best mFscore 50.51% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0889 lr=2.48e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0906 lr=2.45e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0906 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 054 / 100 | Elapsed: 0:17:39[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0906 |
| Val Loss 0.3892 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 58.17%[0m |
| [92m[1mmIoU [0m [92m[1m 37.03%[0m |
| [92m[1mmFscore [0m [92m[1m 50.55%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 45.79%[0m |
| [0m[1mmRecall [0m [0m[1m 67.77%[0m |
| [0m[1mKappa [0m [0m[1m 50.89%[0m |
| ────────────────── ────────── |
| Best mFscore 50.51% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 50.55% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0929 lr=2.40e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0904 lr=2.37e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0904 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 055 / 100 | Elapsed: 0:17:58[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0904 |
| Val Loss 0.3675 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 59.93%[0m |
| [92m[1mmIoU [0m [92m[1m 38.43%[0m |
| [92m[1mmFscore [0m [92m[1m 52.09%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 47.39%[0m |
| [0m[1mmRecall [0m [0m[1m 69.06%[0m |
| [0m[1mKappa [0m [0m[1m 52.47%[0m |
| ────────────────── ────────── |
| Best mFscore 50.55% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 52.09% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0755 lr=2.32e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0803 lr=2.29e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0803 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 056 / 100 | Elapsed: 0:18:18[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0803 |
| Val Loss 0.3800 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 58.62%[0m |
| [92m[1mmIoU [0m [92m[1m 37.39%[0m |
| [92m[1mmFscore [0m [92m[1m 50.94%[0m |
| [0m[1mmPrecision [0m [0m[1m 46.80%[0m |
| [0m[1mmRecall [0m [0m[1m 67.84%[0m |
| [0m[1mKappa [0m [0m[1m 51.23%[0m |
| ────────────────── ────────── |
| Best mFscore 52.09% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0724 lr=2.24e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0776 lr=2.20e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0776 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 057 / 100 | Elapsed: 0:18:37[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0776 |
| Val Loss 0.3977 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 58.81%[0m |
| [92m[1mmIoU [0m [92m[1m 36.99%[0m |
| [92m[1mmFscore [0m [92m[1m 50.55%[0m |
| [0m[1mmPrecision [0m [0m[1m 46.18%[0m |
| [0m[1mmRecall [0m [0m[1m 68.33%[0m |
| [0m[1mKappa [0m [0m[1m 51.49%[0m |
| ────────────────── ────────── |
| Best mFscore 52.09% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0779 lr=2.16e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0800 lr=2.12e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0800 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 058 / 100 | Elapsed: 0:18:56[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0800 |
| Val Loss 0.4295 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 59.11%[0m |
| [92m[1mmIoU [0m [92m[1m 38.53%[0m |
| [92m[1mmFscore [0m [92m[1m 51.99%[0m |
| [0m[1mmPrecision [0m [0m[1m 47.67%[0m |
| [0m[1mmRecall [0m [0m[1m 68.02%[0m |
| [0m[1mKappa [0m [0m[1m 51.73%[0m |
| ────────────────── ────────── |
| Best mFscore 52.09% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0818 lr=2.08e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0799 lr=2.04e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0799 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 059 / 100 | Elapsed: 0:19:15[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0799 |
| Val Loss 0.4023 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 59.85%[0m |
| [92m[1mmIoU [0m [92m[1m 38.59%[0m |
| [92m[1mmFscore [0m [92m[1m 52.21%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 47.46%[0m |
| [0m[1mmRecall [0m [0m[1m 68.68%[0m |
| [0m[1mKappa [0m [0m[1m 52.53%[0m |
| ────────────────── ────────── |
| Best mFscore 52.09% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 52.21% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0762 lr=2.00e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0734 lr=1.97e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0734 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 060 / 100 | Elapsed: 0:19:35[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0734 |
| Val Loss 0.4075 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 60.30%[0m |
| [92m[1mmIoU [0m [92m[1m 38.83%[0m |
| [92m[1mmFscore [0m [92m[1m 52.54%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 47.80%[0m |
| [0m[1mmRecall [0m [0m[1m 68.54%[0m |
| [0m[1mKappa [0m [0m[1m 53.02%[0m |
| ────────────────── ────────── |
| Best mFscore 52.21% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 52.54% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0770 lr=1.92e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0749 lr=1.89e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0749 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 061 / 100 | Elapsed: 0:19:54[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0749 |
| Val Loss 0.4194 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 61.68%[0m |
| [92m[1mmIoU [0m [92m[1m 39.18%[0m |
| [92m[1mmFscore [0m [92m[1m 52.82%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 47.64%[0m |
| [0m[1mmRecall [0m [0m[1m 69.14%[0m |
| [0m[1mKappa [0m [0m[1m 54.32%[0m |
| ────────────────── ────────── |
| Best mFscore 52.54% |
| Val Time 3.7s |
|
|
| [92m[1m★ New best mFscore: 52.82% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0715 lr=1.84e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0708 lr=1.81e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0708 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 062 / 100 | Elapsed: 0:20:14[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0708 |
| Val Loss 0.4302 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 61.01%[0m |
| [92m[1mmIoU [0m [92m[1m 39.37%[0m |
| [92m[1mmFscore [0m [92m[1m 53.15%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 47.95%[0m |
| [0m[1mmRecall [0m [0m[1m 68.95%[0m |
| [0m[1mKappa [0m [0m[1m 53.68%[0m |
| ────────────────── ────────── |
| Best mFscore 52.82% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 53.15% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0730 lr=1.77e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0707 lr=1.73e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0707 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 063 / 100 | Elapsed: 0:20:33[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0707 |
| Val Loss 0.3929 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 60.70%[0m |
| [92m[1mmIoU [0m [92m[1m 37.96%[0m |
| [92m[1mmFscore [0m [92m[1m 51.66%[0m |
| [0m[1mmPrecision [0m [0m[1m 46.87%[0m |
| [0m[1mmRecall [0m [0m[1m 68.73%[0m |
| [0m[1mKappa [0m [0m[1m 53.10%[0m |
| ────────────────── ────────── |
| Best mFscore 53.15% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0665 lr=1.69e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0684 lr=1.65e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0684 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 064 / 100 | Elapsed: 0:20:52[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0684 |
| Val Loss 0.4181 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 60.64%[0m |
| [92m[1mmIoU [0m [92m[1m 38.57%[0m |
| [92m[1mmFscore [0m [92m[1m 51.94%[0m |
| [0m[1mmPrecision [0m [0m[1m 47.05%[0m |
| [0m[1mmRecall [0m [0m[1m 68.44%[0m |
| [0m[1mKappa [0m [0m[1m 53.40%[0m |
| ────────────────── ────────── |
| Best mFscore 53.15% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0675 lr=1.61e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0686 lr=1.58e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0686 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 065 / 100 | Elapsed: 0:21:12[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0686 |
| Val Loss 0.4272 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 61.79%[0m |
| [92m[1mmIoU [0m [92m[1m 40.01%[0m |
| [92m[1mmFscore [0m [92m[1m 53.58%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 48.78%[0m |
| [0m[1mmRecall [0m [0m[1m 68.70%[0m |
| [0m[1mKappa [0m [0m[1m 54.48%[0m |
| ────────────────── ────────── |
| Best mFscore 53.15% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 53.58% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0653 lr=1.54e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0649 lr=1.51e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0649 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 066 / 100 | Elapsed: 0:21:31[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0649 |
| Val Loss 0.4317 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 61.57%[0m |
| [92m[1mmIoU [0m [92m[1m 38.96%[0m |
| [92m[1mmFscore [0m [92m[1m 52.60%[0m |
| [0m[1mmPrecision [0m [0m[1m 47.24%[0m |
| [0m[1mmRecall [0m [0m[1m 69.21%[0m |
| [0m[1mKappa [0m [0m[1m 54.34%[0m |
| ────────────────── ────────── |
| Best mFscore 53.58% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0655 lr=1.46e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0640 lr=1.43e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0640 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 067 / 100 | Elapsed: 0:21:50[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0640 |
| Val Loss 0.4407 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 62.77%[0m |
| [92m[1mmIoU [0m [92m[1m 39.85%[0m |
| [92m[1mmFscore [0m [92m[1m 53.51%[0m |
| [0m[1mmPrecision [0m [0m[1m 48.22%[0m |
| [0m[1mmRecall [0m [0m[1m 69.03%[0m |
| [0m[1mKappa [0m [0m[1m 55.34%[0m |
| ────────────────── ────────── |
| Best mFscore 53.58% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0618 lr=1.39e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0631 lr=1.36e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0631 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 068 / 100 | Elapsed: 0:22:09[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0631 |
| Val Loss 0.4592 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 62.63%[0m |
| [92m[1mmIoU [0m [92m[1m 40.02%[0m |
| [92m[1mmFscore [0m [92m[1m 53.64%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 48.45%[0m |
| [0m[1mmRecall [0m [0m[1m 68.95%[0m |
| [0m[1mKappa [0m [0m[1m 55.24%[0m |
| ────────────────── ────────── |
| Best mFscore 53.58% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 53.64% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0614 lr=1.32e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0613 lr=1.29e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0613 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 069 / 100 | Elapsed: 0:22:29[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0613 |
| Val Loss 0.4638 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 63.11%[0m |
| [92m[1mmIoU [0m [92m[1m 40.25%[0m |
| [92m[1mmFscore [0m [92m[1m 53.97%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 48.69%[0m |
| [0m[1mmRecall [0m [0m[1m 68.98%[0m |
| [0m[1mKappa [0m [0m[1m 55.81%[0m |
| ────────────────── ────────── |
| Best mFscore 53.64% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 53.97% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0598 lr=1.25e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0603 lr=1.22e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0603 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 070 / 100 | Elapsed: 0:22:49[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0603 |
| Val Loss 0.4612 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 63.15%[0m |
| [92m[1mmIoU [0m [92m[1m 40.38%[0m |
| [92m[1mmFscore [0m [92m[1m 54.01%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 48.70%[0m |
| [0m[1mmRecall [0m [0m[1m 69.20%[0m |
| [0m[1mKappa [0m [0m[1m 55.87%[0m |
| ────────────────── ────────── |
| Best mFscore 53.97% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 54.01% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0609 lr=1.18e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0607 lr=1.15e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0607 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 071 / 100 | Elapsed: 0:23:08[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0607 |
| Val Loss 0.4582 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 62.64%[0m |
| [92m[1mmIoU [0m [92m[1m 40.04%[0m |
| [92m[1mmFscore [0m [92m[1m 53.70%[0m |
| [0m[1mmPrecision [0m [0m[1m 48.78%[0m |
| [0m[1mmRecall [0m [0m[1m 68.70%[0m |
| [0m[1mKappa [0m [0m[1m 55.25%[0m |
| ────────────────── ────────── |
| Best mFscore 54.01% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0602 lr=1.12e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0595 lr=1.09e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0595 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 072 / 100 | Elapsed: 0:23:27[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0595 |
| Val Loss 0.4728 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 63.84%[0m |
| [92m[1mmIoU [0m [92m[1m 40.06%[0m |
| [92m[1mmFscore [0m [92m[1m 53.85%[0m |
| [0m[1mmPrecision [0m [0m[1m 48.21%[0m |
| [0m[1mmRecall [0m [0m[1m 69.30%[0m |
| [0m[1mKappa [0m [0m[1m 56.48%[0m |
| ────────────────── ────────── |
| Best mFscore 54.01% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0568 lr=1.05e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0577 lr=1.02e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0577 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 073 / 100 | Elapsed: 0:23:47[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0577 |
| Val Loss 0.4933 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 63.91%[0m |
| [92m[1mmIoU [0m [92m[1m 40.69%[0m |
| [92m[1mmFscore [0m [92m[1m 54.51%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 48.98%[0m |
| [0m[1mmRecall [0m [0m[1m 68.92%[0m |
| [0m[1mKappa [0m [0m[1m 56.59%[0m |
| ────────────────── ────────── |
| Best mFscore 54.01% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 54.51% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0564 lr=9.88e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0563 lr=9.60e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0563 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 074 / 100 | Elapsed: 0:24:06[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0563 |
| Val Loss 0.4856 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 63.89%[0m |
| [92m[1mmIoU [0m [92m[1m 41.19%[0m |
| [92m[1mmFscore [0m [92m[1m 54.90%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 49.79%[0m |
| [0m[1mmRecall [0m [0m[1m 69.02%[0m |
| [0m[1mKappa [0m [0m[1m 56.57%[0m |
| ────────────────── ────────── |
| Best mFscore 54.51% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 54.90% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0573 lr=9.26e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0573 lr=8.98e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0573 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 075 / 100 | Elapsed: 0:24:26[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0573 |
| Val Loss 0.4875 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 64.12%[0m |
| [92m[1mmIoU [0m [92m[1m 40.65%[0m |
| [92m[1mmFscore [0m [92m[1m 54.32%[0m |
| [0m[1mmPrecision [0m [0m[1m 48.87%[0m |
| [0m[1mmRecall [0m [0m[1m 69.22%[0m |
| [0m[1mKappa [0m [0m[1m 56.80%[0m |
| ────────────────── ────────── |
| Best mFscore 54.90% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0557 lr=8.66e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0560 lr=8.39e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0560 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 076 / 100 | Elapsed: 0:24:45[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0560 |
| Val Loss 0.4864 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 64.41%[0m |
| [92m[1mmIoU [0m [92m[1m 40.66%[0m |
| [92m[1mmFscore [0m [92m[1m 54.32%[0m |
| [0m[1mmPrecision [0m [0m[1m 48.96%[0m |
| [0m[1mmRecall [0m [0m[1m 68.86%[0m |
| [0m[1mKappa [0m [0m[1m 57.12%[0m |
| ────────────────── ────────── |
| Best mFscore 54.90% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0549 lr=8.07e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0537 lr=7.82e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0537 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 077 / 100 | Elapsed: 0:25:04[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0537 |
| Val Loss 0.4991 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 65.43%[0m |
| [92m[1mmIoU [0m [92m[1m 41.58%[0m |
| [92m[1mmFscore [0m [92m[1m 55.36%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 49.93%[0m |
| [0m[1mmRecall [0m [0m[1m 69.23%[0m |
| [0m[1mKappa [0m [0m[1m 58.14%[0m |
| ────────────────── ────────── |
| Best mFscore 54.90% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 55.36% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0515 lr=7.51e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0535 lr=7.27e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0535 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 078 / 100 | Elapsed: 0:25:24[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0535 |
| Val Loss 0.5015 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 64.78%[0m |
| [92m[1mmIoU [0m [92m[1m 41.26%[0m |
| [92m[1mmFscore [0m [92m[1m 55.01%[0m |
| [0m[1mmPrecision [0m [0m[1m 49.61%[0m |
| [0m[1mmRecall [0m [0m[1m 69.21%[0m |
| [0m[1mKappa [0m [0m[1m 57.42%[0m |
| ────────────────── ────────── |
| Best mFscore 55.36% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0530 lr=6.97e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0530 lr=6.73e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0530 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 079 / 100 | Elapsed: 0:25:43[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0530 |
| Val Loss 0.4953 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 65.14%[0m |
| [92m[1mmIoU [0m [92m[1m 41.16%[0m |
| [92m[1mmFscore [0m [92m[1m 54.90%[0m |
| [0m[1mmPrecision [0m [0m[1m 49.34%[0m |
| [0m[1mmRecall [0m [0m[1m 69.12%[0m |
| [0m[1mKappa [0m [0m[1m 57.78%[0m |
| ────────────────── ────────── |
| Best mFscore 55.36% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0533 lr=6.45e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0521 lr=6.22e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0521 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 080 / 100 | Elapsed: 0:26:02[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0521 |
| Val Loss 0.5078 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 64.47%[0m |
| [92m[1mmIoU [0m [92m[1m 41.04%[0m |
| [92m[1mmFscore [0m [92m[1m 54.71%[0m |
| [0m[1mmPrecision [0m [0m[1m 49.44%[0m |
| [0m[1mmRecall [0m [0m[1m 68.65%[0m |
| [0m[1mKappa [0m [0m[1m 57.15%[0m |
| ────────────────── ────────── |
| Best mFscore 55.36% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0498 lr=5.95e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0523 lr=5.73e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0523 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 081 / 100 | Elapsed: 0:26:21[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0523 |
| Val Loss 0.5058 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 64.60%[0m |
| [92m[1mmIoU [0m [92m[1m 40.92%[0m |
| [92m[1mmFscore [0m [92m[1m 54.61%[0m |
| [0m[1mmPrecision [0m [0m[1m 49.10%[0m |
| [0m[1mmRecall [0m [0m[1m 69.11%[0m |
| [0m[1mKappa [0m [0m[1m 57.26%[0m |
| ────────────────── ────────── |
| Best mFscore 55.36% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0516 lr=5.47e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0514 lr=5.26e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0514 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 082 / 100 | Elapsed: 0:26:40[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0514 |
| Val Loss 0.5202 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 65.29%[0m |
| [92m[1mmIoU [0m [92m[1m 41.34%[0m |
| [92m[1mmFscore [0m [92m[1m 55.06%[0m |
| [0m[1mmPrecision [0m [0m[1m 49.63%[0m |
| [0m[1mmRecall [0m [0m[1m 68.55%[0m |
| [0m[1mKappa [0m [0m[1m 57.92%[0m |
| ────────────────── ────────── |
| Best mFscore 55.36% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0498 lr=5.01e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0507 lr=4.81e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0507 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 083 / 100 | Elapsed: 0:26:59[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0507 |
| Val Loss 0.5040 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 64.92%[0m |
| [92m[1mmIoU [0m [92m[1m 40.98%[0m |
| [92m[1mmFscore [0m [92m[1m 54.73%[0m |
| [0m[1mmPrecision [0m [0m[1m 49.25%[0m |
| [0m[1mmRecall [0m [0m[1m 68.95%[0m |
| [0m[1mKappa [0m [0m[1m 57.58%[0m |
| ────────────────── ────────── |
| Best mFscore 55.36% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0492 lr=4.57e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0494 lr=4.38e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0494 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 084 / 100 | Elapsed: 0:27:18[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0494 |
| Val Loss 0.5382 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.05%[0m |
| [92m[1mmIoU [0m [92m[1m 41.85%[0m |
| [92m[1mmFscore [0m [92m[1m 55.68%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 50.07%[0m |
| [0m[1mmRecall [0m [0m[1m 69.03%[0m |
| [0m[1mKappa [0m [0m[1m 58.69%[0m |
| ────────────────── ────────── |
| Best mFscore 55.36% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 55.68% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0510 lr=4.16e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0499 lr=3.98e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0499 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 085 / 100 | Elapsed: 0:27:38[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0499 |
| Val Loss 0.5264 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 64.96%[0m |
| [92m[1mmIoU [0m [92m[1m 41.47%[0m |
| [92m[1mmFscore [0m [92m[1m 55.24%[0m |
| [0m[1mmPrecision [0m [0m[1m 49.75%[0m |
| [0m[1mmRecall [0m [0m[1m 69.09%[0m |
| [0m[1mKappa [0m [0m[1m 57.68%[0m |
| ────────────────── ────────── |
| Best mFscore 55.68% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0503 lr=3.77e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0493 lr=3.61e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0493 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 086 / 100 | Elapsed: 0:27:57[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0493 |
| Val Loss 0.5273 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 65.92%[0m |
| [92m[1mmIoU [0m [92m[1m 41.74%[0m |
| [92m[1mmFscore [0m [92m[1m 55.53%[0m |
| [0m[1mmPrecision [0m [0m[1m 49.84%[0m |
| [0m[1mmRecall [0m [0m[1m 69.25%[0m |
| [0m[1mKappa [0m [0m[1m 58.59%[0m |
| ────────────────── ────────── |
| Best mFscore 55.68% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0480 lr=3.41e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0483 lr=3.25e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0483 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 087 / 100 | Elapsed: 0:28:16[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0483 |
| Val Loss 0.5264 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 65.98%[0m |
| [92m[1mmIoU [0m [92m[1m 42.01%[0m |
| [92m[1mmFscore [0m [92m[1m 55.81%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 50.41%[0m |
| [0m[1mmRecall [0m [0m[1m 69.08%[0m |
| [0m[1mKappa [0m [0m[1m 58.58%[0m |
| ────────────────── ────────── |
| Best mFscore 55.68% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 55.81% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0462 lr=3.07e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0487 lr=2.92e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0487 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 088 / 100 | Elapsed: 0:28:36[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0487 |
| Val Loss 0.5124 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 64.93%[0m |
| [92m[1mmIoU [0m [92m[1m 41.08%[0m |
| [92m[1mmFscore [0m [92m[1m 54.82%[0m |
| [0m[1mmPrecision [0m [0m[1m 49.28%[0m |
| [0m[1mmRecall [0m [0m[1m 69.05%[0m |
| [0m[1mKappa [0m [0m[1m 57.64%[0m |
| ────────────────── ────────── |
| Best mFscore 55.81% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0500 lr=2.75e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0482 lr=2.62e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0482 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 089 / 100 | Elapsed: 0:28:55[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0482 |
| Val Loss 0.5451 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 65.53%[0m |
| [92m[1mmIoU [0m [92m[1m 41.28%[0m |
| [92m[1mmFscore [0m [92m[1m 55.05%[0m |
| [0m[1mmPrecision [0m [0m[1m 49.45%[0m |
| [0m[1mmRecall [0m [0m[1m 68.66%[0m |
| [0m[1mKappa [0m [0m[1m 58.20%[0m |
| ────────────────── ────────── |
| Best mFscore 55.81% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0451 lr=2.46e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0474 lr=2.34e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0474 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 090 / 100 | Elapsed: 0:29:14[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0474 |
| Val Loss 0.5503 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.00%[0m |
| [92m[1mmIoU [0m [92m[1m 41.87%[0m |
| [92m[1mmFscore [0m [92m[1m 55.66%[0m |
| [0m[1mmPrecision [0m [0m[1m 50.17%[0m |
| [0m[1mmRecall [0m [0m[1m 68.89%[0m |
| [0m[1mKappa [0m [0m[1m 58.64%[0m |
| ────────────────── ────────── |
| Best mFscore 55.81% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0460 lr=2.20e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0473 lr=2.09e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0473 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 091 / 100 | Elapsed: 0:29:33[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0473 |
| Val Loss 0.5510 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.05%[0m |
| [92m[1mmIoU [0m [92m[1m 42.22%[0m |
| [92m[1mmFscore [0m [92m[1m 55.95%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 50.70%[0m |
| [0m[1mmRecall [0m [0m[1m 68.77%[0m |
| [0m[1mKappa [0m [0m[1m 58.69%[0m |
| ────────────────── ────────── |
| Best mFscore 55.81% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 55.95% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0459 lr=1.96e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0464 lr=1.86e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0464 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 092 / 100 | Elapsed: 0:29:53[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0464 |
| Val Loss 0.5358 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.33%[0m |
| [92m[1mmIoU [0m [92m[1m 42.20%[0m |
| [92m[1mmFscore [0m [92m[1m 55.93%[0m |
| [0m[1mmPrecision [0m [0m[1m 50.51%[0m |
| [0m[1mmRecall [0m [0m[1m 69.01%[0m |
| [0m[1mKappa [0m [0m[1m 58.96%[0m |
| ────────────────── ────────── |
| Best mFscore 55.95% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0463 lr=1.75e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0467 lr=1.66e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0467 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 093 / 100 | Elapsed: 0:30:12[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0467 |
| Val Loss 0.5466 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.54%[0m |
| [92m[1mmIoU [0m [92m[1m 42.22%[0m |
| [92m[1mmFscore [0m [92m[1m 55.99%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 50.55%[0m |
| [0m[1mmRecall [0m [0m[1m 69.06%[0m |
| [0m[1mKappa [0m [0m[1m 59.19%[0m |
| ────────────────── ────────── |
| Best mFscore 55.95% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 55.99% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0467 lr=1.56e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0463 lr=1.49e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0463 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 094 / 100 | Elapsed: 0:30:32[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0463 |
| Val Loss 0.5545 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.34%[0m |
| [92m[1mmIoU [0m [92m[1m 42.03%[0m |
| [92m[1mmFscore [0m [92m[1m 55.83%[0m |
| [0m[1mmPrecision [0m [0m[1m 50.19%[0m |
| [0m[1mmRecall [0m [0m[1m 68.98%[0m |
| [0m[1mKappa [0m [0m[1m 58.99%[0m |
| ────────────────── ────────── |
| Best mFscore 55.99% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0456 lr=1.40e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0462 lr=1.34e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0462 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 095 / 100 | Elapsed: 0:30:51[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0462 |
| Val Loss 0.5535 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.21%[0m |
| [92m[1mmIoU [0m [92m[1m 41.93%[0m |
| [92m[1mmFscore [0m [92m[1m 55.71%[0m |
| [0m[1mmPrecision [0m [0m[1m 50.14%[0m |
| [0m[1mmRecall [0m [0m[1m 69.02%[0m |
| [0m[1mKappa [0m [0m[1m 58.89%[0m |
| ────────────────── ────────── |
| Best mFscore 55.99% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0453 lr=1.27e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0466 lr=1.22e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0466 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 096 / 100 | Elapsed: 0:31:10[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0466 |
| Val Loss 0.5520 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 65.77%[0m |
| [92m[1mmIoU [0m [92m[1m 41.55%[0m |
| [92m[1mmFscore [0m [92m[1m 55.26%[0m |
| [0m[1mmPrecision [0m [0m[1m 49.74%[0m |
| [0m[1mmRecall [0m [0m[1m 68.88%[0m |
| [0m[1mKappa [0m [0m[1m 58.45%[0m |
| ────────────────── ────────── |
| Best mFscore 55.99% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0465 lr=1.16e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0461 lr=1.12e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0461 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 097 / 100 | Elapsed: 0:31:29[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0461 |
| Val Loss 0.5548 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.27%[0m |
| [92m[1mmIoU [0m [92m[1m 41.93%[0m |
| [92m[1mmFscore [0m [92m[1m 55.72%[0m |
| [0m[1mmPrecision [0m [0m[1m 50.24%[0m |
| [0m[1mmRecall [0m [0m[1m 68.70%[0m |
| [0m[1mKappa [0m [0m[1m 58.94%[0m |
| ────────────────── ────────── |
| Best mFscore 55.99% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0449 lr=1.08e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0457 lr=1.05e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0457 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 098 / 100 | Elapsed: 0:31:49[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0457 |
| Val Loss 0.5586 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.10%[0m |
| [92m[1mmIoU [0m [92m[1m 42.08%[0m |
| [92m[1mmFscore [0m [92m[1m 55.85%[0m |
| [0m[1mmPrecision [0m [0m[1m 50.37%[0m |
| [0m[1mmRecall [0m [0m[1m 68.95%[0m |
| [0m[1mKappa [0m [0m[1m 58.77%[0m |
| ────────────────── ────────── |
| Best mFscore 55.99% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0460 lr=1.03e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0456 lr=1.01e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0456 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 099 / 100 | Elapsed: 0:32:08[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0456 |
| Val Loss 0.5560 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.62%[0m |
| [92m[1mmIoU [0m [92m[1m 42.23%[0m |
| [92m[1mmFscore [0m [92m[1m 56.01%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 50.52%[0m |
| [0m[1mmRecall [0m [0m[1m 68.91%[0m |
| [0m[1mKappa [0m [0m[1m 59.26%[0m |
| ────────────────── ────────── |
| Best mFscore 55.99% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 56.01% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.9% iter 50/91 loss=0.0447 lr=1.00e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 91/91 loss=0.0455 lr=1.00e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0455 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 100 / 100 | Elapsed: 0:32:27[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0455 |
| Val Loss 0.5670 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.82%[0m |
| [92m[1mmIoU [0m [92m[1m 42.29%[0m |
| [92m[1mmFscore [0m [92m[1m 56.12%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 50.69%[0m |
| [0m[1mmRecall [0m [0m[1m 68.89%[0m |
| [0m[1mKappa [0m [0m[1m 59.44%[0m |
| ────────────────── ────────── |
| Best mFscore 56.01% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 56.12% → saved best_model.pth[0m |
|
|
| [1m[96m══════════════════════════════════════════════════════════════════════[0m |
| [1m[96m Final Test Evaluation[0m |
| [1m[96m══════════════════════════════════════════════════════════════════════[0m |
|
|
| [1mTestidating...[0m |
| MIOpen(HIP): Error [Init] Not found :31-DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3> |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Final Test Results[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.85%[0m |
| [92m[1mmIoU [0m [92m[1m 42.90%[0m |
| [92m[1mmFscore [0m [92m[1m 56.69%[0m |
| [0m[1mmPrecision [0m [0m[1m 51.33%[0m |
| [0m[1mmRecall [0m [0m[1m 69.00%[0m |
| [0m[1mKappa [0m [0m[1m 59.71%[0m |
| ────────────────── ────────── |
| Test Loss 0.5367 |
| Total Time 0:32:35 |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Per-Class IoU (Test)[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Class IoU Bar |
| ────────────────────────────── ─────── ──────────────────── |
| [92mBackground 50.20% ██████████[0m |
| [92mMeadow 55.96% ███████████[0m |
| [92mSoft winter wheat 68.92% █████████████[0m |
| [92mCorn 75.31% ███████████████[0m |
| [92mWinter barley 59.08% ███████████[0m |
| [92mWinter rapeseed 76.05% ███████████████[0m |
| [92mSpring barley 40.00% ████████[0m |
| [92mSunflower 48.13% █████████[0m |
| [92mGrapevine 36.62% ███████[0m |
| [92mBeet 72.52% ██████████████[0m |
| [93mWinter triticale 19.33% ███[0m |
| [92mWinter durum wheat 43.68% ████████[0m |
| [93mFruits vegetables flowers 19.75% ███[0m |
| [92mPotatoes 37.75% ███████[0m |
| [92mLeguminous fodder 20.88% ████[0m |
| [92mSoybeans 55.03% ███████████[0m |
| [93mOrchard 13.11% ██[0m |
| [93mMixed cereal 12.64% ██[0m |
| [93mSorghum 10.12% ██[0m |
|
|
| [92m[1mAll results saved to: ./work_dirs/fold2_small[0m |
| training_log.txt — full training log |
| log.json — per-epoch metrics |
| test_results.json — final test + per-class IoU |
| best_model.pth — best checkpoint (by val mFscore) |
| latest.pth — last epoch checkpoint |
| args.json — training configuration |
|
|
