| /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 3 | 2026-04-17 08:05:22[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/fold3_small |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Building Datasets[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| PASTIS fold=3 split=train: 1477 patches (augment=True) |
| PASTIS fold=3 split=val: 482 patches (augment=False) |
| PASTIS fold=3 split=test: 474 patches (augment=False) |
|
|
| Train: 1477 Val: 482 Test: 474 |
| Train batches: 92 Val batches: 31 |
|
|
| [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=3, sampled 300 patches): |
| Class Count Weight |
| ────────────────────────────── ────────── ──────── |
| Background 1998636 0.010 |
| Meadow 712057 0.029 |
| Soft winter wheat 369859 0.056 |
| Corn 243931 0.084 |
| Winter barley 102567 0.200 |
| Winter rapeseed 105312 0.195 |
| Spring barley 28498 0.721 |
| Sunflower 42628 0.482 |
| Grapevine 237169 0.087 |
| Beet 46100 0.445 |
| Winter triticale 14290 1.437 |
| Winter durum wheat 93967 0.219 |
| Fruits vegetables flowers 77918 0.264 |
| Potatoes 19139 1.073 |
| Leguminous fodder 104778 0.196 |
| Soybeans 1777 11.557 |
| Orchard 97344 0.211 |
| Mixed cereal 25357 0.810 |
| Sorghum 22178 0.926 |
|
|
| [1m[96m══════════════════════════════════════════════════════════════════════[0m |
| [1m[96m Training | 100 epochs | model=small (~14M) | fold=3[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> |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=1.0600 lr=5.90e-06 eta=0:00:11 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.8407 lr=1.00e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.8407 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: 0:00:28[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.8407 |
| Val Loss 0.5811 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 2.22%[0m |
| [92m[1mmIoU [0m [92m[1m 0.80%[0m |
| [92m[1mmFscore [0m [92m[1m 1.53%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 4.93%[0m |
| [0m[1mmRecall [0m [0m[1m 11.84%[0m |
| [0m[1mKappa [0m [0m[1m 1.28%[0m |
| ────────────────── ────────── |
| Best mFscore 0.00% |
| Val Time 8.0s |
|
|
| [92m[1m★ New best mFscore: 1.53% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.4702 lr=1.49e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.4580 lr=1.90e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.4580 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 002 / 100 | Elapsed: 0:00:48[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.4580 |
| Val Loss 0.4700 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 4.78%[0m |
| [92m[1mmIoU [0m [92m[1m 3.85%[0m |
| [92m[1mmFscore [0m [92m[1m 6.96%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 12.24%[0m |
| [0m[1mmRecall [0m [0m[1m 21.10%[0m |
| [0m[1mKappa [0m [0m[1m 3.60%[0m |
| ────────────────── ────────── |
| Best mFscore 1.53% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 6.96% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.3816 lr=2.39e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.3681 lr=2.80e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.3681 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 003 / 100 | Elapsed: 0:01:08[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3681 |
| Val Loss 0.4604 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.15%[0m |
| [92m[1mmIoU [0m [92m[1m 9.46%[0m |
| [92m[1mmFscore [0m [92m[1m 16.43%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 21.52%[0m |
| [0m[1mmRecall [0m [0m[1m 34.66%[0m |
| [0m[1mKappa [0m [0m[1m 8.40%[0m |
| ────────────────── ────────── |
| Best mFscore 6.96% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 16.43% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.3299 lr=3.29e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.3307 lr=3.71e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.3307 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 004 / 100 | Elapsed: 0:01:28[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3307 |
| Val Loss 0.3811 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 18.68%[0m |
| [92m[1mmIoU [0m [92m[1m 12.89%[0m |
| [92m[1mmFscore [0m [92m[1m 21.64%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 24.23%[0m |
| [0m[1mmRecall [0m [0m[1m 40.42%[0m |
| [0m[1mKappa [0m [0m[1m 15.21%[0m |
| ────────────────── ────────── |
| Best mFscore 16.43% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 21.64% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.3185 lr=4.20e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.3138 lr=4.61e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.3138 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 005 / 100 | Elapsed: 0:01:48[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3138 |
| Val Loss 0.3767 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 19.35%[0m |
| [92m[1mmIoU [0m [92m[1m 14.33%[0m |
| [92m[1mmFscore [0m [92m[1m 23.54%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 24.09%[0m |
| [0m[1mmRecall [0m [0m[1m 44.80%[0m |
| [0m[1mKappa [0m [0m[1m 15.93%[0m |
| ────────────────── ────────── |
| Best mFscore 21.64% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 23.54% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.2969 lr=5.00e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.3010 lr=5.00e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.3010 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 006 / 100 | Elapsed: 0:02:07[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3010 |
| Val Loss 0.3934 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 15.89%[0m |
| [92m[1mmIoU [0m [92m[1m 13.16%[0m |
| [92m[1mmFscore [0m [92m[1m 21.60%[0m |
| [0m[1mmPrecision [0m [0m[1m 26.62%[0m |
| [0m[1mmRecall [0m [0m[1m 38.86%[0m |
| [0m[1mKappa [0m [0m[1m 12.64%[0m |
| ────────────────── ────────── |
| Best mFscore 23.54% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.2832 lr=5.00e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.2843 lr=5.00e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2843 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 0.2843 |
| Val Loss 0.3459 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 25.67%[0m |
| [92m[1mmIoU [0m [92m[1m 17.13%[0m |
| [92m[1mmFscore [0m [92m[1m 27.13%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 25.42%[0m |
| [0m[1mmRecall [0m [0m[1m 50.83%[0m |
| [0m[1mKappa [0m [0m[1m 21.60%[0m |
| ────────────────── ────────── |
| Best mFscore 23.54% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 27.13% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.2528 lr=4.99e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.2540 lr=4.99e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2540 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 0.2540 |
| Val Loss 0.3211 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 27.46%[0m |
| [92m[1mmIoU [0m [92m[1m 19.95%[0m |
| [92m[1mmFscore [0m [92m[1m 30.62%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 26.76%[0m |
| [0m[1mmRecall [0m [0m[1m 52.54%[0m |
| [0m[1mKappa [0m [0m[1m 23.48%[0m |
| ────────────────── ────────── |
| Best mFscore 27.13% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 30.62% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.2362 lr=4.99e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.2386 lr=4.98e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2386 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 0.2386 |
| Val Loss 0.3444 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 25.69%[0m |
| [92m[1mmIoU [0m [92m[1m 19.77%[0m |
| [92m[1mmFscore [0m [92m[1m 30.38%[0m |
| [0m[1mmPrecision [0m [0m[1m 34.97%[0m |
| [0m[1mmRecall [0m [0m[1m 52.36%[0m |
| [0m[1mKappa [0m [0m[1m 21.11%[0m |
| ────────────────── ────────── |
| Best mFscore 30.62% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.2394 lr=4.98e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.2330 lr=4.97e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2330 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 010 / 100 | Elapsed: 0:03:25[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2330 |
| Val Loss 0.3467 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 28.43%[0m |
| [92m[1mmIoU [0m [92m[1m 21.95%[0m |
| [92m[1mmFscore [0m [92m[1m 32.84%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 33.16%[0m |
| [0m[1mmRecall [0m [0m[1m 56.30%[0m |
| [0m[1mKappa [0m [0m[1m 24.21%[0m |
| ────────────────── ────────── |
| Best mFscore 30.62% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 32.84% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.2043 lr=4.96e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.2154 lr=4.96e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2154 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 0.2154 |
| Val Loss 0.3558 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 24.27%[0m |
| [92m[1mmIoU [0m [92m[1m 19.69%[0m |
| [92m[1mmFscore [0m [92m[1m 30.26%[0m |
| [0m[1mmPrecision [0m [0m[1m 32.46%[0m |
| [0m[1mmRecall [0m [0m[1m 55.23%[0m |
| [0m[1mKappa [0m [0m[1m 20.41%[0m |
| ────────────────── ────────── |
| Best mFscore 32.84% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.2088 lr=4.95e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.2117 lr=4.94e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2117 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 012 / 100 | Elapsed: 0:04:04[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2117 |
| Val Loss 0.3353 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 29.66%[0m |
| [92m[1mmIoU [0m [92m[1m 21.72%[0m |
| [92m[1mmFscore [0m [92m[1m 32.85%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 34.24%[0m |
| [0m[1mmRecall [0m [0m[1m 55.83%[0m |
| [0m[1mKappa [0m [0m[1m 25.10%[0m |
| ────────────────── ────────── |
| Best mFscore 32.84% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 32.85% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.2035 lr=4.93e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.2027 lr=4.92e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2027 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 013 / 100 | Elapsed: 0:04:24[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2027 |
| Val Loss 0.3507 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 31.87%[0m |
| [92m[1mmIoU [0m [92m[1m 23.23%[0m |
| [92m[1mmFscore [0m [92m[1m 34.01%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 37.14%[0m |
| [0m[1mmRecall [0m [0m[1m 52.49%[0m |
| [0m[1mKappa [0m [0m[1m 26.20%[0m |
| ────────────────── ────────── |
| Best mFscore 32.85% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 34.01% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.1862 lr=4.91e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.1859 lr=4.90e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1859 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 0.1859 |
| Val Loss 0.3387 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 37.81%[0m |
| [92m[1mmIoU [0m [92m[1m 26.02%[0m |
| [92m[1mmFscore [0m [92m[1m 37.40%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 35.78%[0m |
| [0m[1mmRecall [0m [0m[1m 60.62%[0m |
| [0m[1mKappa [0m [0m[1m 32.50%[0m |
| ────────────────── ────────── |
| Best mFscore 34.01% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 37.40% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.1795 lr=4.89e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.1813 lr=4.88e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1813 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 015 / 100 | Elapsed: 0:05:04[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1813 |
| Val Loss 0.3222 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 36.76%[0m |
| [92m[1mmIoU [0m [92m[1m 25.36%[0m |
| [92m[1mmFscore [0m [92m[1m 37.60%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 38.10%[0m |
| [0m[1mmRecall [0m [0m[1m 57.48%[0m |
| [0m[1mKappa [0m [0m[1m 30.95%[0m |
| ────────────────── ────────── |
| Best mFscore 37.40% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 37.60% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.1742 lr=4.86e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.1775 lr=4.85e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1775 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 016 / 100 | Elapsed: 0:05:24[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1775 |
| Val Loss 0.3534 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 41.15%[0m |
| [92m[1mmIoU [0m [92m[1m 26.72%[0m |
| [92m[1mmFscore [0m [92m[1m 38.86%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 37.02%[0m |
| [0m[1mmRecall [0m [0m[1m 61.15%[0m |
| [0m[1mKappa [0m [0m[1m 35.23%[0m |
| ────────────────── ────────── |
| Best mFscore 37.60% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 38.86% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.1641 lr=4.84e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.1671 lr=4.82e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1671 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 017 / 100 | Elapsed: 0:05:44[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1671 |
| Val Loss 0.3747 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 38.53%[0m |
| [92m[1mmIoU [0m [92m[1m 26.40%[0m |
| [92m[1mmFscore [0m [92m[1m 38.31%[0m |
| [0m[1mmPrecision [0m [0m[1m 38.61%[0m |
| [0m[1mmRecall [0m [0m[1m 56.42%[0m |
| [0m[1mKappa [0m [0m[1m 32.26%[0m |
| ────────────────── ────────── |
| Best mFscore 38.86% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.1576 lr=4.80e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.1659 lr=4.79e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1659 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 018 / 100 | Elapsed: 0:06:03[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1659 |
| Val Loss 0.2840 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 38.96%[0m |
| [92m[1mmIoU [0m [92m[1m 24.96%[0m |
| [92m[1mmFscore [0m [92m[1m 37.02%[0m |
| [0m[1mmPrecision [0m [0m[1m 37.33%[0m |
| [0m[1mmRecall [0m [0m[1m 59.86%[0m |
| [0m[1mKappa [0m [0m[1m 32.93%[0m |
| ────────────────── ────────── |
| Best mFscore 38.86% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.1512 lr=4.77e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.1513 lr=4.76e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1513 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 019 / 100 | Elapsed: 0:06:22[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1513 |
| Val Loss 0.3472 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 38.97%[0m |
| [92m[1mmIoU [0m [92m[1m 27.76%[0m |
| [92m[1mmFscore [0m [92m[1m 39.76%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 39.19%[0m |
| [0m[1mmRecall [0m [0m[1m 61.84%[0m |
| [0m[1mKappa [0m [0m[1m 32.75%[0m |
| ────────────────── ────────── |
| Best mFscore 38.86% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 39.76% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.1446 lr=4.74e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.1484 lr=4.72e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1484 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 020 / 100 | Elapsed: 0:06:42[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1484 |
| Val Loss 0.3682 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 41.05%[0m |
| [92m[1mmIoU [0m [92m[1m 28.60%[0m |
| [92m[1mmFscore [0m [92m[1m 40.65%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 40.27%[0m |
| [0m[1mmRecall [0m [0m[1m 62.48%[0m |
| [0m[1mKappa [0m [0m[1m 35.06%[0m |
| ────────────────── ────────── |
| Best mFscore 39.76% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 40.65% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.1439 lr=4.70e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.1468 lr=4.68e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1468 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 021 / 100 | Elapsed: 0:07:02[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1468 |
| Val Loss 0.3223 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 49.20%[0m |
| [92m[1mmIoU [0m [92m[1m 30.47%[0m |
| [92m[1mmFscore [0m [92m[1m 43.35%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 39.93%[0m |
| [0m[1mmRecall [0m [0m[1m 64.33%[0m |
| [0m[1mKappa [0m [0m[1m 42.38%[0m |
| ────────────────── ────────── |
| Best mFscore 40.65% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 43.35% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.1463 lr=4.66e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.1425 lr=4.64e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1425 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 022 / 100 | Elapsed: 0:07:22[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1425 |
| Val Loss 0.3719 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 43.40%[0m |
| [92m[1mmIoU [0m [92m[1m 29.83%[0m |
| [92m[1mmFscore [0m [92m[1m 42.29%[0m |
| [0m[1mmPrecision [0m [0m[1m 39.61%[0m |
| [0m[1mmRecall [0m [0m[1m 63.64%[0m |
| [0m[1mKappa [0m [0m[1m 36.91%[0m |
| ────────────────── ────────── |
| Best mFscore 43.35% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.1290 lr=4.61e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.1353 lr=4.59e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1353 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 023 / 100 | Elapsed: 0:07:41[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1353 |
| Val Loss 0.3891 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 48.34%[0m |
| [92m[1mmIoU [0m [92m[1m 31.73%[0m |
| [92m[1mmFscore [0m [92m[1m 44.68%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 41.13%[0m |
| [0m[1mmRecall [0m [0m[1m 65.50%[0m |
| [0m[1mKappa [0m [0m[1m 41.53%[0m |
| ────────────────── ────────── |
| Best mFscore 43.35% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 44.68% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.1243 lr=4.57e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.1274 lr=4.55e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1274 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 024 / 100 | Elapsed: 0:08:01[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1274 |
| Val Loss 0.3769 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 50.92%[0m |
| [92m[1mmIoU [0m [92m[1m 32.57%[0m |
| [92m[1mmFscore [0m [92m[1m 45.71%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 41.54%[0m |
| [0m[1mmRecall [0m [0m[1m 66.71%[0m |
| [0m[1mKappa [0m [0m[1m 43.88%[0m |
| ────────────────── ────────── |
| Best mFscore 44.68% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 45.71% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.1267 lr=4.52e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.1303 lr=4.50e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1303 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 025 / 100 | Elapsed: 0:08:20[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1303 |
| Val Loss 0.4062 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 48.19%[0m |
| [92m[1mmIoU [0m [92m[1m 30.87%[0m |
| [92m[1mmFscore [0m [92m[1m 43.50%[0m |
| [0m[1mmPrecision [0m [0m[1m 40.79%[0m |
| [0m[1mmRecall [0m [0m[1m 64.50%[0m |
| [0m[1mKappa [0m [0m[1m 41.55%[0m |
| ────────────────── ────────── |
| Best mFscore 45.71% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.1195 lr=4.47e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.1190 lr=4.45e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1190 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 026 / 100 | Elapsed: 0:08:40[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1190 |
| Val Loss 0.3860 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 49.89%[0m |
| [92m[1mmIoU [0m [92m[1m 31.44%[0m |
| [92m[1mmFscore [0m [92m[1m 44.33%[0m |
| [0m[1mmPrecision [0m [0m[1m 40.73%[0m |
| [0m[1mmRecall [0m [0m[1m 66.20%[0m |
| [0m[1mKappa [0m [0m[1m 43.14%[0m |
| ────────────────── ────────── |
| Best mFscore 45.71% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.1153 lr=4.42e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.1166 lr=4.40e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1166 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 027 / 100 | Elapsed: 0:08:59[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1166 |
| Val Loss 0.3672 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 50.15%[0m |
| [92m[1mmIoU [0m [92m[1m 31.96%[0m |
| [92m[1mmFscore [0m [92m[1m 44.72%[0m |
| [0m[1mmPrecision [0m [0m[1m 41.00%[0m |
| [0m[1mmRecall [0m [0m[1m 65.83%[0m |
| [0m[1mKappa [0m [0m[1m 43.52%[0m |
| ────────────────── ────────── |
| Best mFscore 45.71% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.1159 lr=4.37e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.1197 lr=4.34e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1197 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 028 / 100 | Elapsed: 0:09:18[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1197 |
| Val Loss 0.3629 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 53.25%[0m |
| [92m[1mmIoU [0m [92m[1m 33.68%[0m |
| [92m[1mmFscore [0m [92m[1m 47.08%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 42.41%[0m |
| [0m[1mmRecall [0m [0m[1m 67.32%[0m |
| [0m[1mKappa [0m [0m[1m 46.19%[0m |
| ────────────────── ────────── |
| Best mFscore 45.71% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 47.08% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.1094 lr=4.31e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.1128 lr=4.29e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1128 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 029 / 100 | Elapsed: 0:09:38[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1128 |
| Val Loss 0.3898 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 53.12%[0m |
| [92m[1mmIoU [0m [92m[1m 34.25%[0m |
| [92m[1mmFscore [0m [92m[1m 47.40%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 42.96%[0m |
| [0m[1mmRecall [0m [0m[1m 67.86%[0m |
| [0m[1mKappa [0m [0m[1m 46.29%[0m |
| ────────────────── ────────── |
| Best mFscore 47.08% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 47.40% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0976 lr=4.26e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0995 lr=4.23e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0995 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 030 / 100 | Elapsed: 0:09:58[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0995 |
| Val Loss 0.4086 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 52.59%[0m |
| [92m[1mmIoU [0m [92m[1m 32.98%[0m |
| [92m[1mmFscore [0m [92m[1m 46.24%[0m |
| [0m[1mmPrecision [0m [0m[1m 41.68%[0m |
| [0m[1mmRecall [0m [0m[1m 66.95%[0m |
| [0m[1mKappa [0m [0m[1m 45.65%[0m |
| ────────────────── ────────── |
| Best mFscore 47.40% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0944 lr=4.20e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0973 lr=4.17e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0973 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 031 / 100 | Elapsed: 0:10:17[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0973 |
| Val Loss 0.4253 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 53.91%[0m |
| [92m[1mmIoU [0m [92m[1m 34.17%[0m |
| [92m[1mmFscore [0m [92m[1m 47.39%[0m |
| [0m[1mmPrecision [0m [0m[1m 43.49%[0m |
| [0m[1mmRecall [0m [0m[1m 66.81%[0m |
| [0m[1mKappa [0m [0m[1m 46.74%[0m |
| ────────────────── ────────── |
| Best mFscore 47.40% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0990 lr=4.13e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0979 lr=4.11e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0979 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 032 / 100 | Elapsed: 0:10:37[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0979 |
| Val Loss 0.4131 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 54.47%[0m |
| [92m[1mmIoU [0m [92m[1m 35.18%[0m |
| [92m[1mmFscore [0m [92m[1m 48.35%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 43.84%[0m |
| [0m[1mmRecall [0m [0m[1m 68.12%[0m |
| [0m[1mKappa [0m [0m[1m 47.42%[0m |
| ────────────────── ────────── |
| Best mFscore 47.40% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 48.35% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0916 lr=4.07e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0942 lr=4.04e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0942 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 033 / 100 | Elapsed: 0:10:56[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0942 |
| Val Loss 0.3577 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 51.36%[0m |
| [92m[1mmIoU [0m [92m[1m 34.26%[0m |
| [92m[1mmFscore [0m [92m[1m 47.44%[0m |
| [0m[1mmPrecision [0m [0m[1m 44.22%[0m |
| [0m[1mmRecall [0m [0m[1m 67.45%[0m |
| [0m[1mKappa [0m [0m[1m 44.19%[0m |
| ────────────────── ────────── |
| Best mFscore 48.35% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0898 lr=4.01e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0903 lr=3.98e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0903 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 034 / 100 | Elapsed: 0:11:16[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0903 |
| Val Loss 0.3951 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 55.40%[0m |
| [92m[1mmIoU [0m [92m[1m 34.98%[0m |
| [92m[1mmFscore [0m [92m[1m 48.25%[0m |
| [0m[1mmPrecision [0m [0m[1m 44.19%[0m |
| [0m[1mmRecall [0m [0m[1m 67.91%[0m |
| [0m[1mKappa [0m [0m[1m 48.22%[0m |
| ────────────────── ────────── |
| Best mFscore 48.35% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0875 lr=3.94e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0919 lr=3.91e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0919 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 035 / 100 | Elapsed: 0:11:35[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0919 |
| Val Loss 0.4038 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 57.84%[0m |
| [92m[1mmIoU [0m [92m[1m 35.49%[0m |
| [92m[1mmFscore [0m [92m[1m 48.97%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 43.67%[0m |
| [0m[1mmRecall [0m [0m[1m 68.51%[0m |
| [0m[1mKappa [0m [0m[1m 50.54%[0m |
| ────────────────── ────────── |
| Best mFscore 48.35% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 48.97% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0927 lr=3.87e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0947 lr=3.84e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0947 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 036 / 100 | Elapsed: 0:11:55[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0947 |
| Val Loss 0.4228 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 55.61%[0m |
| [92m[1mmIoU [0m [92m[1m 35.68%[0m |
| [92m[1mmFscore [0m [92m[1m 49.19%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 44.28%[0m |
| [0m[1mmRecall [0m [0m[1m 68.06%[0m |
| [0m[1mKappa [0m [0m[1m 48.45%[0m |
| ────────────────── ────────── |
| Best mFscore 48.97% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 49.19% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0985 lr=3.80e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0963 lr=3.77e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0963 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 037 / 100 | Elapsed: 0:12:15[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0963 |
| Val Loss 0.4207 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 55.49%[0m |
| [92m[1mmIoU [0m [92m[1m 35.17%[0m |
| [92m[1mmFscore [0m [92m[1m 48.47%[0m |
| [0m[1mmPrecision [0m [0m[1m 43.77%[0m |
| [0m[1mmRecall [0m [0m[1m 68.86%[0m |
| [0m[1mKappa [0m [0m[1m 48.38%[0m |
| ────────────────── ────────── |
| Best mFscore 49.19% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0804 lr=3.73e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0858 lr=3.70e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0858 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 038 / 100 | Elapsed: 0:12:34[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0858 |
| Val Loss 0.4121 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 55.83%[0m |
| [92m[1mmIoU [0m [92m[1m 35.97%[0m |
| [92m[1mmFscore [0m [92m[1m 49.19%[0m |
| [0m[1mmPrecision [0m [0m[1m 44.33%[0m |
| [0m[1mmRecall [0m [0m[1m 69.04%[0m |
| [0m[1mKappa [0m [0m[1m 48.90%[0m |
| ────────────────── ────────── |
| Best mFscore 49.19% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0842 lr=3.66e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0823 lr=3.63e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0823 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 039 / 100 | Elapsed: 0:12:54[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0823 |
| Val Loss 0.3949 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 54.06%[0m |
| [92m[1mmIoU [0m [92m[1m 35.91%[0m |
| [92m[1mmFscore [0m [92m[1m 49.19%[0m |
| [0m[1mmPrecision [0m [0m[1m 44.48%[0m |
| [0m[1mmRecall [0m [0m[1m 69.34%[0m |
| [0m[1mKappa [0m [0m[1m 47.09%[0m |
| ────────────────── ────────── |
| Best mFscore 49.19% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0743 lr=3.59e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0758 lr=3.55e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0758 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 040 / 100 | Elapsed: 0:13:13[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0758 |
| Val Loss 0.4159 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 57.83%[0m |
| [92m[1mmIoU [0m [92m[1m 37.94%[0m |
| [92m[1mmFscore [0m [92m[1m 51.47%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 46.00%[0m |
| [0m[1mmRecall [0m [0m[1m 69.84%[0m |
| [0m[1mKappa [0m [0m[1m 50.75%[0m |
| ────────────────── ────────── |
| Best mFscore 49.19% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 51.47% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0720 lr=3.51e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0723 lr=3.48e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0723 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 041 / 100 | Elapsed: 0:13:33[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0723 |
| Val Loss 0.4412 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 58.21%[0m |
| [92m[1mmIoU [0m [92m[1m 37.75%[0m |
| [92m[1mmFscore [0m [92m[1m 51.19%[0m |
| [0m[1mmPrecision [0m [0m[1m 46.39%[0m |
| [0m[1mmRecall [0m [0m[1m 68.92%[0m |
| [0m[1mKappa [0m [0m[1m 50.91%[0m |
| ────────────────── ────────── |
| Best mFscore 51.47% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0691 lr=3.44e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0698 lr=3.40e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0698 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 042 / 100 | Elapsed: 0:13:52[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0698 |
| Val Loss 0.4344 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 60.19%[0m |
| [92m[1mmIoU [0m [92m[1m 38.55%[0m |
| [92m[1mmFscore [0m [92m[1m 52.24%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 46.81%[0m |
| [0m[1mmRecall [0m [0m[1m 69.48%[0m |
| [0m[1mKappa [0m [0m[1m 52.85%[0m |
| ────────────────── ────────── |
| Best mFscore 51.47% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 52.24% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0711 lr=3.36e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0737 lr=3.33e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0737 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 043 / 100 | Elapsed: 0:14:12[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0737 |
| Val Loss 0.4247 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 58.15%[0m |
| [92m[1mmIoU [0m [92m[1m 38.23%[0m |
| [92m[1mmFscore [0m [92m[1m 51.98%[0m |
| [0m[1mmPrecision [0m [0m[1m 46.44%[0m |
| [0m[1mmRecall [0m [0m[1m 70.24%[0m |
| [0m[1mKappa [0m [0m[1m 50.90%[0m |
| ────────────────── ────────── |
| Best mFscore 52.24% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0686 lr=3.29e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0683 lr=3.25e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0683 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 044 / 100 | Elapsed: 0:14:31[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0683 |
| Val Loss 0.4058 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 58.59%[0m |
| [92m[1mmIoU [0m [92m[1m 36.49%[0m |
| [92m[1mmFscore [0m [92m[1m 50.25%[0m |
| [0m[1mmPrecision [0m [0m[1m 44.83%[0m |
| [0m[1mmRecall [0m [0m[1m 70.28%[0m |
| [0m[1mKappa [0m [0m[1m 51.39%[0m |
| ────────────────── ────────── |
| Best mFscore 52.24% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0660 lr=3.21e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0650 lr=3.17e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0650 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 045 / 100 | Elapsed: 0:14:51[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0650 |
| Val Loss 0.4500 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 61.06%[0m |
| [92m[1mmIoU [0m [92m[1m 39.31%[0m |
| [92m[1mmFscore [0m [92m[1m 53.00%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 47.23%[0m |
| [0m[1mmRecall [0m [0m[1m 70.38%[0m |
| [0m[1mKappa [0m [0m[1m 53.84%[0m |
| ────────────────── ────────── |
| Best mFscore 52.24% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 53.00% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0617 lr=3.13e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0623 lr=3.09e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0623 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 046 / 100 | Elapsed: 0:15:10[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0623 |
| Val Loss 0.4150 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 61.45%[0m |
| [92m[1mmIoU [0m [92m[1m 39.88%[0m |
| [92m[1mmFscore [0m [92m[1m 53.56%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 47.72%[0m |
| [0m[1mmRecall [0m [0m[1m 70.69%[0m |
| [0m[1mKappa [0m [0m[1m 54.28%[0m |
| ────────────────── ────────── |
| Best mFscore 53.00% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 53.56% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0608 lr=3.05e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0608 lr=3.01e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0608 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 047 / 100 | Elapsed: 0:15:30[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0608 |
| Val Loss 0.4566 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 62.86%[0m |
| [92m[1mmIoU [0m [92m[1m 40.39%[0m |
| [92m[1mmFscore [0m [92m[1m 54.35%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 48.44%[0m |
| [0m[1mmRecall [0m [0m[1m 70.58%[0m |
| [0m[1mKappa [0m [0m[1m 55.56%[0m |
| ────────────────── ────────── |
| Best mFscore 53.56% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 54.35% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0641 lr=2.97e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0654 lr=2.93e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0654 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 048 / 100 | Elapsed: 0:15:50[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0654 |
| Val Loss 0.4405 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 60.07%[0m |
| [92m[1mmIoU [0m [92m[1m 38.16%[0m |
| [92m[1mmFscore [0m [92m[1m 51.77%[0m |
| [0m[1mmPrecision [0m [0m[1m 46.00%[0m |
| [0m[1mmRecall [0m [0m[1m 69.93%[0m |
| [0m[1mKappa [0m [0m[1m 52.92%[0m |
| ────────────────── ────────── |
| Best mFscore 54.35% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0640 lr=2.89e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0618 lr=2.85e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0618 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 049 / 100 | Elapsed: 0:16:10[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0618 |
| Val Loss 0.4523 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 63.08%[0m |
| [92m[1mmIoU [0m [92m[1m 40.22%[0m |
| [92m[1mmFscore [0m [92m[1m 53.91%[0m |
| [0m[1mmPrecision [0m [0m[1m 48.41%[0m |
| [0m[1mmRecall [0m [0m[1m 70.34%[0m |
| [0m[1mKappa [0m [0m[1m 55.88%[0m |
| ────────────────── ────────── |
| Best mFscore 54.35% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0656 lr=2.81e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0651 lr=2.77e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0651 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 050 / 100 | Elapsed: 0:16:29[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0651 |
| Val Loss 0.4501 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 64.67%[0m |
| [92m[1mmIoU [0m [92m[1m 41.34%[0m |
| [92m[1mmFscore [0m [92m[1m 55.28%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 49.17%[0m |
| [0m[1mmRecall [0m [0m[1m 69.86%[0m |
| [0m[1mKappa [0m [0m[1m 57.32%[0m |
| ────────────────── ────────── |
| Best mFscore 54.35% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 55.28% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0623 lr=2.73e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0616 lr=2.69e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0616 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 051 / 100 | Elapsed: 0:16:49[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0616 |
| Val Loss 0.4498 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 60.74%[0m |
| [92m[1mmIoU [0m [92m[1m 38.61%[0m |
| [92m[1mmFscore [0m [92m[1m 52.41%[0m |
| [0m[1mmPrecision [0m [0m[1m 46.73%[0m |
| [0m[1mmRecall [0m [0m[1m 70.90%[0m |
| [0m[1mKappa [0m [0m[1m 53.38%[0m |
| ────────────────── ────────── |
| Best mFscore 55.28% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0574 lr=2.65e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0587 lr=2.61e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0587 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 052 / 100 | Elapsed: 0:17:08[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0587 |
| Val Loss 0.4950 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 61.88%[0m |
| [92m[1mmIoU [0m [92m[1m 39.46%[0m |
| [92m[1mmFscore [0m [92m[1m 53.40%[0m |
| [0m[1mmPrecision [0m [0m[1m 47.33%[0m |
| [0m[1mmRecall [0m [0m[1m 70.52%[0m |
| [0m[1mKappa [0m [0m[1m 54.66%[0m |
| ────────────────── ────────── |
| Best mFscore 55.28% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0564 lr=2.56e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0549 lr=2.53e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0549 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 053 / 100 | Elapsed: 0:17:28[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0549 |
| Val Loss 0.4538 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 64.20%[0m |
| [92m[1mmIoU [0m [92m[1m 41.00%[0m |
| [92m[1mmFscore [0m [92m[1m 54.90%[0m |
| [0m[1mmPrecision [0m [0m[1m 48.64%[0m |
| [0m[1mmRecall [0m [0m[1m 71.25%[0m |
| [0m[1mKappa [0m [0m[1m 56.98%[0m |
| ────────────────── ────────── |
| Best mFscore 55.28% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0544 lr=2.48e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0546 lr=2.45e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0546 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 054 / 100 | Elapsed: 0:17:47[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0546 |
| Val Loss 0.4474 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 62.70%[0m |
| [92m[1mmIoU [0m [92m[1m 40.97%[0m |
| [92m[1mmFscore [0m [92m[1m 54.85%[0m |
| [0m[1mmPrecision [0m [0m[1m 48.78%[0m |
| [0m[1mmRecall [0m [0m[1m 71.07%[0m |
| [0m[1mKappa [0m [0m[1m 55.52%[0m |
| ────────────────── ────────── |
| Best mFscore 55.28% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0531 lr=2.40e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0529 lr=2.36e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0529 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 055 / 100 | Elapsed: 0:18:06[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0529 |
| Val Loss 0.4360 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 64.17%[0m |
| [92m[1mmIoU [0m [92m[1m 42.15%[0m |
| [92m[1mmFscore [0m [92m[1m 56.19%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 50.29%[0m |
| [0m[1mmRecall [0m [0m[1m 71.18%[0m |
| [0m[1mKappa [0m [0m[1m 56.97%[0m |
| ────────────────── ────────── |
| Best mFscore 55.28% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 56.19% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0504 lr=2.32e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0507 lr=2.28e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0507 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 056 / 100 | Elapsed: 0:18:26[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0507 |
| Val Loss 0.4577 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 65.01%[0m |
| [92m[1mmIoU [0m [92m[1m 41.83%[0m |
| [92m[1mmFscore [0m [92m[1m 55.78%[0m |
| [0m[1mmPrecision [0m [0m[1m 49.55%[0m |
| [0m[1mmRecall [0m [0m[1m 71.63%[0m |
| [0m[1mKappa [0m [0m[1m 57.80%[0m |
| ────────────────── ────────── |
| Best mFscore 56.19% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0485 lr=2.24e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0489 lr=2.20e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0489 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 057 / 100 | Elapsed: 0:18:45[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0489 |
| Val Loss 0.4838 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 64.75%[0m |
| [92m[1mmIoU [0m [92m[1m 41.94%[0m |
| [92m[1mmFscore [0m [92m[1m 55.95%[0m |
| [0m[1mmPrecision [0m [0m[1m 49.77%[0m |
| [0m[1mmRecall [0m [0m[1m 70.49%[0m |
| [0m[1mKappa [0m [0m[1m 57.53%[0m |
| ────────────────── ────────── |
| Best mFscore 56.19% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0486 lr=2.16e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0488 lr=2.12e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0488 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 058 / 100 | Elapsed: 0:19:05[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0488 |
| Val Loss 0.4859 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.53%[0m |
| [92m[1mmIoU [0m [92m[1m 43.04%[0m |
| [92m[1mmFscore [0m [92m[1m 57.03%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 50.94%[0m |
| [0m[1mmRecall [0m [0m[1m 70.30%[0m |
| [0m[1mKappa [0m [0m[1m 59.28%[0m |
| ────────────────── ────────── |
| Best mFscore 56.19% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 57.03% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0488 lr=2.08e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0479 lr=2.04e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0479 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 059 / 100 | Elapsed: 0:19:25[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0479 |
| Val Loss 0.4593 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 64.77%[0m |
| [92m[1mmIoU [0m [92m[1m 42.21%[0m |
| [92m[1mmFscore [0m [92m[1m 56.06%[0m |
| [0m[1mmPrecision [0m [0m[1m 50.01%[0m |
| [0m[1mmRecall [0m [0m[1m 71.25%[0m |
| [0m[1mKappa [0m [0m[1m 57.62%[0m |
| ────────────────── ────────── |
| Best mFscore 57.03% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0454 lr=2.00e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0466 lr=1.96e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0466 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 060 / 100 | Elapsed: 0:19:44[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0466 |
| Val Loss 0.4867 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 65.99%[0m |
| [92m[1mmIoU [0m [92m[1m 42.48%[0m |
| [92m[1mmFscore [0m [92m[1m 56.46%[0m |
| [0m[1mmPrecision [0m [0m[1m 50.55%[0m |
| [0m[1mmRecall [0m [0m[1m 69.70%[0m |
| [0m[1mKappa [0m [0m[1m 58.70%[0m |
| ────────────────── ────────── |
| Best mFscore 57.03% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0468 lr=1.92e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0460 lr=1.88e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0460 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 061 / 100 | Elapsed: 0:20:03[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0460 |
| Val Loss 0.4997 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.78%[0m |
| [92m[1mmIoU [0m [92m[1m 42.89%[0m |
| [92m[1mmFscore [0m [92m[1m 56.92%[0m |
| [0m[1mmPrecision [0m [0m[1m 50.71%[0m |
| [0m[1mmRecall [0m [0m[1m 70.66%[0m |
| [0m[1mKappa [0m [0m[1m 59.57%[0m |
| ────────────────── ────────── |
| Best mFscore 57.03% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0459 lr=1.84e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0450 lr=1.81e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0450 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 062 / 100 | Elapsed: 0:20:23[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0450 |
| Val Loss 0.5076 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 65.43%[0m |
| [92m[1mmIoU [0m [92m[1m 43.07%[0m |
| [92m[1mmFscore [0m [92m[1m 57.11%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 51.30%[0m |
| [0m[1mmRecall [0m [0m[1m 70.26%[0m |
| [0m[1mKappa [0m [0m[1m 58.18%[0m |
| ────────────────── ────────── |
| Best mFscore 57.03% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 57.11% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0428 lr=1.76e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0432 lr=1.73e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0432 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 063 / 100 | Elapsed: 0:20:43[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0432 |
| Val Loss 0.5067 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.82%[0m |
| [92m[1mmIoU [0m [92m[1m 43.67%[0m |
| [92m[1mmFscore [0m [92m[1m 57.75%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 51.89%[0m |
| [0m[1mmRecall [0m [0m[1m 70.62%[0m |
| [0m[1mKappa [0m [0m[1m 59.55%[0m |
| ────────────────── ────────── |
| Best mFscore 57.11% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 57.75% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0413 lr=1.69e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0429 lr=1.65e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0429 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 064 / 100 | Elapsed: 0:21:02[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0429 |
| Val Loss 0.5185 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.22%[0m |
| [92m[1mmIoU [0m [92m[1m 43.36%[0m |
| [92m[1mmFscore [0m [92m[1m 57.50%[0m |
| [0m[1mmPrecision [0m [0m[1m 51.66%[0m |
| [0m[1mmRecall [0m [0m[1m 70.58%[0m |
| [0m[1mKappa [0m [0m[1m 59.01%[0m |
| ────────────────── ────────── |
| Best mFscore 57.75% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0414 lr=1.61e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0413 lr=1.58e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0413 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 065 / 100 | Elapsed: 0:21:22[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0413 |
| Val Loss 0.4916 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 65.77%[0m |
| [92m[1mmIoU [0m [92m[1m 43.37%[0m |
| [92m[1mmFscore [0m [92m[1m 57.40%[0m |
| [0m[1mmPrecision [0m [0m[1m 51.64%[0m |
| [0m[1mmRecall [0m [0m[1m 70.52%[0m |
| [0m[1mKappa [0m [0m[1m 58.57%[0m |
| ────────────────── ────────── |
| Best mFscore 57.75% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0387 lr=1.54e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0410 lr=1.50e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0410 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 066 / 100 | Elapsed: 0:21:41[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0410 |
| Val Loss 0.5076 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 65.77%[0m |
| [92m[1mmIoU [0m [92m[1m 42.20%[0m |
| [92m[1mmFscore [0m [92m[1m 56.12%[0m |
| [0m[1mmPrecision [0m [0m[1m 49.87%[0m |
| [0m[1mmRecall [0m [0m[1m 70.37%[0m |
| [0m[1mKappa [0m [0m[1m 58.56%[0m |
| ────────────────── ────────── |
| Best mFscore 57.75% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0411 lr=1.46e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0408 lr=1.43e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0408 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 067 / 100 | Elapsed: 0:22:01[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0408 |
| Val Loss 0.5097 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 65.87%[0m |
| [92m[1mmIoU [0m [92m[1m 43.72%[0m |
| [92m[1mmFscore [0m [92m[1m 57.77%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 51.88%[0m |
| [0m[1mmRecall [0m [0m[1m 70.83%[0m |
| [0m[1mKappa [0m [0m[1m 58.63%[0m |
| ────────────────── ────────── |
| Best mFscore 57.75% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 57.77% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0394 lr=1.39e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0396 lr=1.36e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0396 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 068 / 100 | Elapsed: 0:22:20[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0396 |
| Val Loss 0.4684 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.88%[0m |
| [92m[1mmIoU [0m [92m[1m 43.31%[0m |
| [92m[1mmFscore [0m [92m[1m 57.35%[0m |
| [0m[1mmPrecision [0m [0m[1m 51.19%[0m |
| [0m[1mmRecall [0m [0m[1m 70.52%[0m |
| [0m[1mKappa [0m [0m[1m 59.70%[0m |
| ────────────────── ────────── |
| Best mFscore 57.77% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0378 lr=1.32e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0384 lr=1.29e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0384 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 069 / 100 | Elapsed: 0:22:40[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0384 |
| Val Loss 0.5369 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 67.08%[0m |
| [92m[1mmIoU [0m [92m[1m 44.04%[0m |
| [92m[1mmFscore [0m [92m[1m 58.09%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 52.43%[0m |
| [0m[1mmRecall [0m [0m[1m 70.22%[0m |
| [0m[1mKappa [0m [0m[1m 59.91%[0m |
| ────────────────── ────────── |
| Best mFscore 57.77% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 58.09% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0383 lr=1.25e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0383 lr=1.22e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0383 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 070 / 100 | Elapsed: 0:23:00[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0383 |
| Val Loss 0.5174 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 67.26%[0m |
| [92m[1mmIoU [0m [92m[1m 43.97%[0m |
| [92m[1mmFscore [0m [92m[1m 58.03%[0m |
| [0m[1mmPrecision [0m [0m[1m 52.36%[0m |
| [0m[1mmRecall [0m [0m[1m 70.02%[0m |
| [0m[1mKappa [0m [0m[1m 60.08%[0m |
| ────────────────── ────────── |
| Best mFscore 58.09% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0370 lr=1.18e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0374 lr=1.15e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0374 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 071 / 100 | Elapsed: 0:23:19[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0374 |
| Val Loss 0.5160 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 67.54%[0m |
| [92m[1mmIoU [0m [92m[1m 44.38%[0m |
| [92m[1mmFscore [0m [92m[1m 58.43%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 52.97%[0m |
| [0m[1mmRecall [0m [0m[1m 70.25%[0m |
| [0m[1mKappa [0m [0m[1m 60.35%[0m |
| ────────────────── ────────── |
| Best mFscore 58.09% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 58.43% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0369 lr=1.12e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0370 lr=1.09e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0370 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 072 / 100 | Elapsed: 0:23:39[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0370 |
| Val Loss 0.5308 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 68.26%[0m |
| [92m[1mmIoU [0m [92m[1m 44.40%[0m |
| [92m[1mmFscore [0m [92m[1m 58.45%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 52.77%[0m |
| [0m[1mmRecall [0m [0m[1m 70.71%[0m |
| [0m[1mKappa [0m [0m[1m 61.08%[0m |
| ────────────────── ────────── |
| Best mFscore 58.43% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 58.45% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0363 lr=1.05e-05 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0364 lr=1.02e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0364 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 073 / 100 | Elapsed: 0:23:59[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0364 |
| Val Loss 0.5209 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 68.05%[0m |
| [92m[1mmIoU [0m [92m[1m 44.36%[0m |
| [92m[1mmFscore [0m [92m[1m 58.42%[0m |
| [0m[1mmPrecision [0m [0m[1m 52.67%[0m |
| [0m[1mmRecall [0m [0m[1m 70.70%[0m |
| [0m[1mKappa [0m [0m[1m 60.86%[0m |
| ────────────────── ────────── |
| Best mFscore 58.45% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0359 lr=9.87e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0359 lr=9.59e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0359 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 074 / 100 | Elapsed: 0:24:18[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0359 |
| Val Loss 0.5144 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 67.32%[0m |
| [92m[1mmIoU [0m [92m[1m 44.44%[0m |
| [92m[1mmFscore [0m [92m[1m 58.46%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 52.85%[0m |
| [0m[1mmRecall [0m [0m[1m 70.71%[0m |
| [0m[1mKappa [0m [0m[1m 60.14%[0m |
| ────────────────── ────────── |
| Best mFscore 58.45% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 58.46% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0345 lr=9.25e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0353 lr=8.98e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0353 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 075 / 100 | Elapsed: 0:24:38[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0353 |
| Val Loss 0.5399 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 67.11%[0m |
| [92m[1mmIoU [0m [92m[1m 44.18%[0m |
| [92m[1mmFscore [0m [92m[1m 58.18%[0m |
| [0m[1mmPrecision [0m [0m[1m 52.93%[0m |
| [0m[1mmRecall [0m [0m[1m 69.87%[0m |
| [0m[1mKappa [0m [0m[1m 59.91%[0m |
| ────────────────── ────────── |
| Best mFscore 58.46% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0354 lr=8.65e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0351 lr=8.38e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0351 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 076 / 100 | Elapsed: 0:24:58[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0351 |
| Val Loss 0.5146 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 67.80%[0m |
| [92m[1mmIoU [0m [92m[1m 44.29%[0m |
| [92m[1mmFscore [0m [92m[1m 58.38%[0m |
| [0m[1mmPrecision [0m [0m[1m 52.74%[0m |
| [0m[1mmRecall [0m [0m[1m 70.33%[0m |
| [0m[1mKappa [0m [0m[1m 60.61%[0m |
| ────────────────── ────────── |
| Best mFscore 58.46% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0339 lr=8.07e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0344 lr=7.81e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0344 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 077 / 100 | Elapsed: 0:25:17[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0344 |
| Val Loss 0.5492 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 68.73%[0m |
| [92m[1mmIoU [0m [92m[1m 44.89%[0m |
| [92m[1mmFscore [0m [92m[1m 59.04%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 53.58%[0m |
| [0m[1mmRecall [0m [0m[1m 70.10%[0m |
| [0m[1mKappa [0m [0m[1m 61.50%[0m |
| ────────────────── ────────── |
| Best mFscore 58.46% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 59.04% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0337 lr=7.51e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0340 lr=7.26e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0340 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 078 / 100 | Elapsed: 0:25:37[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0340 |
| Val Loss 0.5515 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 68.12%[0m |
| [92m[1mmIoU [0m [92m[1m 44.46%[0m |
| [92m[1mmFscore [0m [92m[1m 58.64%[0m |
| [0m[1mmPrecision [0m [0m[1m 53.03%[0m |
| [0m[1mmRecall [0m [0m[1m 70.07%[0m |
| [0m[1mKappa [0m [0m[1m 60.88%[0m |
| ────────────────── ────────── |
| Best mFscore 59.04% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0331 lr=6.97e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0336 lr=6.72e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0336 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 079 / 100 | Elapsed: 0:25:56[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0336 |
| Val Loss 0.5536 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 68.57%[0m |
| [92m[1mmIoU [0m [92m[1m 45.25%[0m |
| [92m[1mmFscore [0m [92m[1m 59.36%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 54.20%[0m |
| [0m[1mmRecall [0m [0m[1m 70.29%[0m |
| [0m[1mKappa [0m [0m[1m 61.38%[0m |
| ────────────────── ────────── |
| Best mFscore 59.04% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 59.36% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0335 lr=6.44e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0333 lr=6.21e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0333 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 080 / 100 | Elapsed: 0:26:16[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0333 |
| Val Loss 0.5374 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.45%[0m |
| [92m[1mmIoU [0m [92m[1m 45.20%[0m |
| [92m[1mmFscore [0m [92m[1m 59.26%[0m |
| [0m[1mmPrecision [0m [0m[1m 54.04%[0m |
| [0m[1mmRecall [0m [0m[1m 69.84%[0m |
| [0m[1mKappa [0m [0m[1m 62.23%[0m |
| ────────────────── ────────── |
| Best mFscore 59.36% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0317 lr=5.94e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0326 lr=5.72e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0326 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 081 / 100 | Elapsed: 0:26:36[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0326 |
| Val Loss 0.5388 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.04%[0m |
| [92m[1mmIoU [0m [92m[1m 45.27%[0m |
| [92m[1mmFscore [0m [92m[1m 59.42%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 53.94%[0m |
| [0m[1mmRecall [0m [0m[1m 70.20%[0m |
| [0m[1mKappa [0m [0m[1m 61.82%[0m |
| ────────────────── ────────── |
| Best mFscore 59.36% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 59.42% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0327 lr=5.46e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0325 lr=5.25e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0325 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 082 / 100 | Elapsed: 0:26:56[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0325 |
| Val Loss 0.5651 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 68.96%[0m |
| [92m[1mmIoU [0m [92m[1m 45.00%[0m |
| [92m[1mmFscore [0m [92m[1m 59.09%[0m |
| [0m[1mmPrecision [0m [0m[1m 53.77%[0m |
| [0m[1mmRecall [0m [0m[1m 69.95%[0m |
| [0m[1mKappa [0m [0m[1m 61.76%[0m |
| ────────────────── ────────── |
| Best mFscore 59.42% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0318 lr=5.01e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0322 lr=4.80e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0322 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 083 / 100 | Elapsed: 0:27:15[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0322 |
| Val Loss 0.5429 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.63%[0m |
| [92m[1mmIoU [0m [92m[1m 45.78%[0m |
| [92m[1mmFscore [0m [92m[1m 59.90%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 54.80%[0m |
| [0m[1mmRecall [0m [0m[1m 69.89%[0m |
| [0m[1mKappa [0m [0m[1m 62.41%[0m |
| ────────────────── ────────── |
| Best mFscore 59.42% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 59.90% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0313 lr=4.57e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0319 lr=4.38e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0319 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 084 / 100 | Elapsed: 0:27:35[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0319 |
| Val Loss 0.5475 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.25%[0m |
| [92m[1mmIoU [0m [92m[1m 45.34%[0m |
| [92m[1mmFscore [0m [92m[1m 59.51%[0m |
| [0m[1mmPrecision [0m [0m[1m 54.32%[0m |
| [0m[1mmRecall [0m [0m[1m 69.90%[0m |
| [0m[1mKappa [0m [0m[1m 62.02%[0m |
| ────────────────── ────────── |
| Best mFscore 59.90% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0314 lr=4.16e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0318 lr=3.98e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0318 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 085 / 100 | Elapsed: 0:27:54[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0318 |
| Val Loss 0.5547 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 68.58%[0m |
| [92m[1mmIoU [0m [92m[1m 45.12%[0m |
| [92m[1mmFscore [0m [92m[1m 59.23%[0m |
| [0m[1mmPrecision [0m [0m[1m 53.96%[0m |
| [0m[1mmRecall [0m [0m[1m 69.95%[0m |
| [0m[1mKappa [0m [0m[1m 61.38%[0m |
| ────────────────── ────────── |
| Best mFscore 59.90% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0317 lr=3.77e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0317 lr=3.60e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0317 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 086 / 100 | Elapsed: 0:28:14[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0317 |
| Val Loss 0.5713 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.47%[0m |
| [92m[1mmIoU [0m [92m[1m 44.97%[0m |
| [92m[1mmFscore [0m [92m[1m 59.10%[0m |
| [0m[1mmPrecision [0m [0m[1m 53.88%[0m |
| [0m[1mmRecall [0m [0m[1m 69.37%[0m |
| [0m[1mKappa [0m [0m[1m 62.25%[0m |
| ────────────────── ────────── |
| Best mFscore 59.90% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0312 lr=3.41e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0311 lr=3.25e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0311 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 087 / 100 | Elapsed: 0:28:33[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0311 |
| Val Loss 0.5680 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.83%[0m |
| [92m[1mmIoU [0m [92m[1m 45.37%[0m |
| [92m[1mmFscore [0m [92m[1m 59.47%[0m |
| [0m[1mmPrecision [0m [0m[1m 54.06%[0m |
| [0m[1mmRecall [0m [0m[1m 69.78%[0m |
| [0m[1mKappa [0m [0m[1m 62.60%[0m |
| ────────────────── ────────── |
| Best mFscore 59.90% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0312 lr=3.07e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0311 lr=2.92e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0311 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 088 / 100 | Elapsed: 0:28:52[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0311 |
| Val Loss 0.5569 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.67%[0m |
| [92m[1mmIoU [0m [92m[1m 45.42%[0m |
| [92m[1mmFscore [0m [92m[1m 59.52%[0m |
| [0m[1mmPrecision [0m [0m[1m 54.53%[0m |
| [0m[1mmRecall [0m [0m[1m 69.54%[0m |
| [0m[1mKappa [0m [0m[1m 62.44%[0m |
| ────────────────── ────────── |
| Best mFscore 59.90% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0311 lr=2.75e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0308 lr=2.62e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0308 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 089 / 100 | Elapsed: 0:29:12[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0308 |
| Val Loss 0.5527 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 70.24%[0m |
| [92m[1mmIoU [0m [92m[1m 45.52%[0m |
| [92m[1mmFscore [0m [92m[1m 59.65%[0m |
| [0m[1mmPrecision [0m [0m[1m 54.40%[0m |
| [0m[1mmRecall [0m [0m[1m 69.70%[0m |
| [0m[1mKappa [0m [0m[1m 63.03%[0m |
| ────────────────── ────────── |
| Best mFscore 59.90% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0307 lr=2.46e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0308 lr=2.34e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0308 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 090 / 100 | Elapsed: 0:29:31[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0308 |
| Val Loss 0.5636 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.53%[0m |
| [92m[1mmIoU [0m [92m[1m 45.34%[0m |
| [92m[1mmFscore [0m [92m[1m 59.35%[0m |
| [0m[1mmPrecision [0m [0m[1m 54.08%[0m |
| [0m[1mmRecall [0m [0m[1m 69.76%[0m |
| [0m[1mKappa [0m [0m[1m 62.32%[0m |
| ────────────────── ────────── |
| Best mFscore 59.90% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0305 lr=2.20e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0304 lr=2.09e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0304 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 091 / 100 | Elapsed: 0:29:50[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0304 |
| Val Loss 0.5756 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 70.03%[0m |
| [92m[1mmIoU [0m [92m[1m 45.73%[0m |
| [92m[1mmFscore [0m [92m[1m 59.86%[0m |
| [0m[1mmPrecision [0m [0m[1m 54.72%[0m |
| [0m[1mmRecall [0m [0m[1m 69.71%[0m |
| [0m[1mKappa [0m [0m[1m 62.83%[0m |
| ────────────────── ────────── |
| Best mFscore 59.90% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0306 lr=1.96e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0304 lr=1.86e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0304 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 092 / 100 | Elapsed: 0:30:10[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0304 |
| Val Loss 0.5743 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 70.04%[0m |
| [92m[1mmIoU [0m [92m[1m 45.79%[0m |
| [92m[1mmFscore [0m [92m[1m 59.89%[0m |
| [0m[1mmPrecision [0m [0m[1m 54.72%[0m |
| [0m[1mmRecall [0m [0m[1m 69.87%[0m |
| [0m[1mKappa [0m [0m[1m 62.83%[0m |
| ────────────────── ────────── |
| Best mFscore 59.90% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0303 lr=1.75e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0301 lr=1.66e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0301 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 093 / 100 | Elapsed: 0:30:29[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0301 |
| Val Loss 0.5744 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 70.26%[0m |
| [92m[1mmIoU [0m [92m[1m 45.98%[0m |
| [92m[1mmFscore [0m [92m[1m 60.14%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 55.18%[0m |
| [0m[1mmRecall [0m [0m[1m 69.73%[0m |
| [0m[1mKappa [0m [0m[1m 63.06%[0m |
| ────────────────── ────────── |
| Best mFscore 59.90% |
| Val Time 3.8s |
|
|
| [92m[1m★ New best mFscore: 60.14% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0302 lr=1.56e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0300 lr=1.49e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0300 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 094 / 100 | Elapsed: 0:30:49[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0300 |
| Val Loss 0.5749 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.36%[0m |
| [92m[1mmIoU [0m [92m[1m 45.25%[0m |
| [92m[1mmFscore [0m [92m[1m 59.42%[0m |
| [0m[1mmPrecision [0m [0m[1m 54.14%[0m |
| [0m[1mmRecall [0m [0m[1m 69.71%[0m |
| [0m[1mKappa [0m [0m[1m 62.17%[0m |
| ────────────────── ────────── |
| Best mFscore 60.14% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0303 lr=1.40e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0304 lr=1.34e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0304 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 095 / 100 | Elapsed: 0:31:08[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0304 |
| Val Loss 0.5788 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.38%[0m |
| [92m[1mmIoU [0m [92m[1m 45.26%[0m |
| [92m[1mmFscore [0m [92m[1m 59.44%[0m |
| [0m[1mmPrecision [0m [0m[1m 54.14%[0m |
| [0m[1mmRecall [0m [0m[1m 69.68%[0m |
| [0m[1mKappa [0m [0m[1m 62.17%[0m |
| ────────────────── ────────── |
| Best mFscore 60.14% |
| Val Time 3.8s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0297 lr=1.27e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0299 lr=1.22e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0299 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 096 / 100 | Elapsed: 0:31:27[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0299 |
| Val Loss 0.5660 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.80%[0m |
| [92m[1mmIoU [0m [92m[1m 45.25%[0m |
| [92m[1mmFscore [0m [92m[1m 59.48%[0m |
| [0m[1mmPrecision [0m [0m[1m 54.20%[0m |
| [0m[1mmRecall [0m [0m[1m 69.55%[0m |
| [0m[1mKappa [0m [0m[1m 62.57%[0m |
| ────────────────── ────────── |
| Best mFscore 60.14% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0296 lr=1.16e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0299 lr=1.12e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0299 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 097 / 100 | Elapsed: 0:31:47[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0299 |
| Val Loss 0.5600 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.81%[0m |
| [92m[1mmIoU [0m [92m[1m 45.15%[0m |
| [92m[1mmFscore [0m [92m[1m 59.29%[0m |
| [0m[1mmPrecision [0m [0m[1m 53.95%[0m |
| [0m[1mmRecall [0m [0m[1m 69.66%[0m |
| [0m[1mKappa [0m [0m[1m 62.60%[0m |
| ────────────────── ────────── |
| Best mFscore 60.14% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0295 lr=1.08e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0296 lr=1.05e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0296 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 098 / 100 | Elapsed: 0:32:06[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0296 |
| Val Loss 0.5640 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.92%[0m |
| [92m[1mmIoU [0m [92m[1m 45.49%[0m |
| [92m[1mmFscore [0m [92m[1m 59.64%[0m |
| [0m[1mmPrecision [0m [0m[1m 54.51%[0m |
| [0m[1mmRecall [0m [0m[1m 69.54%[0m |
| [0m[1mKappa [0m [0m[1m 62.70%[0m |
| ────────────────── ────────── |
| Best mFscore 60.14% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0298 lr=1.03e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0295 lr=1.01e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0295 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 099 / 100 | Elapsed: 0:32:25[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0295 |
| Val Loss 0.5694 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.92%[0m |
| [92m[1mmIoU [0m [92m[1m 45.90%[0m |
| [92m[1mmFscore [0m [92m[1m 60.06%[0m |
| [0m[1mmPrecision [0m [0m[1m 54.93%[0m |
| [0m[1mmRecall [0m [0m[1m 69.88%[0m |
| [0m[1mKappa [0m [0m[1m 62.71%[0m |
| ────────────────── ────────── |
| Best mFscore 60.14% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [█████████████████████░░░░░░░░░░░░░░░░░░░] 54.3% iter 50/92 loss=0.0295 lr=1.00e-06 eta=0:00:07 |
| [████████████████████████████████████████] 100.0% iter 92/92 loss=0.0295 lr=1.00e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0295 time=0:00:15[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 100 / 100 | Elapsed: 0:32:45[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0295 |
| Val Loss 0.5841 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.61%[0m |
| [92m[1mmIoU [0m [92m[1m 45.33%[0m |
| [92m[1mmFscore [0m [92m[1m 59.46%[0m |
| [0m[1mmPrecision [0m [0m[1m 54.28%[0m |
| [0m[1mmRecall [0m [0m[1m 69.46%[0m |
| [0m[1mKappa [0m [0m[1m 62.38%[0m |
| ────────────────── ────────── |
| Best mFscore 60.14% |
| Val Time 4.0s |
|
|
| [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 69.96%[0m |
| [92m[1mmIoU [0m [92m[1m 45.54%[0m |
| [92m[1mmFscore [0m [92m[1m 59.18%[0m |
| [0m[1mmPrecision [0m [0m[1m 54.51%[0m |
| [0m[1mmRecall [0m [0m[1m 68.69%[0m |
| [0m[1mKappa [0m [0m[1m 62.79%[0m |
| ────────────────── ────────── |
| Test Loss 0.4496 |
| Total Time 0:32:52 |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Per-Class IoU (Test)[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Class IoU Bar |
| ────────────────────────────── ─────── ──────────────────── |
| [92mBackground 51.60% ██████████[0m |
| [92mMeadow 57.47% ███████████[0m |
| [92mSoft winter wheat 71.64% ██████████████[0m |
| [92mCorn 75.75% ███████████████[0m |
| [92mWinter barley 57.70% ███████████[0m |
| [92mWinter rapeseed 77.14% ███████████████[0m |
| [92mSpring barley 32.87% ██████[0m |
| [92mSunflower 64.54% ████████████[0m |
| [92mGrapevine 37.52% ███████[0m |
| [92mBeet 78.01% ███████████████[0m |
| [92mWinter triticale 24.30% ████[0m |
| [92mWinter durum wheat 49.19% █████████[0m |
| [92mFruits vegetables flowers 20.97% ████[0m |
| [92mPotatoes 34.93% ██████[0m |
| [92mLeguminous fodder 21.02% ████[0m |
| [92mSoybeans 63.35% ████████████[0m |
| [92mOrchard 26.05% █████[0m |
| [93mMixed cereal 13.20% ██[0m |
| [93mSorghum 8.04% █[0m |
|
|
| [92m[1mAll results saved to: ./work_dirs/fold3_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 |
|
|
