| /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 4 | 2026-04-17 08:38:19[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/fold4_small |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Building Datasets[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| PASTIS fold=4 split=train: 1455 patches (augment=True) |
| PASTIS fold=4 split=val: 496 patches (augment=False) |
| PASTIS fold=4 split=test: 482 patches (augment=False) |
|
|
| Train: 1455 Val: 496 Test: 482 |
| Train batches: 90 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=4, sampled 300 patches): |
| Class Count Weight |
| ────────────────────────────── ────────── ──────── |
| Background 2203811 0.011 |
| Meadow 837973 0.030 |
| Soft winter wheat 195576 0.128 |
| Corn 245541 0.102 |
| Winter barley 83456 0.300 |
| Winter rapeseed 64400 0.389 |
| Spring barley 10440 2.400 |
| Sunflower 69786 0.359 |
| Grapevine 219712 0.114 |
| Beet 3039 8.246 |
| Winter triticale 39131 0.640 |
| Winter durum wheat 92000 0.272 |
| Fruits vegetables flowers 62314 0.402 |
| Potatoes 9508 2.636 |
| Leguminous fodder 102935 0.243 |
| Soybeans 64896 0.386 |
| Orchard 66819 0.375 |
| Mixed cereal 22343 1.122 |
| Sorghum 29722 0.843 |
|
|
| [1m[96m══════════════════════════════════════════════════════════════════════[0m |
| [1m[96m Training | 100 epochs | model=small (~14M) | fold=4[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> |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.8021 lr=5.90e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.7522 lr=9.82e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.7522 time=0:00:19[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 001 / 100 | Elapsed: 0:00:27[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.7522 |
| Val Loss 0.6439 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 2.42%[0m |
| [92m[1mmIoU [0m [92m[1m 0.93%[0m |
| [92m[1mmFscore [0m [92m[1m 1.80%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 3.62%[0m |
| [0m[1mmRecall [0m [0m[1m 13.24%[0m |
| [0m[1mKappa [0m [0m[1m 1.51%[0m |
| ────────────────── ────────── |
| Best mFscore 0.00% |
| Val Time 6.8s |
|
|
| [92m[1m★ New best mFscore: 1.80% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.5460 lr=1.47e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.5251 lr=1.86e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.5251 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 002 / 100 | Elapsed: 0:00:47[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.5251 |
| Val Loss 0.5058 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.32%[0m |
| [92m[1mmIoU [0m [92m[1m 7.37%[0m |
| [92m[1mmFscore [0m [92m[1m 12.81%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 13.50%[0m |
| [0m[1mmRecall [0m [0m[1m 30.47%[0m |
| [0m[1mKappa [0m [0m[1m 8.66%[0m |
| ────────────────── ────────── |
| Best mFscore 1.80% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 12.81% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.4270 lr=2.35e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.4242 lr=2.75e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.4242 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 003 / 100 | Elapsed: 0:01:06[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.4242 |
| Val Loss 0.4464 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 18.69%[0m |
| [92m[1mmIoU [0m [92m[1m 12.03%[0m |
| [92m[1mmFscore [0m [92m[1m 20.11%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 19.32%[0m |
| [0m[1mmRecall [0m [0m[1m 41.57%[0m |
| [0m[1mKappa [0m [0m[1m 15.90%[0m |
| ────────────────── ────────── |
| Best mFscore 12.81% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 20.11% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.3564 lr=3.24e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.3728 lr=3.63e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.3728 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 004 / 100 | Elapsed: 0:01:26[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3728 |
| Val Loss 0.4414 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 25.32%[0m |
| [92m[1mmIoU [0m [92m[1m 14.72%[0m |
| [92m[1mmFscore [0m [92m[1m 23.07%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 22.80%[0m |
| [0m[1mmRecall [0m [0m[1m 40.04%[0m |
| [0m[1mKappa [0m [0m[1m 21.39%[0m |
| ────────────────── ────────── |
| Best mFscore 20.11% |
| Val Time 4.2s |
|
|
| [92m[1m★ New best mFscore: 23.07% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.3327 lr=4.12e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.3360 lr=4.51e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.3360 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 005 / 100 | Elapsed: 0:01:46[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3360 |
| Val Loss 0.4218 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 19.56%[0m |
| [92m[1mmIoU [0m [92m[1m 15.36%[0m |
| [92m[1mmFscore [0m [92m[1m 24.88%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 24.98%[0m |
| [0m[1mmRecall [0m [0m[1m 45.12%[0m |
| [0m[1mKappa [0m [0m[1m 17.11%[0m |
| ────────────────── ────────── |
| Best mFscore 23.07% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 24.88% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.3191 lr=5.00e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.3278 lr=5.00e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.3278 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 006 / 100 | Elapsed: 0:02:05[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3278 |
| Val Loss 0.3942 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 25.20%[0m |
| [92m[1mmIoU [0m [92m[1m 16.79%[0m |
| [92m[1mmFscore [0m [92m[1m 26.28%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 23.10%[0m |
| [0m[1mmRecall [0m [0m[1m 47.25%[0m |
| [0m[1mKappa [0m [0m[1m 22.02%[0m |
| ────────────────── ────────── |
| Best mFscore 24.88% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 26.28% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.2833 lr=5.00e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.3034 lr=5.00e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.3034 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 007 / 100 | Elapsed: 0:02:25[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3034 |
| Val Loss 0.3641 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 28.49%[0m |
| [92m[1mmIoU [0m [92m[1m 20.11%[0m |
| [92m[1mmFscore [0m [92m[1m 30.27%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 27.30%[0m |
| [0m[1mmRecall [0m [0m[1m 50.22%[0m |
| [0m[1mKappa [0m [0m[1m 24.59%[0m |
| ────────────────── ────────── |
| Best mFscore 26.28% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 30.27% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.2740 lr=4.99e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.2655 lr=4.99e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2655 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 008 / 100 | Elapsed: 0:02:45[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2655 |
| Val Loss 0.3456 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 33.44%[0m |
| [92m[1mmIoU [0m [92m[1m 21.78%[0m |
| [92m[1mmFscore [0m [92m[1m 32.54%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 35.17%[0m |
| [0m[1mmRecall [0m [0m[1m 53.36%[0m |
| [0m[1mKappa [0m [0m[1m 28.82%[0m |
| ────────────────── ────────── |
| Best mFscore 30.27% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 32.54% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.2439 lr=4.99e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.2511 lr=4.98e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2511 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 009 / 100 | Elapsed: 0:03:05[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2511 |
| Val Loss 0.3428 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 32.33%[0m |
| [92m[1mmIoU [0m [92m[1m 22.82%[0m |
| [92m[1mmFscore [0m [92m[1m 33.62%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 34.15%[0m |
| [0m[1mmRecall [0m [0m[1m 55.18%[0m |
| [0m[1mKappa [0m [0m[1m 27.81%[0m |
| ────────────────── ────────── |
| Best mFscore 32.54% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 33.62% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.2244 lr=4.98e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.2337 lr=4.97e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2337 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 0.2337 |
| Val Loss 0.3340 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 32.02%[0m |
| [92m[1mmIoU [0m [92m[1m 23.65%[0m |
| [92m[1mmFscore [0m [92m[1m 34.45%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 34.22%[0m |
| [0m[1mmRecall [0m [0m[1m 56.29%[0m |
| [0m[1mKappa [0m [0m[1m 28.16%[0m |
| ────────────────── ────────── |
| Best mFscore 33.62% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 34.45% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.2171 lr=4.97e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.2201 lr=4.96e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2201 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 011 / 100 | Elapsed: 0:03:44[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2201 |
| Val Loss 0.3281 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 32.68%[0m |
| [92m[1mmIoU [0m [92m[1m 23.73%[0m |
| [92m[1mmFscore [0m [92m[1m 34.59%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 36.29%[0m |
| [0m[1mmRecall [0m [0m[1m 55.17%[0m |
| [0m[1mKappa [0m [0m[1m 28.26%[0m |
| ────────────────── ────────── |
| Best mFscore 34.45% |
| Val Time 4.2s |
|
|
| [92m[1m★ New best mFscore: 34.59% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.2107 lr=4.95e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.2123 lr=4.94e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.2123 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 012 / 100 | Elapsed: 0:04:04[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2123 |
| Val Loss 0.3141 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 37.03%[0m |
| [92m[1mmIoU [0m [92m[1m 27.02%[0m |
| [92m[1mmFscore [0m [92m[1m 38.63%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 37.16%[0m |
| [0m[1mmRecall [0m [0m[1m 59.22%[0m |
| [0m[1mKappa [0m [0m[1m 32.06%[0m |
| ────────────────── ────────── |
| Best mFscore 34.59% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 38.63% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1961 lr=4.93e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1974 lr=4.93e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1974 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 013 / 100 | Elapsed: 0:04:24[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1974 |
| Val Loss 0.3089 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 41.43%[0m |
| [92m[1mmIoU [0m [92m[1m 29.17%[0m |
| [92m[1mmFscore [0m [92m[1m 41.42%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 39.79%[0m |
| [0m[1mmRecall [0m [0m[1m 60.79%[0m |
| [0m[1mKappa [0m [0m[1m 35.29%[0m |
| ────────────────── ────────── |
| Best mFscore 38.63% |
| Val Time 3.9s |
|
|
| [92m[1m★ New best mFscore: 41.42% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1856 lr=4.91e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1833 lr=4.90e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1833 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 014 / 100 | Elapsed: 0:04:43[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1833 |
| Val Loss 0.3326 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 40.98%[0m |
| [92m[1mmIoU [0m [92m[1m 27.56%[0m |
| [92m[1mmFscore [0m [92m[1m 39.94%[0m |
| [0m[1mmPrecision [0m [0m[1m 37.75%[0m |
| [0m[1mmRecall [0m [0m[1m 59.02%[0m |
| [0m[1mKappa [0m [0m[1m 35.62%[0m |
| ────────────────── ────────── |
| Best mFscore 41.42% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1842 lr=4.89e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1916 lr=4.88e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1916 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 015 / 100 | Elapsed: 0:05:02[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1916 |
| Val Loss 0.3361 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 38.80%[0m |
| [92m[1mmIoU [0m [92m[1m 27.72%[0m |
| [92m[1mmFscore [0m [92m[1m 39.65%[0m |
| [0m[1mmPrecision [0m [0m[1m 37.80%[0m |
| [0m[1mmRecall [0m [0m[1m 59.43%[0m |
| [0m[1mKappa [0m [0m[1m 33.03%[0m |
| ────────────────── ────────── |
| Best mFscore 41.42% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1770 lr=4.87e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1797 lr=4.85e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1797 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 016 / 100 | Elapsed: 0:05:22[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1797 |
| Val Loss 0.3214 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 42.73%[0m |
| [92m[1mmIoU [0m [92m[1m 29.65%[0m |
| [92m[1mmFscore [0m [92m[1m 42.05%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 40.02%[0m |
| [0m[1mmRecall [0m [0m[1m 59.62%[0m |
| [0m[1mKappa [0m [0m[1m 36.82%[0m |
| ────────────────── ────────── |
| Best mFscore 41.42% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 42.05% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1651 lr=4.84e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1669 lr=4.82e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1669 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 017 / 100 | Elapsed: 0:05:41[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1669 |
| Val Loss 0.3088 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 49.31%[0m |
| [92m[1mmIoU [0m [92m[1m 32.15%[0m |
| [92m[1mmFscore [0m [92m[1m 45.26%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 41.34%[0m |
| [0m[1mmRecall [0m [0m[1m 65.59%[0m |
| [0m[1mKappa [0m [0m[1m 42.88%[0m |
| ────────────────── ────────── |
| Best mFscore 42.05% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 45.26% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1629 lr=4.81e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1618 lr=4.79e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1618 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 018 / 100 | Elapsed: 0:06:01[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1618 |
| Val Loss 0.3110 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 45.61%[0m |
| [92m[1mmIoU [0m [92m[1m 31.59%[0m |
| [92m[1mmFscore [0m [92m[1m 44.07%[0m |
| [0m[1mmPrecision [0m [0m[1m 41.60%[0m |
| [0m[1mmRecall [0m [0m[1m 63.74%[0m |
| [0m[1mKappa [0m [0m[1m 39.60%[0m |
| ────────────────── ────────── |
| Best mFscore 45.26% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1496 lr=4.77e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1518 lr=4.76e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1518 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 019 / 100 | Elapsed: 0:06:20[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1518 |
| Val Loss 0.3115 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 48.53%[0m |
| [92m[1mmIoU [0m [92m[1m 31.79%[0m |
| [92m[1mmFscore [0m [92m[1m 44.47%[0m |
| [0m[1mmPrecision [0m [0m[1m 43.13%[0m |
| [0m[1mmRecall [0m [0m[1m 62.25%[0m |
| [0m[1mKappa [0m [0m[1m 42.03%[0m |
| ────────────────── ────────── |
| Best mFscore 45.26% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1435 lr=4.74e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1480 lr=4.72e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1480 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 020 / 100 | Elapsed: 0:06:39[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1480 |
| Val Loss 0.2999 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 46.03%[0m |
| [92m[1mmIoU [0m [92m[1m 29.97%[0m |
| [92m[1mmFscore [0m [92m[1m 42.41%[0m |
| [0m[1mmPrecision [0m [0m[1m 38.82%[0m |
| [0m[1mmRecall [0m [0m[1m 63.43%[0m |
| [0m[1mKappa [0m [0m[1m 39.75%[0m |
| ────────────────── ────────── |
| Best mFscore 45.26% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1422 lr=4.70e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1424 lr=4.68e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1424 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 021 / 100 | Elapsed: 0:06:58[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1424 |
| Val Loss 0.3056 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 49.69%[0m |
| [92m[1mmIoU [0m [92m[1m 32.56%[0m |
| [92m[1mmFscore [0m [92m[1m 45.52%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 42.11%[0m |
| [0m[1mmRecall [0m [0m[1m 63.65%[0m |
| [0m[1mKappa [0m [0m[1m 43.19%[0m |
| ────────────────── ────────── |
| Best mFscore 45.26% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 45.52% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1417 lr=4.66e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1394 lr=4.64e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1394 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 022 / 100 | Elapsed: 0:07:18[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1394 |
| Val Loss 0.3104 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 48.14%[0m |
| [92m[1mmIoU [0m [92m[1m 32.69%[0m |
| [92m[1mmFscore [0m [92m[1m 45.48%[0m |
| [0m[1mmPrecision [0m [0m[1m 41.56%[0m |
| [0m[1mmRecall [0m [0m[1m 64.85%[0m |
| [0m[1mKappa [0m [0m[1m 41.74%[0m |
| ────────────────── ────────── |
| Best mFscore 45.52% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1294 lr=4.62e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1300 lr=4.60e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1300 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 023 / 100 | Elapsed: 0:07:37[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1300 |
| Val Loss 0.3224 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 50.52%[0m |
| [92m[1mmIoU [0m [92m[1m 33.92%[0m |
| [92m[1mmFscore [0m [92m[1m 46.99%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 44.36%[0m |
| [0m[1mmRecall [0m [0m[1m 64.78%[0m |
| [0m[1mKappa [0m [0m[1m 44.08%[0m |
| ────────────────── ────────── |
| Best mFscore 45.52% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 46.99% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1222 lr=4.57e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1269 lr=4.55e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1269 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 024 / 100 | Elapsed: 0:07:57[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1269 |
| Val Loss 0.3541 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 50.41%[0m |
| [92m[1mmIoU [0m [92m[1m 34.25%[0m |
| [92m[1mmFscore [0m [92m[1m 47.05%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 45.39%[0m |
| [0m[1mmRecall [0m [0m[1m 62.06%[0m |
| [0m[1mKappa [0m [0m[1m 43.61%[0m |
| ────────────────── ────────── |
| Best mFscore 46.99% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 47.05% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1292 lr=4.53e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1267 lr=4.51e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1267 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 025 / 100 | Elapsed: 0:08:17[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1267 |
| Val Loss 0.3154 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 50.85%[0m |
| [92m[1mmIoU [0m [92m[1m 33.42%[0m |
| [92m[1mmFscore [0m [92m[1m 46.44%[0m |
| [0m[1mmPrecision [0m [0m[1m 43.02%[0m |
| [0m[1mmRecall [0m [0m[1m 65.88%[0m |
| [0m[1mKappa [0m [0m[1m 44.21%[0m |
| ────────────────── ────────── |
| Best mFscore 47.05% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1183 lr=4.48e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1194 lr=4.45e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1194 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 026 / 100 | Elapsed: 0:08:36[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1194 |
| Val Loss 0.3345 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 51.72%[0m |
| [92m[1mmIoU [0m [92m[1m 35.32%[0m |
| [92m[1mmFscore [0m [92m[1m 48.28%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 44.46%[0m |
| [0m[1mmRecall [0m [0m[1m 65.34%[0m |
| [0m[1mKappa [0m [0m[1m 44.90%[0m |
| ────────────────── ────────── |
| Best mFscore 47.05% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 48.28% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1156 lr=4.43e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1180 lr=4.40e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1180 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 027 / 100 | Elapsed: 0:08:55[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1180 |
| Val Loss 0.3366 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 53.55%[0m |
| [92m[1mmIoU [0m [92m[1m 33.85%[0m |
| [92m[1mmFscore [0m [92m[1m 46.71%[0m |
| [0m[1mmPrecision [0m [0m[1m 42.02%[0m |
| [0m[1mmRecall [0m [0m[1m 66.03%[0m |
| [0m[1mKappa [0m [0m[1m 46.69%[0m |
| ────────────────── ────────── |
| Best mFscore 48.28% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1126 lr=4.37e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1174 lr=4.35e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1174 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 028 / 100 | Elapsed: 0:09:14[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1174 |
| Val Loss 0.3347 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 50.29%[0m |
| [92m[1mmIoU [0m [92m[1m 31.74%[0m |
| [92m[1mmFscore [0m [92m[1m 44.67%[0m |
| [0m[1mmPrecision [0m [0m[1m 41.16%[0m |
| [0m[1mmRecall [0m [0m[1m 63.62%[0m |
| [0m[1mKappa [0m [0m[1m 43.64%[0m |
| ────────────────── ────────── |
| Best mFscore 48.28% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1327 lr=4.32e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1269 lr=4.29e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1269 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 029 / 100 | Elapsed: 0:09:34[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1269 |
| Val Loss 0.3398 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 53.61%[0m |
| [92m[1mmIoU [0m [92m[1m 35.30%[0m |
| [92m[1mmFscore [0m [92m[1m 48.43%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 45.04%[0m |
| [0m[1mmRecall [0m [0m[1m 65.20%[0m |
| [0m[1mKappa [0m [0m[1m 46.76%[0m |
| ────────────────── ────────── |
| Best mFscore 48.28% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 48.43% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1090 lr=4.26e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1103 lr=4.23e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1103 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 030 / 100 | Elapsed: 0:09:53[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1103 |
| Val Loss 0.3339 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 54.02%[0m |
| [92m[1mmIoU [0m [92m[1m 34.85%[0m |
| [92m[1mmFscore [0m [92m[1m 47.97%[0m |
| [0m[1mmPrecision [0m [0m[1m 43.16%[0m |
| [0m[1mmRecall [0m [0m[1m 66.35%[0m |
| [0m[1mKappa [0m [0m[1m 47.21%[0m |
| ────────────────── ────────── |
| Best mFscore 48.43% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1043 lr=4.20e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.1054 lr=4.17e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.1054 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 031 / 100 | Elapsed: 0:10:12[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1054 |
| Val Loss 0.3292 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 54.13%[0m |
| [92m[1mmIoU [0m [92m[1m 36.19%[0m |
| [92m[1mmFscore [0m [92m[1m 49.11%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 46.37%[0m |
| [0m[1mmRecall [0m [0m[1m 65.57%[0m |
| [0m[1mKappa [0m [0m[1m 47.21%[0m |
| ────────────────── ────────── |
| Best mFscore 48.43% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 49.11% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0954 lr=4.14e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0994 lr=4.11e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0994 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 032 / 100 | Elapsed: 0:10:32[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0994 |
| Val Loss 0.3385 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 56.24%[0m |
| [92m[1mmIoU [0m [92m[1m 35.40%[0m |
| [92m[1mmFscore [0m [92m[1m 48.62%[0m |
| [0m[1mmPrecision [0m [0m[1m 44.42%[0m |
| [0m[1mmRecall [0m [0m[1m 65.23%[0m |
| [0m[1mKappa [0m [0m[1m 49.22%[0m |
| ────────────────── ────────── |
| Best mFscore 49.11% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.1007 lr=4.08e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0989 lr=4.05e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0989 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 033 / 100 | Elapsed: 0:10:51[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0989 |
| Val Loss 0.3512 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 54.29%[0m |
| [92m[1mmIoU [0m [92m[1m 36.59%[0m |
| [92m[1mmFscore [0m [92m[1m 49.35%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 45.14%[0m |
| [0m[1mmRecall [0m [0m[1m 66.23%[0m |
| [0m[1mKappa [0m [0m[1m 47.43%[0m |
| ────────────────── ────────── |
| Best mFscore 49.11% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 49.35% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0910 lr=4.01e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0915 lr=3.98e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0915 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 034 / 100 | Elapsed: 0:11:11[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0915 |
| Val Loss 0.3342 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 56.96%[0m |
| [92m[1mmIoU [0m [92m[1m 37.62%[0m |
| [92m[1mmFscore [0m [92m[1m 51.09%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 45.92%[0m |
| [0m[1mmRecall [0m [0m[1m 67.41%[0m |
| [0m[1mKappa [0m [0m[1m 49.88%[0m |
| ────────────────── ────────── |
| Best mFscore 49.35% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 51.09% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0861 lr=3.95e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0897 lr=3.92e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0897 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 035 / 100 | Elapsed: 0:11:30[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0897 |
| Val Loss 0.3469 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 57.54%[0m |
| [92m[1mmIoU [0m [92m[1m 37.21%[0m |
| [92m[1mmFscore [0m [92m[1m 50.85%[0m |
| [0m[1mmPrecision [0m [0m[1m 45.98%[0m |
| [0m[1mmRecall [0m [0m[1m 67.26%[0m |
| [0m[1mKappa [0m [0m[1m 50.65%[0m |
| ────────────────── ────────── |
| Best mFscore 51.09% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0876 lr=3.88e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0861 lr=3.85e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0861 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 036 / 100 | Elapsed: 0:11:50[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0861 |
| Val Loss 0.3384 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 57.89%[0m |
| [92m[1mmIoU [0m [92m[1m 37.35%[0m |
| [92m[1mmFscore [0m [92m[1m 50.73%[0m |
| [0m[1mmPrecision [0m [0m[1m 45.58%[0m |
| [0m[1mmRecall [0m [0m[1m 67.79%[0m |
| [0m[1mKappa [0m [0m[1m 50.95%[0m |
| ────────────────── ────────── |
| Best mFscore 51.09% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0800 lr=3.81e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0800 lr=3.78e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0800 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 037 / 100 | Elapsed: 0:12:09[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0800 |
| Val Loss 0.3676 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 59.92%[0m |
| [92m[1mmIoU [0m [92m[1m 38.69%[0m |
| [92m[1mmFscore [0m [92m[1m 52.24%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 46.98%[0m |
| [0m[1mmRecall [0m [0m[1m 68.36%[0m |
| [0m[1mKappa [0m [0m[1m 52.88%[0m |
| ────────────────── ────────── |
| Best mFscore 51.09% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 52.24% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0797 lr=3.74e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0795 lr=3.71e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0795 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 038 / 100 | Elapsed: 0:12:28[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0795 |
| Val Loss 0.3450 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 58.38%[0m |
| [92m[1mmIoU [0m [92m[1m 38.86%[0m |
| [92m[1mmFscore [0m [92m[1m 52.39%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 47.30%[0m |
| [0m[1mmRecall [0m [0m[1m 68.44%[0m |
| [0m[1mKappa [0m [0m[1m 51.40%[0m |
| ────────────────── ────────── |
| Best mFscore 52.24% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 52.39% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0755 lr=3.67e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0758 lr=3.63e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0758 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 039 / 100 | Elapsed: 0:12:48[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0758 |
| Val Loss 0.3579 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 60.99%[0m |
| [92m[1mmIoU [0m [92m[1m 38.46%[0m |
| [92m[1mmFscore [0m [92m[1m 51.82%[0m |
| [0m[1mmPrecision [0m [0m[1m 46.25%[0m |
| [0m[1mmRecall [0m [0m[1m 68.53%[0m |
| [0m[1mKappa [0m [0m[1m 53.93%[0m |
| ────────────────── ────────── |
| Best mFscore 52.39% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0750 lr=3.59e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0746 lr=3.56e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0746 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 040 / 100 | Elapsed: 0:13:08[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0746 |
| Val Loss 0.3746 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 60.45%[0m |
| [92m[1mmIoU [0m [92m[1m 39.35%[0m |
| [92m[1mmFscore [0m [92m[1m 52.95%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 47.47%[0m |
| [0m[1mmRecall [0m [0m[1m 68.22%[0m |
| [0m[1mKappa [0m [0m[1m 53.26%[0m |
| ────────────────── ────────── |
| Best mFscore 52.39% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 52.95% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0758 lr=3.52e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0770 lr=3.49e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0770 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 041 / 100 | Elapsed: 0:13:28[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0770 |
| Val Loss 0.3909 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 59.88%[0m |
| [92m[1mmIoU [0m [92m[1m 39.54%[0m |
| [92m[1mmFscore [0m [92m[1m 53.16%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 48.21%[0m |
| [0m[1mmRecall [0m [0m[1m 67.30%[0m |
| [0m[1mKappa [0m [0m[1m 52.73%[0m |
| ────────────────── ────────── |
| Best mFscore 52.95% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 53.16% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0731 lr=3.44e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0755 lr=3.41e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0755 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 042 / 100 | Elapsed: 0:13:47[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0755 |
| Val Loss 0.3838 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 61.54%[0m |
| [92m[1mmIoU [0m [92m[1m 39.85%[0m |
| [92m[1mmFscore [0m [92m[1m 53.79%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 48.49%[0m |
| [0m[1mmRecall [0m [0m[1m 68.02%[0m |
| [0m[1mKappa [0m [0m[1m 54.49%[0m |
| ────────────────── ────────── |
| Best mFscore 53.16% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 53.79% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0781 lr=3.37e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0773 lr=3.33e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0773 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 043 / 100 | Elapsed: 0:14:07[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0773 |
| Val Loss 0.3919 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 60.34%[0m |
| [92m[1mmIoU [0m [92m[1m 40.29%[0m |
| [92m[1mmFscore [0m [92m[1m 53.98%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 49.11%[0m |
| [0m[1mmRecall [0m [0m[1m 68.48%[0m |
| [0m[1mKappa [0m [0m[1m 53.20%[0m |
| ────────────────── ────────── |
| Best mFscore 53.79% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 53.98% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0669 lr=3.29e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0670 lr=3.26e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0670 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 044 / 100 | Elapsed: 0:14:27[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0670 |
| Val Loss 0.3930 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 62.24%[0m |
| [92m[1mmIoU [0m [92m[1m 39.97%[0m |
| [92m[1mmFscore [0m [92m[1m 53.76%[0m |
| [0m[1mmPrecision [0m [0m[1m 48.06%[0m |
| [0m[1mmRecall [0m [0m[1m 68.45%[0m |
| [0m[1mKappa [0m [0m[1m 55.06%[0m |
| ────────────────── ────────── |
| Best mFscore 53.98% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0679 lr=3.21e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0678 lr=3.18e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0678 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 045 / 100 | Elapsed: 0:14:46[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0678 |
| Val Loss 0.3776 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 63.64%[0m |
| [92m[1mmIoU [0m [92m[1m 39.88%[0m |
| [92m[1mmFscore [0m [92m[1m 53.70%[0m |
| [0m[1mmPrecision [0m [0m[1m 47.92%[0m |
| [0m[1mmRecall [0m [0m[1m 68.39%[0m |
| [0m[1mKappa [0m [0m[1m 56.38%[0m |
| ────────────────── ────────── |
| Best mFscore 53.98% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0633 lr=3.13e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0645 lr=3.10e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0645 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 046 / 100 | Elapsed: 0:15:05[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0645 |
| Val Loss 0.3771 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 60.77%[0m |
| [92m[1mmIoU [0m [92m[1m 39.57%[0m |
| [92m[1mmFscore [0m [92m[1m 53.21%[0m |
| [0m[1mmPrecision [0m [0m[1m 48.17%[0m |
| [0m[1mmRecall [0m [0m[1m 67.63%[0m |
| [0m[1mKappa [0m [0m[1m 53.64%[0m |
| ────────────────── ────────── |
| Best mFscore 53.98% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0621 lr=3.05e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0628 lr=3.02e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0628 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 047 / 100 | Elapsed: 0:15:25[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0628 |
| Val Loss 0.4149 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 62.80%[0m |
| [92m[1mmIoU [0m [92m[1m 40.95%[0m |
| [92m[1mmFscore [0m [92m[1m 54.82%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 49.39%[0m |
| [0m[1mmRecall [0m [0m[1m 67.83%[0m |
| [0m[1mKappa [0m [0m[1m 55.60%[0m |
| ────────────────── ────────── |
| Best mFscore 53.98% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 54.82% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0630 lr=2.97e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0605 lr=2.94e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0605 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 048 / 100 | Elapsed: 0:15:44[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0605 |
| Val Loss 0.3967 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 63.94%[0m |
| [92m[1mmIoU [0m [92m[1m 41.83%[0m |
| [92m[1mmFscore [0m [92m[1m 55.67%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 50.37%[0m |
| [0m[1mmRecall [0m [0m[1m 69.38%[0m |
| [0m[1mKappa [0m [0m[1m 56.84%[0m |
| ────────────────── ────────── |
| Best mFscore 54.82% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 55.67% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0568 lr=2.89e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0607 lr=2.86e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0607 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 049 / 100 | Elapsed: 0:16:04[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0607 |
| Val Loss 0.4104 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 61.74%[0m |
| [92m[1mmIoU [0m [92m[1m 39.54%[0m |
| [92m[1mmFscore [0m [92m[1m 53.34%[0m |
| [0m[1mmPrecision [0m [0m[1m 47.83%[0m |
| [0m[1mmRecall [0m [0m[1m 68.43%[0m |
| [0m[1mKappa [0m [0m[1m 54.65%[0m |
| ────────────────── ────────── |
| Best mFscore 55.67% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0608 lr=2.81e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0590 lr=2.78e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0590 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 050 / 100 | Elapsed: 0:16:23[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0590 |
| Val Loss 0.4251 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 61.47%[0m |
| [92m[1mmIoU [0m [92m[1m 39.93%[0m |
| [92m[1mmFscore [0m [92m[1m 53.24%[0m |
| [0m[1mmPrecision [0m [0m[1m 48.22%[0m |
| [0m[1mmRecall [0m [0m[1m 68.05%[0m |
| [0m[1mKappa [0m [0m[1m 54.35%[0m |
| ────────────────── ────────── |
| Best mFscore 55.67% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0559 lr=2.73e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0574 lr=2.69e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0574 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 051 / 100 | Elapsed: 0:16:43[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0574 |
| Val Loss 0.4278 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 62.89%[0m |
| [92m[1mmIoU [0m [92m[1m 40.75%[0m |
| [92m[1mmFscore [0m [92m[1m 54.64%[0m |
| [0m[1mmPrecision [0m [0m[1m 49.64%[0m |
| [0m[1mmRecall [0m [0m[1m 67.80%[0m |
| [0m[1mKappa [0m [0m[1m 55.72%[0m |
| ────────────────── ────────── |
| Best mFscore 55.67% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0584 lr=2.65e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0564 lr=2.61e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0564 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 052 / 100 | Elapsed: 0:17:02[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0564 |
| Val Loss 0.4142 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 64.29%[0m |
| [92m[1mmIoU [0m [92m[1m 41.25%[0m |
| [92m[1mmFscore [0m [92m[1m 55.10%[0m |
| [0m[1mmPrecision [0m [0m[1m 49.26%[0m |
| [0m[1mmRecall [0m [0m[1m 68.89%[0m |
| [0m[1mKappa [0m [0m[1m 57.16%[0m |
| ────────────────── ────────── |
| Best mFscore 55.67% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0521 lr=2.57e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0531 lr=2.53e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0531 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 053 / 100 | Elapsed: 0:17:21[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0531 |
| Val Loss 0.4498 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 65.51%[0m |
| [92m[1mmIoU [0m [92m[1m 42.15%[0m |
| [92m[1mmFscore [0m [92m[1m 55.85%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 51.38%[0m |
| [0m[1mmRecall [0m [0m[1m 68.28%[0m |
| [0m[1mKappa [0m [0m[1m 58.32%[0m |
| ────────────────── ────────── |
| Best mFscore 55.67% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 55.85% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0527 lr=2.49e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0525 lr=2.45e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0525 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 054 / 100 | Elapsed: 0:17:41[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0525 |
| Val Loss 0.4373 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 62.96%[0m |
| [92m[1mmIoU [0m [92m[1m 41.59%[0m |
| [92m[1mmFscore [0m [92m[1m 55.50%[0m |
| [0m[1mmPrecision [0m [0m[1m 50.64%[0m |
| [0m[1mmRecall [0m [0m[1m 68.39%[0m |
| [0m[1mKappa [0m [0m[1m 55.84%[0m |
| ────────────────── ────────── |
| Best mFscore 55.85% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0521 lr=2.41e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0517 lr=2.37e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0517 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 055 / 100 | Elapsed: 0:18:00[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0517 |
| Val Loss 0.4529 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 64.25%[0m |
| [92m[1mmIoU [0m [92m[1m 42.39%[0m |
| [92m[1mmFscore [0m [92m[1m 56.38%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 51.09%[0m |
| [0m[1mmRecall [0m [0m[1m 68.64%[0m |
| [0m[1mKappa [0m [0m[1m 57.11%[0m |
| ────────────────── ────────── |
| Best mFscore 55.85% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 56.38% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0509 lr=2.32e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0511 lr=2.29e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0511 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 056 / 100 | Elapsed: 0:18:20[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0511 |
| Val Loss 0.4412 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 62.42%[0m |
| [92m[1mmIoU [0m [92m[1m 40.50%[0m |
| [92m[1mmFscore [0m [92m[1m 54.33%[0m |
| [0m[1mmPrecision [0m [0m[1m 48.80%[0m |
| [0m[1mmRecall [0m [0m[1m 68.78%[0m |
| [0m[1mKappa [0m [0m[1m 55.30%[0m |
| ────────────────── ────────── |
| Best mFscore 56.38% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0498 lr=2.24e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0504 lr=2.21e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0504 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 057 / 100 | Elapsed: 0:18:39[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0504 |
| Val Loss 0.4580 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.55%[0m |
| [92m[1mmIoU [0m [92m[1m 42.71%[0m |
| [92m[1mmFscore [0m [92m[1m 56.45%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 51.53%[0m |
| [0m[1mmRecall [0m [0m[1m 68.24%[0m |
| [0m[1mKappa [0m [0m[1m 59.32%[0m |
| ────────────────── ────────── |
| Best mFscore 56.38% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 56.45% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0487 lr=2.16e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0488 lr=2.13e-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: 0:18:59[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0488 |
| Val Loss 0.4465 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 65.80%[0m |
| [92m[1mmIoU [0m [92m[1m 42.92%[0m |
| [92m[1mmFscore [0m [92m[1m 56.99%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 52.09%[0m |
| [0m[1mmRecall [0m [0m[1m 68.39%[0m |
| [0m[1mKappa [0m [0m[1m 58.63%[0m |
| ────────────────── ────────── |
| Best mFscore 56.45% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 56.99% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0467 lr=2.08e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0470 lr=2.05e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0470 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 059 / 100 | Elapsed: 0:19:19[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0470 |
| Val Loss 0.4547 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 65.32%[0m |
| [92m[1mmIoU [0m [92m[1m 43.23%[0m |
| [92m[1mmFscore [0m [92m[1m 57.21%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 52.83%[0m |
| [0m[1mmRecall [0m [0m[1m 68.15%[0m |
| [0m[1mKappa [0m [0m[1m 58.11%[0m |
| ────────────────── ────────── |
| Best mFscore 56.99% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 57.21% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0463 lr=2.00e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0466 lr=1.97e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0466 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 060 / 100 | Elapsed: 0:19:38[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0466 |
| Val Loss 0.4398 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 64.47%[0m |
| [92m[1mmIoU [0m [92m[1m 42.31%[0m |
| [92m[1mmFscore [0m [92m[1m 56.30%[0m |
| [0m[1mmPrecision [0m [0m[1m 51.37%[0m |
| [0m[1mmRecall [0m [0m[1m 68.36%[0m |
| [0m[1mKappa [0m [0m[1m 57.37%[0m |
| ────────────────── ────────── |
| Best mFscore 57.21% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0459 lr=1.92e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0465 lr=1.89e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0465 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 061 / 100 | Elapsed: 0:19:58[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0465 |
| Val Loss 0.4517 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 65.88%[0m |
| [92m[1mmIoU [0m [92m[1m 43.55%[0m |
| [92m[1mmFscore [0m [92m[1m 57.56%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 52.82%[0m |
| [0m[1mmRecall [0m [0m[1m 69.01%[0m |
| [0m[1mKappa [0m [0m[1m 58.73%[0m |
| ────────────────── ────────── |
| Best mFscore 57.21% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 57.56% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0450 lr=1.84e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0455 lr=1.81e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0455 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 062 / 100 | Elapsed: 0:20:17[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0455 |
| Val Loss 0.4817 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 65.44%[0m |
| [92m[1mmIoU [0m [92m[1m 43.50%[0m |
| [92m[1mmFscore [0m [92m[1m 57.38%[0m |
| [0m[1mmPrecision [0m [0m[1m 53.28%[0m |
| [0m[1mmRecall [0m [0m[1m 68.63%[0m |
| [0m[1mKappa [0m [0m[1m 58.34%[0m |
| ────────────────── ────────── |
| Best mFscore 57.56% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0432 lr=1.77e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0433 lr=1.73e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0433 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 063 / 100 | Elapsed: 0:20:36[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0433 |
| Val Loss 0.4855 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.76%[0m |
| [92m[1mmIoU [0m [92m[1m 43.45%[0m |
| [92m[1mmFscore [0m [92m[1m 57.47%[0m |
| [0m[1mmPrecision [0m [0m[1m 52.85%[0m |
| [0m[1mmRecall [0m [0m[1m 68.12%[0m |
| [0m[1mKappa [0m [0m[1m 59.57%[0m |
| ────────────────── ────────── |
| Best mFscore 57.56% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0437 lr=1.69e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0432 lr=1.66e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0432 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 064 / 100 | Elapsed: 0:20:55[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0432 |
| Val Loss 0.4910 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.78%[0m |
| [92m[1mmIoU [0m [92m[1m 44.41%[0m |
| [92m[1mmFscore [0m [92m[1m 58.34%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 54.36%[0m |
| [0m[1mmRecall [0m [0m[1m 68.47%[0m |
| [0m[1mKappa [0m [0m[1m 59.64%[0m |
| ────────────────── ────────── |
| Best mFscore 57.56% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 58.34% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0427 lr=1.61e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0432 lr=1.58e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0432 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 065 / 100 | Elapsed: 0:21:15[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0432 |
| Val Loss 0.4664 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 67.06%[0m |
| [92m[1mmIoU [0m [92m[1m 43.74%[0m |
| [92m[1mmFscore [0m [92m[1m 57.70%[0m |
| [0m[1mmPrecision [0m [0m[1m 52.31%[0m |
| [0m[1mmRecall [0m [0m[1m 69.27%[0m |
| [0m[1mKappa [0m [0m[1m 59.93%[0m |
| ────────────────── ────────── |
| Best mFscore 58.34% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0424 lr=1.54e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0418 lr=1.51e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0418 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 066 / 100 | Elapsed: 0:21:34[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0418 |
| Val Loss 0.4647 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 67.77%[0m |
| [92m[1mmIoU [0m [92m[1m 44.20%[0m |
| [92m[1mmFscore [0m [92m[1m 58.15%[0m |
| [0m[1mmPrecision [0m [0m[1m 53.45%[0m |
| [0m[1mmRecall [0m [0m[1m 68.75%[0m |
| [0m[1mKappa [0m [0m[1m 60.66%[0m |
| ────────────────── ────────── |
| Best mFscore 58.34% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0412 lr=1.47e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0418 lr=1.43e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0418 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 067 / 100 | Elapsed: 0:21:54[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0418 |
| Val Loss 0.4799 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 67.78%[0m |
| [92m[1mmIoU [0m [92m[1m 44.00%[0m |
| [92m[1mmFscore [0m [92m[1m 57.98%[0m |
| [0m[1mmPrecision [0m [0m[1m 53.68%[0m |
| [0m[1mmRecall [0m [0m[1m 68.22%[0m |
| [0m[1mKappa [0m [0m[1m 60.59%[0m |
| ────────────────── ────────── |
| Best mFscore 58.34% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0403 lr=1.39e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0403 lr=1.36e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0403 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 068 / 100 | Elapsed: 0:22:13[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0403 |
| Val Loss 0.4857 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 67.58%[0m |
| [92m[1mmIoU [0m [92m[1m 44.37%[0m |
| [92m[1mmFscore [0m [92m[1m 58.38%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 53.98%[0m |
| [0m[1mmRecall [0m [0m[1m 68.95%[0m |
| [0m[1mKappa [0m [0m[1m 60.46%[0m |
| ────────────────── ────────── |
| Best mFscore 58.34% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 58.38% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0393 lr=1.32e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0391 lr=1.29e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0391 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 069 / 100 | Elapsed: 0:22:33[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0391 |
| Val Loss 0.4680 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 67.19%[0m |
| [92m[1mmIoU [0m [92m[1m 44.25%[0m |
| [92m[1mmFscore [0m [92m[1m 58.34%[0m |
| [0m[1mmPrecision [0m [0m[1m 53.62%[0m |
| [0m[1mmRecall [0m [0m[1m 69.22%[0m |
| [0m[1mKappa [0m [0m[1m 60.06%[0m |
| ────────────────── ────────── |
| Best mFscore 58.38% |
| Val Time 4.2s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0406 lr=1.25e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0391 lr=1.22e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0391 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 070 / 100 | Elapsed: 0:22:52[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0391 |
| Val Loss 0.4943 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 66.93%[0m |
| [92m[1mmIoU [0m [92m[1m 44.43%[0m |
| [92m[1mmFscore [0m [92m[1m 58.35%[0m |
| [0m[1mmPrecision [0m [0m[1m 54.60%[0m |
| [0m[1mmRecall [0m [0m[1m 68.06%[0m |
| [0m[1mKappa [0m [0m[1m 59.74%[0m |
| ────────────────── ────────── |
| Best mFscore 58.38% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0385 lr=1.18e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0382 lr=1.15e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0382 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 071 / 100 | Elapsed: 0:23:11[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0382 |
| Val Loss 0.4838 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 68.49%[0m |
| [92m[1mmIoU [0m [92m[1m 45.03%[0m |
| [92m[1mmFscore [0m [92m[1m 59.12%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 54.52%[0m |
| [0m[1mmRecall [0m [0m[1m 69.18%[0m |
| [0m[1mKappa [0m [0m[1m 61.40%[0m |
| ────────────────── ────────── |
| Best mFscore 58.38% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 59.12% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0381 lr=1.12e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0377 lr=1.09e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0377 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 072 / 100 | Elapsed: 0:23:31[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0377 |
| Val Loss 0.4905 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 68.89%[0m |
| [92m[1mmIoU [0m [92m[1m 45.14%[0m |
| [92m[1mmFscore [0m [92m[1m 59.20%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 54.93%[0m |
| [0m[1mmRecall [0m [0m[1m 68.36%[0m |
| [0m[1mKappa [0m [0m[1m 61.72%[0m |
| ────────────────── ────────── |
| Best mFscore 59.12% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 59.20% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0373 lr=1.05e-05 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0370 lr=1.02e-05 eta=0:00:00 |
| [92mDone: avg_loss=0.0370 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 073 / 100 | Elapsed: 0:23:51[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0370 |
| Val Loss 0.5078 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 68.24%[0m |
| [92m[1mmIoU [0m [92m[1m 44.00%[0m |
| [92m[1mmFscore [0m [92m[1m 57.95%[0m |
| [0m[1mmPrecision [0m [0m[1m 53.42%[0m |
| [0m[1mmRecall [0m [0m[1m 68.32%[0m |
| [0m[1mKappa [0m [0m[1m 61.11%[0m |
| ────────────────── ────────── |
| Best mFscore 59.20% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0363 lr=9.88e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0362 lr=9.61e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0362 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 074 / 100 | Elapsed: 0:24:10[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0362 |
| Val Loss 0.4990 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.69%[0m |
| [92m[1mmIoU [0m [92m[1m 45.58%[0m |
| [92m[1mmFscore [0m [92m[1m 59.67%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 55.57%[0m |
| [0m[1mmRecall [0m [0m[1m 68.55%[0m |
| [0m[1mKappa [0m [0m[1m 62.56%[0m |
| ────────────────── ────────── |
| Best mFscore 59.20% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 59.67% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0355 lr=9.26e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0358 lr=8.99e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0358 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 075 / 100 | Elapsed: 0:24:30[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0358 |
| Val Loss 0.5187 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 68.80%[0m |
| [92m[1mmIoU [0m [92m[1m 45.33%[0m |
| [92m[1mmFscore [0m [92m[1m 59.29%[0m |
| [0m[1mmPrecision [0m [0m[1m 55.31%[0m |
| [0m[1mmRecall [0m [0m[1m 68.23%[0m |
| [0m[1mKappa [0m [0m[1m 61.64%[0m |
| ────────────────── ────────── |
| Best mFscore 59.67% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0356 lr=8.66e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0356 lr=8.40e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0356 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 076 / 100 | Elapsed: 0:24:49[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0356 |
| Val Loss 0.4988 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.62%[0m |
| [92m[1mmIoU [0m [92m[1m 45.66%[0m |
| [92m[1mmFscore [0m [92m[1m 59.69%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 55.23%[0m |
| [0m[1mmRecall [0m [0m[1m 68.78%[0m |
| [0m[1mKappa [0m [0m[1m 62.51%[0m |
| ────────────────── ────────── |
| Best mFscore 59.67% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 59.69% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0353 lr=8.08e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0351 lr=7.83e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0351 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 077 / 100 | Elapsed: 0:25:08[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0351 |
| Val Loss 0.5203 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.37%[0m |
| [92m[1mmIoU [0m [92m[1m 45.50%[0m |
| [92m[1mmFscore [0m [92m[1m 59.43%[0m |
| [0m[1mmPrecision [0m [0m[1m 55.90%[0m |
| [0m[1mmRecall [0m [0m[1m 68.14%[0m |
| [0m[1mKappa [0m [0m[1m 62.19%[0m |
| ────────────────── ────────── |
| Best mFscore 59.69% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0356 lr=7.52e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0347 lr=7.27e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0347 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 078 / 100 | Elapsed: 0:25:28[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0347 |
| Val Loss 0.5114 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.14%[0m |
| [92m[1mmIoU [0m [92m[1m 45.34%[0m |
| [92m[1mmFscore [0m [92m[1m 59.43%[0m |
| [0m[1mmPrecision [0m [0m[1m 55.46%[0m |
| [0m[1mmRecall [0m [0m[1m 68.32%[0m |
| [0m[1mKappa [0m [0m[1m 61.99%[0m |
| ────────────────── ────────── |
| Best mFscore 59.69% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0346 lr=6.97e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0342 lr=6.74e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0342 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 079 / 100 | Elapsed: 0:25:47[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0342 |
| Val Loss 0.5279 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 68.69%[0m |
| [92m[1mmIoU [0m [92m[1m 45.33%[0m |
| [92m[1mmFscore [0m [92m[1m 59.42%[0m |
| [0m[1mmPrecision [0m [0m[1m 55.63%[0m |
| [0m[1mmRecall [0m [0m[1m 68.01%[0m |
| [0m[1mKappa [0m [0m[1m 61.52%[0m |
| ────────────────── ────────── |
| Best mFscore 59.69% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0339 lr=6.45e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0338 lr=6.22e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0338 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 080 / 100 | Elapsed: 0:26:06[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0338 |
| Val Loss 0.5332 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.40%[0m |
| [92m[1mmIoU [0m [92m[1m 45.73%[0m |
| [92m[1mmFscore [0m [92m[1m 59.65%[0m |
| [0m[1mmPrecision [0m [0m[1m 56.06%[0m |
| [0m[1mmRecall [0m [0m[1m 67.88%[0m |
| [0m[1mKappa [0m [0m[1m 62.24%[0m |
| ────────────────── ────────── |
| Best mFscore 59.69% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0346 lr=5.95e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0337 lr=5.73e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0337 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 081 / 100 | Elapsed: 0:26:25[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0337 |
| Val Loss 0.5173 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.76%[0m |
| [92m[1mmIoU [0m [92m[1m 45.94%[0m |
| [92m[1mmFscore [0m [92m[1m 59.92%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 56.06%[0m |
| [0m[1mmRecall [0m [0m[1m 68.43%[0m |
| [0m[1mKappa [0m [0m[1m 62.63%[0m |
| ────────────────── ────────── |
| Best mFscore 59.69% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 59.92% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0336 lr=5.47e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0332 lr=5.26e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0332 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 082 / 100 | Elapsed: 0:26:45[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0332 |
| Val Loss 0.5220 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.88%[0m |
| [92m[1mmIoU [0m [92m[1m 45.57%[0m |
| [92m[1mmFscore [0m [92m[1m 59.57%[0m |
| [0m[1mmPrecision [0m [0m[1m 55.53%[0m |
| [0m[1mmRecall [0m [0m[1m 68.01%[0m |
| [0m[1mKappa [0m [0m[1m 62.72%[0m |
| ────────────────── ────────── |
| Best mFscore 59.92% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0320 lr=5.01e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0328 lr=4.81e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0328 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 083 / 100 | Elapsed: 0:27:04[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0328 |
| Val Loss 0.5308 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.49%[0m |
| [92m[1mmIoU [0m [92m[1m 45.79%[0m |
| [92m[1mmFscore [0m [92m[1m 59.73%[0m |
| [0m[1mmPrecision [0m [0m[1m 56.03%[0m |
| [0m[1mmRecall [0m [0m[1m 68.06%[0m |
| [0m[1mKappa [0m [0m[1m 62.35%[0m |
| ────────────────── ────────── |
| Best mFscore 59.92% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0332 lr=4.57e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0327 lr=4.39e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0327 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 084 / 100 | Elapsed: 0:27:23[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0327 |
| Val Loss 0.5325 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 70.15%[0m |
| [92m[1mmIoU [0m [92m[1m 45.63%[0m |
| [92m[1mmFscore [0m [92m[1m 59.63%[0m |
| [0m[1mmPrecision [0m [0m[1m 55.63%[0m |
| [0m[1mmRecall [0m [0m[1m 68.15%[0m |
| [0m[1mKappa [0m [0m[1m 63.01%[0m |
| ────────────────── ────────── |
| Best mFscore 59.92% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0321 lr=4.16e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0323 lr=3.99e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0323 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 085 / 100 | Elapsed: 0:27:42[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0323 |
| Val Loss 0.5455 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.95%[0m |
| [92m[1mmIoU [0m [92m[1m 45.97%[0m |
| [92m[1mmFscore [0m [92m[1m 59.98%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 56.50%[0m |
| [0m[1mmRecall [0m [0m[1m 67.82%[0m |
| [0m[1mKappa [0m [0m[1m 62.79%[0m |
| ────────────────── ────────── |
| Best mFscore 59.92% |
| Val Time 4.1s |
|
|
| [92m[1m★ New best mFscore: 59.98% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0321 lr=3.77e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0322 lr=3.61e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0322 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 086 / 100 | Elapsed: 0:28:02[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0322 |
| Val Loss 0.5428 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.86%[0m |
| [92m[1mmIoU [0m [92m[1m 45.87%[0m |
| [92m[1mmFscore [0m [92m[1m 59.88%[0m |
| [0m[1mmPrecision [0m [0m[1m 56.19%[0m |
| [0m[1mmRecall [0m [0m[1m 68.16%[0m |
| [0m[1mKappa [0m [0m[1m 62.74%[0m |
| ────────────────── ────────── |
| Best mFscore 59.98% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0316 lr=3.41e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0318 lr=3.26e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0318 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 087 / 100 | Elapsed: 0:28:21[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0318 |
| Val Loss 0.5466 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 70.10%[0m |
| [92m[1mmIoU [0m [92m[1m 45.85%[0m |
| [92m[1mmFscore [0m [92m[1m 59.83%[0m |
| [0m[1mmPrecision [0m [0m[1m 56.30%[0m |
| [0m[1mmRecall [0m [0m[1m 67.93%[0m |
| [0m[1mKappa [0m [0m[1m 62.96%[0m |
| ────────────────── ────────── |
| Best mFscore 59.98% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0312 lr=3.07e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0317 lr=2.93e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0317 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 088 / 100 | Elapsed: 0:28:40[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0317 |
| Val Loss 0.5382 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 70.19%[0m |
| [92m[1mmIoU [0m [92m[1m 46.10%[0m |
| [92m[1mmFscore [0m [92m[1m 60.13%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 56.65%[0m |
| [0m[1mmRecall [0m [0m[1m 68.06%[0m |
| [0m[1mKappa [0m [0m[1m 63.05%[0m |
| ────────────────── ────────── |
| Best mFscore 59.98% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 60.13% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0315 lr=2.75e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0315 lr=2.62e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0315 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 089 / 100 | Elapsed: 0:29:00[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0315 |
| Val Loss 0.5373 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 70.04%[0m |
| [92m[1mmIoU [0m [92m[1m 46.03%[0m |
| [92m[1mmFscore [0m [92m[1m 60.04%[0m |
| [0m[1mmPrecision [0m [0m[1m 56.54%[0m |
| [0m[1mmRecall [0m [0m[1m 68.11%[0m |
| [0m[1mKappa [0m [0m[1m 62.90%[0m |
| ────────────────── ────────── |
| Best mFscore 60.13% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0308 lr=2.46e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0314 lr=2.34e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0314 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 090 / 100 | Elapsed: 0:29:19[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0314 |
| Val Loss 0.5509 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 70.18%[0m |
| [92m[1mmIoU [0m [92m[1m 46.08%[0m |
| [92m[1mmFscore [0m [92m[1m 60.11%[0m |
| [0m[1mmPrecision [0m [0m[1m 56.54%[0m |
| [0m[1mmRecall [0m [0m[1m 67.79%[0m |
| [0m[1mKappa [0m [0m[1m 63.00%[0m |
| ────────────────── ────────── |
| Best mFscore 60.13% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0315 lr=2.20e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0314 lr=2.09e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0314 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 091 / 100 | Elapsed: 0:29:38[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0314 |
| Val Loss 0.5429 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 69.76%[0m |
| [92m[1mmIoU [0m [92m[1m 46.14%[0m |
| [92m[1mmFscore [0m [92m[1m 60.12%[0m |
| [0m[1mmPrecision [0m [0m[1m 56.69%[0m |
| [0m[1mmRecall [0m [0m[1m 68.06%[0m |
| [0m[1mKappa [0m [0m[1m 62.61%[0m |
| ────────────────── ────────── |
| Best mFscore 60.13% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0311 lr=1.96e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0310 lr=1.86e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0310 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 092 / 100 | Elapsed: 0:29:57[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0310 |
| Val Loss 0.5437 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 70.40%[0m |
| [92m[1mmIoU [0m [92m[1m 46.11%[0m |
| [92m[1mmFscore [0m [92m[1m 60.09%[0m |
| [0m[1mmPrecision [0m [0m[1m 56.87%[0m |
| [0m[1mmRecall [0m [0m[1m 67.76%[0m |
| [0m[1mKappa [0m [0m[1m 63.25%[0m |
| ────────────────── ────────── |
| Best mFscore 60.13% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0314 lr=1.75e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0309 lr=1.66e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0309 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 093 / 100 | Elapsed: 0:30:16[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0309 |
| Val Loss 0.5327 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 70.61%[0m |
| [92m[1mmIoU [0m [92m[1m 46.18%[0m |
| [92m[1mmFscore [0m [92m[1m 60.22%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 56.55%[0m |
| [0m[1mmRecall [0m [0m[1m 68.07%[0m |
| [0m[1mKappa [0m [0m[1m 63.47%[0m |
| ────────────────── ────────── |
| Best mFscore 60.13% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 60.22% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0308 lr=1.56e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0308 lr=1.49e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0308 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 094 / 100 | Elapsed: 0:30:36[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0308 |
| Val Loss 0.5469 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 70.64%[0m |
| [92m[1mmIoU [0m [92m[1m 46.31%[0m |
| [92m[1mmFscore [0m [92m[1m 60.28%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 56.82%[0m |
| [0m[1mmRecall [0m [0m[1m 67.86%[0m |
| [0m[1mKappa [0m [0m[1m 63.48%[0m |
| ────────────────── ────────── |
| Best mFscore 60.22% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 60.28% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0307 lr=1.40e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0307 lr=1.34e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0307 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 095 / 100 | Elapsed: 0:30:55[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0307 |
| Val Loss 0.5523 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 71.06%[0m |
| [92m[1mmIoU [0m [92m[1m 46.33%[0m |
| [92m[1mmFscore [0m [92m[1m 60.33%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 56.90%[0m |
| [0m[1mmRecall [0m [0m[1m 67.83%[0m |
| [0m[1mKappa [0m [0m[1m 63.92%[0m |
| ────────────────── ────────── |
| Best mFscore 60.28% |
| Val Time 4.0s |
|
|
| [92m[1m★ New best mFscore: 60.33% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0306 lr=1.27e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0307 lr=1.22e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0307 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 096 / 100 | Elapsed: 0:31:15[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0307 |
| Val Loss 0.5598 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 71.14%[0m |
| [92m[1mmIoU [0m [92m[1m 46.26%[0m |
| [92m[1mmFscore [0m [92m[1m 60.22%[0m |
| [0m[1mmPrecision [0m [0m[1m 56.86%[0m |
| [0m[1mmRecall [0m [0m[1m 67.76%[0m |
| [0m[1mKappa [0m [0m[1m 64.00%[0m |
| ────────────────── ────────── |
| Best mFscore 60.33% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0303 lr=1.16e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0306 lr=1.12e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0306 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 097 / 100 | Elapsed: 0:31:34[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0306 |
| Val Loss 0.5539 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 70.63%[0m |
| [92m[1mmIoU [0m [92m[1m 46.15%[0m |
| [92m[1mmFscore [0m [92m[1m 60.14%[0m |
| [0m[1mmPrecision [0m [0m[1m 56.65%[0m |
| [0m[1mmRecall [0m [0m[1m 67.87%[0m |
| [0m[1mKappa [0m [0m[1m 63.49%[0m |
| ────────────────── ────────── |
| Best mFscore 60.33% |
| Val Time 4.0s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0312 lr=1.08e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0309 lr=1.05e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0309 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 098 / 100 | Elapsed: 0:31:53[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0309 |
| Val Loss 0.5460 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 70.76%[0m |
| [92m[1mmIoU [0m [92m[1m 46.10%[0m |
| [92m[1mmFscore [0m [92m[1m 60.11%[0m |
| [0m[1mmPrecision [0m [0m[1m 56.44%[0m |
| [0m[1mmRecall [0m [0m[1m 67.91%[0m |
| [0m[1mKappa [0m [0m[1m 63.61%[0m |
| ────────────────── ────────── |
| Best mFscore 60.33% |
| Val Time 3.9s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0301 lr=1.03e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0306 lr=1.01e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0306 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 099 / 100 | Elapsed: 0:32:13[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0306 |
| Val Loss 0.5572 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 70.78%[0m |
| [92m[1mmIoU [0m [92m[1m 46.32%[0m |
| [92m[1mmFscore [0m [92m[1m 60.30%[0m |
| [0m[1mmPrecision [0m [0m[1m 57.10%[0m |
| [0m[1mmRecall [0m [0m[1m 67.55%[0m |
| [0m[1mKappa [0m [0m[1m 63.61%[0m |
| ────────────────── ────────── |
| Best mFscore 60.33% |
| Val Time 4.1s |
|
|
| [1mTraining[0m |
| [██████████████████████░░░░░░░░░░░░░░░░░░] 55.6% iter 50/90 loss=0.0301 lr=1.00e-06 eta=0:00:06 |
| [████████████████████████████████████████] 100.0% iter 90/90 loss=0.0307 lr=1.00e-06 eta=0:00:00 |
| [92mDone: avg_loss=0.0307 time=0:00:14[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 100 / 100 | Elapsed: 0:32:32[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0307 |
| Val Loss 0.5639 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 70.70%[0m |
| [92m[1mmIoU [0m [92m[1m 46.21%[0m |
| [92m[1mmFscore [0m [92m[1m 60.19%[0m |
| [0m[1mmPrecision [0m [0m[1m 56.60%[0m |
| [0m[1mmRecall [0m [0m[1m 67.81%[0m |
| [0m[1mKappa [0m [0m[1m 63.55%[0m |
| ────────────────── ────────── |
| Best mFscore 60.33% |
| Val Time 4.0s |
|
|
| [1m[96m══════════════════════════════════════════════════════════════════════[0m |
| [1m[96m Final Test Evaluation[0m |
| [1m[96m══════════════════════════════════════════════════════════════════════[0m |
|
|
| [1mTestidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Final Test Results[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 71.48%[0m |
| [92m[1mmIoU [0m [92m[1m 46.80%[0m |
| [92m[1mmFscore [0m [92m[1m 61.00%[0m |
| [0m[1mmPrecision [0m [0m[1m 57.40%[0m |
| [0m[1mmRecall [0m [0m[1m 68.93%[0m |
| [0m[1mKappa [0m [0m[1m 64.33%[0m |
| ────────────────── ────────── |
| Test Loss 0.4765 |
| Total Time 0:32:39 |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Per-Class IoU (Test)[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Class IoU Bar |
| ────────────────────────────── ─────── ──────────────────── |
| [92mBackground 54.88% ██████████[0m |
| [92mMeadow 58.18% ███████████[0m |
| [92mSoft winter wheat 71.18% ██████████████[0m |
| [92mCorn 77.09% ███████████████[0m |
| [92mWinter barley 62.90% ████████████[0m |
| [92mWinter rapeseed 77.49% ███████████████[0m |
| [92mSpring barley 38.06% ███████[0m |
| [92mSunflower 57.16% ███████████[0m |
| [92mGrapevine 38.60% ███████[0m |
| [92mBeet 71.87% ██████████████[0m |
| [92mWinter triticale 23.72% ████[0m |
| [92mWinter durum wheat 47.26% █████████[0m |
| [92mFruits vegetables flowers 22.67% ████[0m |
| [92mPotatoes 42.60% ████████[0m |
| [92mLeguminous fodder 28.88% █████[0m |
| [92mSoybeans 62.73% ████████████[0m |
| [93mOrchard 18.81% ███[0m |
| [93mMixed cereal 16.81% ███[0m |
| [93mSorghum 18.40% ███[0m |
|
|
| [92m[1mAll results saved to: ./work_dirs/fold4_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 |
|
|
