| /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 1 | 2026-04-17 02:08:35[0m |
| [1m[96m══════════════════════════════════════════════════════════════════════[0m |
|
|
| Device : |
| VRAM : 191.7 GB |
| AMP : True |
| Batch size : 16 |
| Epochs : 100 |
| Num frames : 32 |
| Work dir : ./work_dirs/fold1 |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Building Datasets[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| PASTIS fold=1 split=train: 1279 patches |
| PASTIS fold=1 split=val: 623 patches |
| PASTIS fold=1 split=test: 531 patches |
|
|
| Train: 1279 patches Val: 623 patches Test: 531 patches |
| Train batches: 79 Val batches: 39 |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Building Model[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Total params : 196.2M |
| Trainable params : 196.2M |
|
|
| [1m[96m══════════════════════════════════════════════════════════════════════[0m |
| [1m[96m Training | 100 epochs | fold 1[0m |
| [1m[96m══════════════════════════════════════════════════════════════════════[0m |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=2.4168 lr=3.95e-06 eta=0:01:12 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=2.2252 lr=5.66e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=2.2252 time=0:02:14[0m |
|
|
| [1mValidating...[0m |
| GridwiseOp: Problemsize descriptor dimension check failure |
| GridwiseOp: Problemsize descriptor dimension check failure |
| GridwiseOp: Problemsize descriptor dimension check failure |
| GridwiseOp: Problemsize descriptor dimension check failure |
| GridwiseOp: Problemsize descriptor dimension check failure |
| GridwiseOp: Problemsize descriptor dimension check failure |
| GridwiseOp: Problemsize descriptor dimension check failure |
| GridwiseOp: Problemsize descriptor dimension check failure |
| GridwiseOp: Problemsize descriptor dimension check failure |
| GridwiseOp: Problemsize descriptor dimension check failure |
| GridwiseOp: Problemsize descriptor dimension check failure |
| GridwiseOp: Problemsize descriptor dimension check failure |
| GridwiseOp: Problemsize descriptor dimension check failure |
| GridwiseOp: Problemsize descriptor dimension check failure |
| GridwiseOp: Problemsize descriptor dimension check failure |
| MIOpen(HIP): Error [Init] Not found :31-DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3<256, 128, 128, 64, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3> |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 001 / 100 | Elapsed: 0:02:44[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 2.2252 |
| Val Loss 3.0657 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 59.36%[0m |
| [92m[1mmIoU [0m [92m[1m 3.46%[0m |
| [92m[1mmFscore [0m [92m[1m 4.50%[0m ★ |
| [0m[1mmPrecision [0m [0m[1m 8.87%[0m |
| [0m[1mmRecall [0m [0m[1m 6.13%[0m |
| [0m[1mKappa [0m [0m[1m 3.01%[0m |
| ────────────────── ────────── |
| Best mFscore 0.00% |
| Val Time 29.0s |
|
|
| [92m[1m★ New best mFscore: 4.50% → saved best_model.pth[0m |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=1.5884 lr=8.61e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=1.5277 lr=1.03e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=1.5277 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 002 / 100 | Elapsed: 0:03:21[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 1.5277 |
| Val Loss 4.3564 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 32.35%[0m |
| [92m[1mmIoU [0m [92m[1m 2.72%[0m |
| [92m[1mmFscore [0m [92m[1m 4.06%[0m |
| [0m[1mmPrecision [0m [0m[1m 10.65%[0m |
| [0m[1mmRecall [0m [0m[1m 8.95%[0m |
| [0m[1mKappa [0m [0m[1m 7.02%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=1.3313 lr=1.33e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=1.2942 lr=1.50e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=1.2942 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 003 / 100 | Elapsed: 0:03:57[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 1.2942 |
| Val Loss 6.8791 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 11.38%[0m |
| [92m[1mmIoU [0m [92m[1m 1.11%[0m |
| [92m[1mmFscore [0m [92m[1m 1.98%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.76%[0m |
| [0m[1mmRecall [0m [0m[1m 7.60%[0m |
| [0m[1mKappa [0m [0m[1m 2.32%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=1.2134 lr=1.79e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=1.1849 lr=1.96e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=1.1849 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 004 / 100 | Elapsed: 0:04:32[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 1.1849 |
| Val Loss 7.2976 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 14.31%[0m |
| [92m[1mmIoU [0m [92m[1m 1.35%[0m |
| [92m[1mmFscore [0m [92m[1m 2.32%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.39%[0m |
| [0m[1mmRecall [0m [0m[1m 7.71%[0m |
| [0m[1mKappa [0m [0m[1m 2.98%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=1.1092 lr=2.26e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=1.1128 lr=2.43e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=1.1128 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 005 / 100 | Elapsed: 0:05:08[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 1.1128 |
| Val Loss 10.0620 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 7.13%[0m |
| [92m[1mmIoU [0m [92m[1m 0.81%[0m |
| [92m[1mmFscore [0m [92m[1m 1.51%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.62%[0m |
| [0m[1mmRecall [0m [0m[1m 6.27%[0m |
| [0m[1mKappa [0m [0m[1m 1.34%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.7s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=1.0763 lr=2.73e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=1.0769 lr=2.90e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=1.0769 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 006 / 100 | Elapsed: 0:05:43[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 1.0769 |
| Val Loss 8.6700 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 7.64%[0m |
| [92m[1mmIoU [0m [92m[1m 0.93%[0m |
| [92m[1mmFscore [0m [92m[1m 1.74%[0m |
| [0m[1mmPrecision [0m [0m[1m 12.92%[0m |
| [0m[1mmRecall [0m [0m[1m 6.73%[0m |
| [0m[1mKappa [0m [0m[1m 1.71%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=1.0217 lr=3.19e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=1.0356 lr=3.36e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=1.0356 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 007 / 100 | Elapsed: 0:06:19[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 1.0356 |
| Val Loss 8.8265 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 7.83%[0m |
| [92m[1mmIoU [0m [92m[1m 0.95%[0m |
| [92m[1mmFscore [0m [92m[1m 1.78%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.24%[0m |
| [0m[1mmRecall [0m [0m[1m 6.88%[0m |
| [0m[1mKappa [0m [0m[1m 1.75%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.7s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.9873 lr=3.66e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.9814 lr=3.83e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.9814 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 008 / 100 | Elapsed: 0:06:54[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.9814 |
| Val Loss 7.9424 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 12.84%[0m |
| [92m[1mmIoU [0m [92m[1m 1.24%[0m |
| [92m[1mmFscore [0m [92m[1m 2.16%[0m |
| [0m[1mmPrecision [0m [0m[1m 18.49%[0m |
| [0m[1mmRecall [0m [0m[1m 7.37%[0m |
| [0m[1mKappa [0m [0m[1m 2.78%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.9614 lr=4.12e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.9660 lr=4.29e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.9660 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 009 / 100 | Elapsed: 0:07:30[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.9660 |
| Val Loss 10.4450 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 13.35%[0m |
| [92m[1mmIoU [0m [92m[1m 1.39%[0m |
| [92m[1mmFscore [0m [92m[1m 2.44%[0m |
| [0m[1mmPrecision [0m [0m[1m 18.59%[0m |
| [0m[1mmRecall [0m [0m[1m 7.07%[0m |
| [0m[1mKappa [0m [0m[1m 3.50%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.7s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.9220 lr=4.59e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.9333 lr=4.76e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.9333 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 010 / 100 | Elapsed: 0:08:05[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.9333 |
| Val Loss 8.9352 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 12.99%[0m |
| [92m[1mmIoU [0m [92m[1m 1.34%[0m |
| [92m[1mmFscore [0m [92m[1m 2.35%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.77%[0m |
| [0m[1mmRecall [0m [0m[1m 6.98%[0m |
| [0m[1mKappa [0m [0m[1m 3.20%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.9187 lr=5.06e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.9212 lr=5.23e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.9212 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 011 / 100 | Elapsed: 0:08:41[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.9212 |
| Val Loss 11.7064 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 4.94%[0m |
| [92m[1mmIoU [0m [92m[1m 0.73%[0m |
| [92m[1mmFscore [0m [92m[1m 1.42%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.86%[0m |
| [0m[1mmRecall [0m [0m[1m 6.45%[0m |
| [0m[1mKappa [0m [0m[1m 0.83%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.7s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.8644 lr=5.52e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.8789 lr=5.69e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.8789 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 012 / 100 | Elapsed: 0:09:17[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.8789 |
| Val Loss 9.2564 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.07%[0m |
| [92m[1mmIoU [0m [92m[1m 1.39%[0m |
| [92m[1mmFscore [0m [92m[1m 2.57%[0m |
| [0m[1mmPrecision [0m [0m[1m 21.56%[0m |
| [0m[1mmRecall [0m [0m[1m 7.50%[0m |
| [0m[1mKappa [0m [0m[1m 2.20%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.8444 lr=5.99e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.8629 lr=6.00e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.8629 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 013 / 100 | Elapsed: 0:09:52[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.8629 |
| Val Loss 11.4315 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 5.31%[0m |
| [92m[1mmIoU [0m [92m[1m 0.70%[0m |
| [92m[1mmFscore [0m [92m[1m 1.34%[0m |
| [0m[1mmPrecision [0m [0m[1m 12.29%[0m |
| [0m[1mmRecall [0m [0m[1m 6.38%[0m |
| [0m[1mKappa [0m [0m[1m 0.71%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.8496 lr=6.00e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.8501 lr=6.00e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.8501 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 014 / 100 | Elapsed: 0:10:28[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.8501 |
| Val Loss 12.1387 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 7.80%[0m |
| [92m[1mmIoU [0m [92m[1m 1.30%[0m |
| [92m[1mmFscore [0m [92m[1m 2.43%[0m |
| [0m[1mmPrecision [0m [0m[1m 19.71%[0m |
| [0m[1mmRecall [0m [0m[1m 6.95%[0m |
| [0m[1mKappa [0m [0m[1m 1.98%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.8119 lr=5.99e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.8043 lr=5.99e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.8043 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 015 / 100 | Elapsed: 0:11:04[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.8043 |
| Val Loss 13.1070 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 5.46%[0m |
| [92m[1mmIoU [0m [92m[1m 0.82%[0m |
| [92m[1mmFscore [0m [92m[1m 1.58%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.85%[0m |
| [0m[1mmRecall [0m [0m[1m 6.30%[0m |
| [0m[1mKappa [0m [0m[1m 1.06%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.7s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.7809 lr=5.98e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.7761 lr=5.98e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.7761 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 016 / 100 | Elapsed: 0:11:39[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.7761 |
| Val Loss 12.2053 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 6.13%[0m |
| [92m[1mmIoU [0m [92m[1m 0.86%[0m |
| [92m[1mmFscore [0m [92m[1m 1.63%[0m |
| [0m[1mmPrecision [0m [0m[1m 12.97%[0m |
| [0m[1mmRecall [0m [0m[1m 6.48%[0m |
| [0m[1mKappa [0m [0m[1m 1.19%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.7s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.7192 lr=5.97e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.7326 lr=5.96e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.7326 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 017 / 100 | Elapsed: 0:12:15[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.7326 |
| Val Loss 10.1697 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 14.62%[0m |
| [92m[1mmIoU [0m [92m[1m 1.66%[0m |
| [92m[1mmFscore [0m [92m[1m 2.91%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.87%[0m |
| [0m[1mmRecall [0m [0m[1m 7.86%[0m |
| [0m[1mKappa [0m [0m[1m 3.88%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.7173 lr=5.95e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.7296 lr=5.95e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.7296 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 018 / 100 | Elapsed: 0:12:50[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.7296 |
| Val Loss 12.5839 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 7.16%[0m |
| [92m[1mmIoU [0m [92m[1m 1.09%[0m |
| [92m[1mmFscore [0m [92m[1m 2.06%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.64%[0m |
| [0m[1mmRecall [0m [0m[1m 6.30%[0m |
| [0m[1mKappa [0m [0m[1m 1.78%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.7002 lr=5.93e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.7026 lr=5.92e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.7026 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 019 / 100 | Elapsed: 0:13:26[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.7026 |
| Val Loss 13.9551 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 7.29%[0m |
| [92m[1mmIoU [0m [92m[1m 1.03%[0m |
| [92m[1mmFscore [0m [92m[1m 1.95%[0m |
| [0m[1mmPrecision [0m [0m[1m 18.84%[0m |
| [0m[1mmRecall [0m [0m[1m 6.52%[0m |
| [0m[1mKappa [0m [0m[1m 1.44%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.6861 lr=5.91e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.6748 lr=5.90e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.6748 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 020 / 100 | Elapsed: 0:14:02[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.6748 |
| Val Loss 12.8145 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 8.65%[0m |
| [92m[1mmIoU [0m [92m[1m 1.19%[0m |
| [92m[1mmFscore [0m [92m[1m 2.21%[0m |
| [0m[1mmPrecision [0m [0m[1m 18.39%[0m |
| [0m[1mmRecall [0m [0m[1m 7.00%[0m |
| [0m[1mKappa [0m [0m[1m 2.02%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.6261 lr=5.88e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.6351 lr=5.87e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.6351 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 021 / 100 | Elapsed: 0:14:38[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.6351 |
| Val Loss 12.1816 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 8.48%[0m |
| [92m[1mmIoU [0m [92m[1m 1.12%[0m |
| [92m[1mmFscore [0m [92m[1m 2.09%[0m |
| [0m[1mmPrecision [0m [0m[1m 12.27%[0m |
| [0m[1mmRecall [0m [0m[1m 6.75%[0m |
| [0m[1mKappa [0m [0m[1m 1.97%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.6106 lr=5.85e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.6308 lr=5.84e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.6308 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 022 / 100 | Elapsed: 0:15:13[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.6308 |
| Val Loss 10.4017 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 11.07%[0m |
| [92m[1mmIoU [0m [92m[1m 1.33%[0m |
| [92m[1mmFscore [0m [92m[1m 2.40%[0m |
| [0m[1mmPrecision [0m [0m[1m 10.53%[0m |
| [0m[1mmRecall [0m [0m[1m 6.51%[0m |
| [0m[1mKappa [0m [0m[1m 2.47%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.6109 lr=5.81e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.6080 lr=5.80e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.6080 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 023 / 100 | Elapsed: 0:15:49[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.6080 |
| Val Loss 13.1973 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 5.95%[0m |
| [92m[1mmIoU [0m [92m[1m 0.94%[0m |
| [92m[1mmFscore [0m [92m[1m 1.80%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.84%[0m |
| [0m[1mmRecall [0m [0m[1m 6.70%[0m |
| [0m[1mKappa [0m [0m[1m 1.27%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.5722 lr=5.77e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.5812 lr=5.76e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.5812 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 024 / 100 | Elapsed: 0:16:25[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.5812 |
| Val Loss 15.5972 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 6.26%[0m |
| [92m[1mmIoU [0m [92m[1m 0.90%[0m |
| [92m[1mmFscore [0m [92m[1m 1.72%[0m |
| [0m[1mmPrecision [0m [0m[1m 19.53%[0m |
| [0m[1mmRecall [0m [0m[1m 6.23%[0m |
| [0m[1mKappa [0m [0m[1m 1.17%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.5426 lr=5.73e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.5489 lr=5.71e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.5489 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 025 / 100 | Elapsed: 0:17:01[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.5489 |
| Val Loss 14.7647 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 7.24%[0m |
| [92m[1mmIoU [0m [92m[1m 0.99%[0m |
| [92m[1mmFscore [0m [92m[1m 1.86%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.57%[0m |
| [0m[1mmRecall [0m [0m[1m 6.21%[0m |
| [0m[1mKappa [0m [0m[1m 1.58%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.5321 lr=5.68e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.5488 lr=5.67e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.5488 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 026 / 100 | Elapsed: 0:17:36[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.5488 |
| Val Loss 15.4604 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 6.19%[0m |
| [92m[1mmIoU [0m [92m[1m 0.80%[0m |
| [92m[1mmFscore [0m [92m[1m 1.52%[0m |
| [0m[1mmPrecision [0m [0m[1m 11.74%[0m |
| [0m[1mmRecall [0m [0m[1m 6.35%[0m |
| [0m[1mKappa [0m [0m[1m 1.09%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.7s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.5243 lr=5.64e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.5302 lr=5.62e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.5302 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 027 / 100 | Elapsed: 0:18:12[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.5302 |
| Val Loss 16.9596 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 7.56%[0m |
| [92m[1mmIoU [0m [92m[1m 0.94%[0m |
| [92m[1mmFscore [0m [92m[1m 1.76%[0m |
| [0m[1mmPrecision [0m [0m[1m 20.46%[0m |
| [0m[1mmRecall [0m [0m[1m 6.33%[0m |
| [0m[1mKappa [0m [0m[1m 1.52%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.5001 lr=5.58e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.5080 lr=5.56e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.5080 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 028 / 100 | Elapsed: 0:18:48[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.5080 |
| Val Loss 15.3382 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 9.05%[0m |
| [92m[1mmIoU [0m [92m[1m 1.01%[0m |
| [92m[1mmFscore [0m [92m[1m 1.86%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.97%[0m |
| [0m[1mmRecall [0m [0m[1m 6.17%[0m |
| [0m[1mKappa [0m [0m[1m 1.77%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.4759 lr=5.53e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.4829 lr=5.50e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.4829 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 029 / 100 | Elapsed: 0:19:24[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.4829 |
| Val Loss 14.7501 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 7.97%[0m |
| [92m[1mmIoU [0m [92m[1m 1.10%[0m |
| [92m[1mmFscore [0m [92m[1m 2.07%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.43%[0m |
| [0m[1mmRecall [0m [0m[1m 6.39%[0m |
| [0m[1mKappa [0m [0m[1m 1.68%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.4586 lr=5.47e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.4606 lr=5.44e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.4606 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 030 / 100 | Elapsed: 0:19:59[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.4606 |
| Val Loss 14.3078 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 9.86%[0m |
| [92m[1mmIoU [0m [92m[1m 1.34%[0m |
| [92m[1mmFscore [0m [92m[1m 2.48%[0m |
| [0m[1mmPrecision [0m [0m[1m 17.47%[0m |
| [0m[1mmRecall [0m [0m[1m 6.78%[0m |
| [0m[1mKappa [0m [0m[1m 2.32%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.4593 lr=5.40e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.4648 lr=5.38e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.4648 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 031 / 100 | Elapsed: 0:20:35[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.4648 |
| Val Loss 13.8263 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 11.95%[0m |
| [92m[1mmIoU [0m [92m[1m 1.62%[0m |
| [92m[1mmFscore [0m [92m[1m 2.92%[0m |
| [0m[1mmPrecision [0m [0m[1m 15.89%[0m |
| [0m[1mmRecall [0m [0m[1m 7.09%[0m |
| [0m[1mKappa [0m [0m[1m 3.06%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.4514 lr=5.34e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.4356 lr=5.31e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.4356 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 032 / 100 | Elapsed: 0:21:11[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.4356 |
| Val Loss 17.2576 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 5.74%[0m |
| [92m[1mmIoU [0m [92m[1m 0.72%[0m |
| [92m[1mmFscore [0m [92m[1m 1.37%[0m |
| [0m[1mmPrecision [0m [0m[1m 15.45%[0m |
| [0m[1mmRecall [0m [0m[1m 6.12%[0m |
| [0m[1mKappa [0m [0m[1m 0.89%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.3939 lr=5.27e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.3898 lr=5.24e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.3898 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 033 / 100 | Elapsed: 0:21:46[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3898 |
| Val Loss 16.0173 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 6.79%[0m |
| [92m[1mmIoU [0m [92m[1m 0.98%[0m |
| [92m[1mmFscore [0m [92m[1m 1.85%[0m |
| [0m[1mmPrecision [0m [0m[1m 11.90%[0m |
| [0m[1mmRecall [0m [0m[1m 6.21%[0m |
| [0m[1mKappa [0m [0m[1m 1.39%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.3727 lr=5.20e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.3723 lr=5.17e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.3723 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 034 / 100 | Elapsed: 0:22:22[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3723 |
| Val Loss 12.7180 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 16.31%[0m |
| [92m[1mmIoU [0m [92m[1m 2.04%[0m |
| [92m[1mmFscore [0m [92m[1m 3.56%[0m |
| [0m[1mmPrecision [0m [0m[1m 15.18%[0m |
| [0m[1mmRecall [0m [0m[1m 8.13%[0m |
| [0m[1mKappa [0m [0m[1m 4.33%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.3651 lr=5.13e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.3641 lr=5.10e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.3641 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 035 / 100 | Elapsed: 0:22:58[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3641 |
| Val Loss 15.8621 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 9.85%[0m |
| [92m[1mmIoU [0m [92m[1m 1.08%[0m |
| [92m[1mmFscore [0m [92m[1m 1.96%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.76%[0m |
| [0m[1mmRecall [0m [0m[1m 6.62%[0m |
| [0m[1mKappa [0m [0m[1m 2.16%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.3353 lr=5.05e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.3361 lr=5.02e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.3361 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 036 / 100 | Elapsed: 0:23:34[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3361 |
| Val Loss 15.3411 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 11.85%[0m |
| [92m[1mmIoU [0m [92m[1m 1.33%[0m |
| [92m[1mmFscore [0m [92m[1m 2.38%[0m |
| [0m[1mmPrecision [0m [0m[1m 15.23%[0m |
| [0m[1mmRecall [0m [0m[1m 7.08%[0m |
| [0m[1mKappa [0m [0m[1m 2.54%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.3142 lr=4.97e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.3188 lr=4.94e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.3188 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 037 / 100 | Elapsed: 0:24:10[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3188 |
| Val Loss 14.7565 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 14.43%[0m |
| [92m[1mmIoU [0m [92m[1m 1.76%[0m |
| [92m[1mmFscore [0m [92m[1m 3.12%[0m |
| [0m[1mmPrecision [0m [0m[1m 12.84%[0m |
| [0m[1mmRecall [0m [0m[1m 7.49%[0m |
| [0m[1mKappa [0m [0m[1m 3.51%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.3085 lr=4.89e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.3124 lr=4.86e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.3124 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 038 / 100 | Elapsed: 0:24:45[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3124 |
| Val Loss 14.3290 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 16.05%[0m |
| [92m[1mmIoU [0m [92m[1m 1.92%[0m |
| [92m[1mmFscore [0m [92m[1m 3.34%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.15%[0m |
| [0m[1mmRecall [0m [0m[1m 7.44%[0m |
| [0m[1mKappa [0m [0m[1m 4.05%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.3047 lr=4.80e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.3017 lr=4.77e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.3017 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 039 / 100 | Elapsed: 0:25:21[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.3017 |
| Val Loss 16.7230 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 13.92%[0m |
| [92m[1mmIoU [0m [92m[1m 1.58%[0m |
| [92m[1mmFscore [0m [92m[1m 2.79%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.26%[0m |
| [0m[1mmRecall [0m [0m[1m 7.02%[0m |
| [0m[1mKappa [0m [0m[1m 3.29%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.2915 lr=4.72e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.2855 lr=4.68e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.2855 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 040 / 100 | Elapsed: 0:25:56[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2855 |
| Val Loss 17.1575 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 8.55%[0m |
| [92m[1mmIoU [0m [92m[1m 1.17%[0m |
| [92m[1mmFscore [0m [92m[1m 2.18%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.30%[0m |
| [0m[1mmRecall [0m [0m[1m 6.54%[0m |
| [0m[1mKappa [0m [0m[1m 1.88%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.2685 lr=4.63e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.2708 lr=4.60e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.2708 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 041 / 100 | Elapsed: 0:26:32[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2708 |
| Val Loss 15.7666 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 15.75%[0m |
| [92m[1mmIoU [0m [92m[1m 1.85%[0m |
| [92m[1mmFscore [0m [92m[1m 3.24%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.48%[0m |
| [0m[1mmRecall [0m [0m[1m 7.47%[0m |
| [0m[1mKappa [0m [0m[1m 3.81%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.2566 lr=4.54e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.2632 lr=4.50e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.2632 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 042 / 100 | Elapsed: 0:27:08[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2632 |
| Val Loss 16.2391 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 15.69%[0m |
| [92m[1mmIoU [0m [92m[1m 1.84%[0m |
| [92m[1mmFscore [0m [92m[1m 3.20%[0m |
| [0m[1mmPrecision [0m [0m[1m 20.18%[0m |
| [0m[1mmRecall [0m [0m[1m 7.47%[0m |
| [0m[1mKappa [0m [0m[1m 4.29%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.7s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.2499 lr=4.45e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.2501 lr=4.41e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.2501 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 043 / 100 | Elapsed: 0:27:44[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2501 |
| Val Loss 17.4134 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 11.41%[0m |
| [92m[1mmIoU [0m [92m[1m 1.43%[0m |
| [92m[1mmFscore [0m [92m[1m 2.59%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.25%[0m |
| [0m[1mmRecall [0m [0m[1m 7.03%[0m |
| [0m[1mKappa [0m [0m[1m 2.85%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.2390 lr=4.35e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.2425 lr=4.32e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.2425 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 044 / 100 | Elapsed: 0:28:20[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2425 |
| Val Loss 17.6738 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 12.19%[0m |
| [92m[1mmIoU [0m [92m[1m 1.53%[0m |
| [92m[1mmFscore [0m [92m[1m 2.75%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.01%[0m |
| [0m[1mmRecall [0m [0m[1m 7.00%[0m |
| [0m[1mKappa [0m [0m[1m 2.91%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.2385 lr=4.25e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.2364 lr=4.22e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.2364 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 045 / 100 | Elapsed: 0:28:55[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2364 |
| Val Loss 17.9041 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 12.68%[0m |
| [92m[1mmIoU [0m [92m[1m 1.51%[0m |
| [92m[1mmFscore [0m [92m[1m 2.71%[0m |
| [0m[1mmPrecision [0m [0m[1m 15.27%[0m |
| [0m[1mmRecall [0m [0m[1m 6.90%[0m |
| [0m[1mKappa [0m [0m[1m 2.98%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.2282 lr=4.16e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.2267 lr=4.12e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.2267 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 046 / 100 | Elapsed: 0:29:31[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2267 |
| Val Loss 18.6079 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 11.38%[0m |
| [92m[1mmIoU [0m [92m[1m 1.40%[0m |
| [92m[1mmFscore [0m [92m[1m 2.53%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.23%[0m |
| [0m[1mmRecall [0m [0m[1m 6.95%[0m |
| [0m[1mKappa [0m [0m[1m 2.85%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.2186 lr=4.06e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.2181 lr=4.02e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.2181 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 047 / 100 | Elapsed: 0:30:07[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2181 |
| Val Loss 18.5695 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 11.04%[0m |
| [92m[1mmIoU [0m [92m[1m 1.42%[0m |
| [92m[1mmFscore [0m [92m[1m 2.59%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.51%[0m |
| [0m[1mmRecall [0m [0m[1m 6.96%[0m |
| [0m[1mKappa [0m [0m[1m 2.67%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.2073 lr=3.96e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.2087 lr=3.92e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.2087 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 048 / 100 | Elapsed: 0:30:43[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2087 |
| Val Loss 19.9175 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 7.30%[0m |
| [92m[1mmIoU [0m [92m[1m 0.96%[0m |
| [92m[1mmFscore [0m [92m[1m 1.81%[0m |
| [0m[1mmPrecision [0m [0m[1m 16.67%[0m |
| [0m[1mmRecall [0m [0m[1m 6.65%[0m |
| [0m[1mKappa [0m [0m[1m 1.43%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.2076 lr=3.86e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.2041 lr=3.82e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.2041 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 049 / 100 | Elapsed: 0:31:19[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.2041 |
| Val Loss 19.4002 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 13.91%[0m |
| [92m[1mmIoU [0m [92m[1m 1.66%[0m |
| [92m[1mmFscore [0m [92m[1m 2.95%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.59%[0m |
| [0m[1mmRecall [0m [0m[1m 7.21%[0m |
| [0m[1mKappa [0m [0m[1m 3.42%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.7s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1952 lr=3.75e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1977 lr=3.72e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1977 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 050 / 100 | Elapsed: 0:31:54[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1977 |
| Val Loss 18.0987 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 14.80%[0m |
| [92m[1mmIoU [0m [92m[1m 1.69%[0m |
| [92m[1mmFscore [0m [92m[1m 2.96%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.61%[0m |
| [0m[1mmRecall [0m [0m[1m 7.31%[0m |
| [0m[1mKappa [0m [0m[1m 3.55%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1965 lr=3.65e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1932 lr=3.61e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1932 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 051 / 100 | Elapsed: 0:32:30[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1932 |
| Val Loss 18.9550 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 12.45%[0m |
| [92m[1mmIoU [0m [92m[1m 1.42%[0m |
| [92m[1mmFscore [0m [92m[1m 2.54%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.64%[0m |
| [0m[1mmRecall [0m [0m[1m 6.84%[0m |
| [0m[1mKappa [0m [0m[1m 2.89%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1838 lr=3.55e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1828 lr=3.51e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1828 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 052 / 100 | Elapsed: 0:33:06[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1828 |
| Val Loss 18.5658 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 14.26%[0m |
| [92m[1mmIoU [0m [92m[1m 1.65%[0m |
| [92m[1mmFscore [0m [92m[1m 2.92%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.40%[0m |
| [0m[1mmRecall [0m [0m[1m 7.41%[0m |
| [0m[1mKappa [0m [0m[1m 3.42%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1740 lr=3.44e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1751 lr=3.40e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1751 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 053 / 100 | Elapsed: 0:33:42[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1751 |
| Val Loss 20.1786 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 11.74%[0m |
| [92m[1mmIoU [0m [92m[1m 1.38%[0m |
| [92m[1mmFscore [0m [92m[1m 2.49%[0m |
| [0m[1mmPrecision [0m [0m[1m 15.09%[0m |
| [0m[1mmRecall [0m [0m[1m 6.72%[0m |
| [0m[1mKappa [0m [0m[1m 2.72%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.7s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1669 lr=3.34e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1705 lr=3.30e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1705 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 054 / 100 | Elapsed: 0:34:17[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1705 |
| Val Loss 18.8860 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 15.18%[0m |
| [92m[1mmIoU [0m [92m[1m 1.76%[0m |
| [92m[1mmFscore [0m [92m[1m 3.09%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.74%[0m |
| [0m[1mmRecall [0m [0m[1m 7.48%[0m |
| [0m[1mKappa [0m [0m[1m 3.59%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1663 lr=3.23e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1659 lr=3.19e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1659 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 055 / 100 | Elapsed: 0:34:53[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1659 |
| Val Loss 20.0384 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 14.99%[0m |
| [92m[1mmIoU [0m [92m[1m 1.73%[0m |
| [92m[1mmFscore [0m [92m[1m 3.03%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.37%[0m |
| [0m[1mmRecall [0m [0m[1m 7.35%[0m |
| [0m[1mKappa [0m [0m[1m 3.96%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1648 lr=3.12e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1622 lr=3.08e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1622 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 056 / 100 | Elapsed: 0:35:29[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1622 |
| Val Loss 21.7538 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 8.66%[0m |
| [92m[1mmIoU [0m [92m[1m 1.18%[0m |
| [92m[1mmFscore [0m [92m[1m 2.19%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.04%[0m |
| [0m[1mmRecall [0m [0m[1m 6.55%[0m |
| [0m[1mKappa [0m [0m[1m 1.87%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1542 lr=3.02e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1551 lr=2.98e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1551 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 057 / 100 | Elapsed: 0:36:04[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1551 |
| Val Loss 21.1615 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 9.19%[0m |
| [92m[1mmIoU [0m [92m[1m 1.18%[0m |
| [92m[1mmFscore [0m [92m[1m 2.18%[0m |
| [0m[1mmPrecision [0m [0m[1m 20.22%[0m |
| [0m[1mmRecall [0m [0m[1m 6.69%[0m |
| [0m[1mKappa [0m [0m[1m 2.01%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1539 lr=2.91e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1516 lr=2.87e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1516 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 058 / 100 | Elapsed: 0:36:40[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1516 |
| Val Loss 20.1075 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 16.60%[0m |
| [92m[1mmIoU [0m [92m[1m 1.90%[0m |
| [92m[1mmFscore [0m [92m[1m 3.29%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.84%[0m |
| [0m[1mmRecall [0m [0m[1m 7.79%[0m |
| [0m[1mKappa [0m [0m[1m 3.93%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1438 lr=2.81e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1451 lr=2.77e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1451 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 059 / 100 | Elapsed: 0:37:16[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1451 |
| Val Loss 19.9536 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 13.83%[0m |
| [92m[1mmIoU [0m [92m[1m 1.69%[0m |
| [92m[1mmFscore [0m [92m[1m 3.02%[0m |
| [0m[1mmPrecision [0m [0m[1m 19.49%[0m |
| [0m[1mmRecall [0m [0m[1m 7.37%[0m |
| [0m[1mKappa [0m [0m[1m 3.24%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 6.0s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1416 lr=2.70e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1414 lr=2.66e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1414 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 060 / 100 | Elapsed: 0:37:52[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1414 |
| Val Loss 21.3899 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 14.17%[0m |
| [92m[1mmIoU [0m [92m[1m 1.64%[0m |
| [92m[1mmFscore [0m [92m[1m 2.90%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.92%[0m |
| [0m[1mmRecall [0m [0m[1m 7.26%[0m |
| [0m[1mKappa [0m [0m[1m 3.26%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1340 lr=2.60e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1361 lr=2.56e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1361 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 061 / 100 | Elapsed: 0:38:28[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1361 |
| Val Loss 21.3545 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 14.82%[0m |
| [92m[1mmIoU [0m [92m[1m 1.71%[0m |
| [92m[1mmFscore [0m [92m[1m 2.99%[0m |
| [0m[1mmPrecision [0m [0m[1m 15.18%[0m |
| [0m[1mmRecall [0m [0m[1m 7.28%[0m |
| [0m[1mKappa [0m [0m[1m 3.63%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1295 lr=2.49e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1314 lr=2.45e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1314 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 062 / 100 | Elapsed: 0:39:03[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1314 |
| Val Loss 23.5502 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 9.73%[0m |
| [92m[1mmIoU [0m [92m[1m 1.24%[0m |
| [92m[1mmFscore [0m [92m[1m 2.28%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.55%[0m |
| [0m[1mmRecall [0m [0m[1m 6.65%[0m |
| [0m[1mKappa [0m [0m[1m 2.12%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1277 lr=2.39e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1278 lr=2.35e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1278 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 063 / 100 | Elapsed: 0:39:39[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1278 |
| Val Loss 23.3308 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 9.89%[0m |
| [92m[1mmIoU [0m [92m[1m 1.21%[0m |
| [92m[1mmFscore [0m [92m[1m 2.22%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.68%[0m |
| [0m[1mmRecall [0m [0m[1m 6.77%[0m |
| [0m[1mKappa [0m [0m[1m 2.20%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1241 lr=2.28e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1240 lr=2.25e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1240 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 064 / 100 | Elapsed: 0:40:15[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1240 |
| Val Loss 23.4052 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 11.58%[0m |
| [92m[1mmIoU [0m [92m[1m 1.42%[0m |
| [92m[1mmFscore [0m [92m[1m 2.57%[0m |
| [0m[1mmPrecision [0m [0m[1m 15.12%[0m |
| [0m[1mmRecall [0m [0m[1m 6.84%[0m |
| [0m[1mKappa [0m [0m[1m 2.74%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.7s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1220 lr=2.18e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1204 lr=2.14e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1204 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 065 / 100 | Elapsed: 0:40:51[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1204 |
| Val Loss 23.6052 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 13.10%[0m |
| [92m[1mmIoU [0m [92m[1m 1.52%[0m |
| [92m[1mmFscore [0m [92m[1m 2.70%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.71%[0m |
| [0m[1mmRecall [0m [0m[1m 7.00%[0m |
| [0m[1mKappa [0m [0m[1m 3.07%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1165 lr=2.08e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1178 lr=2.04e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1178 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 066 / 100 | Elapsed: 0:41:26[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1178 |
| Val Loss 23.9475 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.12%[0m |
| [92m[1mmIoU [0m [92m[1m 1.24%[0m |
| [92m[1mmFscore [0m [92m[1m 2.27%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.02%[0m |
| [0m[1mmRecall [0m [0m[1m 6.70%[0m |
| [0m[1mKappa [0m [0m[1m 2.21%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1127 lr=1.98e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1129 lr=1.95e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1129 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 067 / 100 | Elapsed: 0:42:02[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1129 |
| Val Loss 24.0848 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.47%[0m |
| [92m[1mmIoU [0m [92m[1m 1.26%[0m |
| [92m[1mmFscore [0m [92m[1m 2.31%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.65%[0m |
| [0m[1mmRecall [0m [0m[1m 6.63%[0m |
| [0m[1mKappa [0m [0m[1m 2.10%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1068 lr=1.88e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1084 lr=1.85e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1084 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 068 / 100 | Elapsed: 0:42:38[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1084 |
| Val Loss 23.6797 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 12.65%[0m |
| [92m[1mmIoU [0m [92m[1m 1.50%[0m |
| [92m[1mmFscore [0m [92m[1m 2.70%[0m |
| [0m[1mmPrecision [0m [0m[1m 15.37%[0m |
| [0m[1mmRecall [0m [0m[1m 7.06%[0m |
| [0m[1mKappa [0m [0m[1m 2.99%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1058 lr=1.79e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1073 lr=1.75e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1073 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 069 / 100 | Elapsed: 0:43:14[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1073 |
| Val Loss 24.6979 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.36%[0m |
| [92m[1mmIoU [0m [92m[1m 1.30%[0m |
| [92m[1mmFscore [0m [92m[1m 2.37%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.60%[0m |
| [0m[1mmRecall [0m [0m[1m 6.84%[0m |
| [0m[1mKappa [0m [0m[1m 2.32%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1059 lr=1.69e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1046 lr=1.66e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1046 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 070 / 100 | Elapsed: 0:43:49[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1046 |
| Val Loss 24.8123 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 13.56%[0m |
| [92m[1mmIoU [0m [92m[1m 1.57%[0m |
| [92m[1mmFscore [0m [92m[1m 2.79%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.80%[0m |
| [0m[1mmRecall [0m [0m[1m 7.09%[0m |
| [0m[1mKappa [0m [0m[1m 3.20%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.1024 lr=1.60e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.1003 lr=1.56e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.1003 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 071 / 100 | Elapsed: 0:44:25[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.1003 |
| Val Loss 25.4997 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.70%[0m |
| [92m[1mmIoU [0m [92m[1m 1.36%[0m |
| [92m[1mmFscore [0m [92m[1m 2.48%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.28%[0m |
| [0m[1mmRecall [0m [0m[1m 6.64%[0m |
| [0m[1mKappa [0m [0m[1m 2.40%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.7s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0957 lr=1.51e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0969 lr=1.47e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0969 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 072 / 100 | Elapsed: 0:45:01[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0969 |
| Val Loss 25.2633 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 13.62%[0m |
| [92m[1mmIoU [0m [92m[1m 1.61%[0m |
| [92m[1mmFscore [0m [92m[1m 2.87%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.67%[0m |
| [0m[1mmRecall [0m [0m[1m 7.05%[0m |
| [0m[1mKappa [0m [0m[1m 3.16%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0954 lr=1.42e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0964 lr=1.39e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0964 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 073 / 100 | Elapsed: 0:45:37[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0964 |
| Val Loss 25.9059 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 12.24%[0m |
| [92m[1mmIoU [0m [92m[1m 1.47%[0m |
| [92m[1mmFscore [0m [92m[1m 2.64%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.42%[0m |
| [0m[1mmRecall [0m [0m[1m 6.85%[0m |
| [0m[1mKappa [0m [0m[1m 2.76%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0936 lr=1.33e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0929 lr=1.30e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0929 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 074 / 100 | Elapsed: 0:46:12[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0929 |
| Val Loss 27.5454 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 9.98%[0m |
| [92m[1mmIoU [0m [92m[1m 1.27%[0m |
| [92m[1mmFscore [0m [92m[1m 2.34%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.31%[0m |
| [0m[1mmRecall [0m [0m[1m 6.66%[0m |
| [0m[1mKappa [0m [0m[1m 2.17%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0884 lr=1.25e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0907 lr=1.21e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0907 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 075 / 100 | Elapsed: 0:46:48[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0907 |
| Val Loss 28.1871 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 9.43%[0m |
| [92m[1mmIoU [0m [92m[1m 1.18%[0m |
| [92m[1mmFscore [0m [92m[1m 2.17%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.63%[0m |
| [0m[1mmRecall [0m [0m[1m 6.54%[0m |
| [0m[1mKappa [0m [0m[1m 2.06%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0903 lr=1.16e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0883 lr=1.13e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0883 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 076 / 100 | Elapsed: 0:47:24[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0883 |
| Val Loss 27.9718 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 9.83%[0m |
| [92m[1mmIoU [0m [92m[1m 1.28%[0m |
| [92m[1mmFscore [0m [92m[1m 2.35%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.05%[0m |
| [0m[1mmRecall [0m [0m[1m 6.62%[0m |
| [0m[1mKappa [0m [0m[1m 2.29%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0854 lr=1.08e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0854 lr=1.05e-05 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0854 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 077 / 100 | Elapsed: 0:48:00[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0854 |
| Val Loss 28.3414 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 9.91%[0m |
| [92m[1mmIoU [0m [92m[1m 1.23%[0m |
| [92m[1mmFscore [0m [92m[1m 2.26%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.96%[0m |
| [0m[1mmRecall [0m [0m[1m 6.50%[0m |
| [0m[1mKappa [0m [0m[1m 2.12%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0841 lr=1.00e-05 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0835 lr=9.76e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0835 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 078 / 100 | Elapsed: 0:48:35[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0835 |
| Val Loss 28.4903 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.74%[0m |
| [92m[1mmIoU [0m [92m[1m 1.35%[0m |
| [92m[1mmFscore [0m [92m[1m 2.47%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.03%[0m |
| [0m[1mmRecall [0m [0m[1m 6.75%[0m |
| [0m[1mKappa [0m [0m[1m 2.43%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.7s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0802 lr=9.29e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0805 lr=9.02e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0805 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 079 / 100 | Elapsed: 0:49:11[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0805 |
| Val Loss 29.3997 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.89%[0m |
| [92m[1mmIoU [0m [92m[1m 1.33%[0m |
| [92m[1mmFscore [0m [92m[1m 2.41%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.78%[0m |
| [0m[1mmRecall [0m [0m[1m 6.64%[0m |
| [0m[1mKappa [0m [0m[1m 2.46%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0804 lr=8.57e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0796 lr=8.31e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0796 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 080 / 100 | Elapsed: 0:49:47[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0796 |
| Val Loss 29.5351 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 11.31%[0m |
| [92m[1mmIoU [0m [92m[1m 1.40%[0m |
| [92m[1mmFscore [0m [92m[1m 2.54%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.74%[0m |
| [0m[1mmRecall [0m [0m[1m 6.73%[0m |
| [0m[1mKappa [0m [0m[1m 2.57%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0778 lr=7.87e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0775 lr=7.62e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0775 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 081 / 100 | Elapsed: 0:50:23[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0775 |
| Val Loss 29.2190 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 11.84%[0m |
| [92m[1mmIoU [0m [92m[1m 1.45%[0m |
| [92m[1mmFscore [0m [92m[1m 2.62%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.83%[0m |
| [0m[1mmRecall [0m [0m[1m 6.78%[0m |
| [0m[1mKappa [0m [0m[1m 2.68%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0768 lr=7.21e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0754 lr=6.97e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0754 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 082 / 100 | Elapsed: 0:50:58[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0754 |
| Val Loss 30.3881 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.74%[0m |
| [92m[1mmIoU [0m [92m[1m 1.34%[0m |
| [92m[1mmFscore [0m [92m[1m 2.44%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.33%[0m |
| [0m[1mmRecall [0m [0m[1m 6.61%[0m |
| [0m[1mKappa [0m [0m[1m 2.42%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0733 lr=6.57e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0734 lr=6.35e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0734 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 083 / 100 | Elapsed: 0:51:34[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0734 |
| Val Loss 31.1368 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 9.98%[0m |
| [92m[1mmIoU [0m [92m[1m 1.25%[0m |
| [92m[1mmFscore [0m [92m[1m 2.30%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.67%[0m |
| [0m[1mmRecall [0m [0m[1m 6.57%[0m |
| [0m[1mKappa [0m [0m[1m 2.22%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0730 lr=5.97e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0724 lr=5.75e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0724 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 084 / 100 | Elapsed: 0:52:10[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0724 |
| Val Loss 32.3626 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 9.25%[0m |
| [92m[1mmIoU [0m [92m[1m 1.16%[0m |
| [92m[1mmFscore [0m [92m[1m 2.15%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.32%[0m |
| [0m[1mmRecall [0m [0m[1m 6.44%[0m |
| [0m[1mKappa [0m [0m[1m 1.95%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0721 lr=5.39e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0718 lr=5.19e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0718 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 085 / 100 | Elapsed: 0:52:46[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0718 |
| Val Loss 31.7615 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.26%[0m |
| [92m[1mmIoU [0m [92m[1m 1.30%[0m |
| [92m[1mmFscore [0m [92m[1m 2.38%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.45%[0m |
| [0m[1mmRecall [0m [0m[1m 6.62%[0m |
| [0m[1mKappa [0m [0m[1m 2.30%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0697 lr=4.85e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0694 lr=4.66e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0694 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 086 / 100 | Elapsed: 0:53:22[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0694 |
| Val Loss 31.6403 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.19%[0m |
| [92m[1mmIoU [0m [92m[1m 1.30%[0m |
| [92m[1mmFscore [0m [92m[1m 2.39%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.66%[0m |
| [0m[1mmRecall [0m [0m[1m 6.64%[0m |
| [0m[1mKappa [0m [0m[1m 2.27%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0658 lr=4.34e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0683 lr=4.17e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0683 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 087 / 100 | Elapsed: 0:53:58[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0683 |
| Val Loss 31.6843 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.96%[0m |
| [92m[1mmIoU [0m [92m[1m 1.37%[0m |
| [92m[1mmFscore [0m [92m[1m 2.49%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.43%[0m |
| [0m[1mmRecall [0m [0m[1m 6.69%[0m |
| [0m[1mKappa [0m [0m[1m 2.50%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.7s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0666 lr=3.87e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0665 lr=3.71e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0665 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 088 / 100 | Elapsed: 0:54:33[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0665 |
| Val Loss 32.1629 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.57%[0m |
| [92m[1mmIoU [0m [92m[1m 1.32%[0m |
| [92m[1mmFscore [0m [92m[1m 2.42%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.64%[0m |
| [0m[1mmRecall [0m [0m[1m 6.63%[0m |
| [0m[1mKappa [0m [0m[1m 2.38%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.7s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0661 lr=3.43e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0665 lr=3.28e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0665 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 089 / 100 | Elapsed: 0:55:09[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0665 |
| Val Loss 32.3392 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 9.94%[0m |
| [92m[1mmIoU [0m [92m[1m 1.29%[0m |
| [92m[1mmFscore [0m [92m[1m 2.37%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.64%[0m |
| [0m[1mmRecall [0m [0m[1m 6.57%[0m |
| [0m[1mKappa [0m [0m[1m 2.17%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0651 lr=3.03e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0651 lr=2.89e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0651 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 090 / 100 | Elapsed: 0:55:45[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0651 |
| Val Loss 32.3829 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.58%[0m |
| [92m[1mmIoU [0m [92m[1m 1.32%[0m |
| [92m[1mmFscore [0m [92m[1m 2.42%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.48%[0m |
| [0m[1mmRecall [0m [0m[1m 6.61%[0m |
| [0m[1mKappa [0m [0m[1m 2.33%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0635 lr=2.66e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0642 lr=2.53e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0642 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 091 / 100 | Elapsed: 0:56:20[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0642 |
| Val Loss 33.8353 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 9.15%[0m |
| [92m[1mmIoU [0m [92m[1m 1.18%[0m |
| [92m[1mmFscore [0m [92m[1m 2.19%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.35%[0m |
| [0m[1mmRecall [0m [0m[1m 6.46%[0m |
| [0m[1mKappa [0m [0m[1m 1.97%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0631 lr=2.33e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0637 lr=2.21e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0637 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 092 / 100 | Elapsed: 0:56:56[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0637 |
| Val Loss 33.7845 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.24%[0m |
| [92m[1mmIoU [0m [92m[1m 1.26%[0m |
| [92m[1mmFscore [0m [92m[1m 2.31%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.49%[0m |
| [0m[1mmRecall [0m [0m[1m 6.53%[0m |
| [0m[1mKappa [0m [0m[1m 2.23%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.7s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0645 lr=2.03e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0632 lr=1.93e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0632 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 093 / 100 | Elapsed: 0:57:32[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0632 |
| Val Loss 33.5007 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.54%[0m |
| [92m[1mmIoU [0m [92m[1m 1.31%[0m |
| [92m[1mmFscore [0m [92m[1m 2.39%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.53%[0m |
| [0m[1mmRecall [0m [0m[1m 6.61%[0m |
| [0m[1mKappa [0m [0m[1m 2.29%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0635 lr=1.77e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0630 lr=1.68e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0630 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 094 / 100 | Elapsed: 0:58:08[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0630 |
| Val Loss 33.4226 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.42%[0m |
| [92m[1mmIoU [0m [92m[1m 1.30%[0m |
| [92m[1mmFscore [0m [92m[1m 2.38%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.45%[0m |
| [0m[1mmRecall [0m [0m[1m 6.58%[0m |
| [0m[1mKappa [0m [0m[1m 2.30%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0629 lr=1.55e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0628 lr=1.48e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0628 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 095 / 100 | Elapsed: 0:58:43[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0628 |
| Val Loss 33.7457 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 9.71%[0m |
| [92m[1mmIoU [0m [92m[1m 1.25%[0m |
| [92m[1mmFscore [0m [92m[1m 2.30%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.38%[0m |
| [0m[1mmRecall [0m [0m[1m 6.52%[0m |
| [0m[1mKappa [0m [0m[1m 2.10%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0632 lr=1.36e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0624 lr=1.30e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0624 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 096 / 100 | Elapsed: 0:59:19[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0624 |
| Val Loss 33.3518 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.80%[0m |
| [92m[1mmIoU [0m [92m[1m 1.33%[0m |
| [92m[1mmFscore [0m [92m[1m 2.43%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.03%[0m |
| [0m[1mmRecall [0m [0m[1m 6.63%[0m |
| [0m[1mKappa [0m [0m[1m 2.38%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0615 lr=1.22e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0615 lr=1.17e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0615 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 097 / 100 | Elapsed: 0:59:55[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0615 |
| Val Loss 33.6797 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.76%[0m |
| [92m[1mmIoU [0m [92m[1m 1.33%[0m |
| [92m[1mmFscore [0m [92m[1m 2.43%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.43%[0m |
| [0m[1mmRecall [0m [0m[1m 6.63%[0m |
| [0m[1mKappa [0m [0m[1m 2.34%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0599 lr=1.11e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0612 lr=1.08e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0612 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 098 / 100 | Elapsed: 1:00:31[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0612 |
| Val Loss 34.0179 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.35%[0m |
| [92m[1mmIoU [0m [92m[1m 1.28%[0m |
| [92m[1mmFscore [0m [92m[1m 2.35%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.72%[0m |
| [0m[1mmRecall [0m [0m[1m 6.57%[0m |
| [0m[1mKappa [0m [0m[1m 2.26%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0622 lr=1.04e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0611 lr=1.02e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0611 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 099 / 100 | Elapsed: 1:01:06[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0611 |
| Val Loss 34.1047 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.34%[0m |
| [92m[1mmIoU [0m [92m[1m 1.32%[0m |
| [92m[1mmFscore [0m [92m[1m 2.41%[0m |
| [0m[1mmPrecision [0m [0m[1m 14.08%[0m |
| [0m[1mmRecall [0m [0m[1m 6.60%[0m |
| [0m[1mKappa [0m [0m[1m 2.27%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.9s |
|
|
| [1mTraining[0m |
| [█████████████████████████░░░░░░░░░░░░░░░] 63.3% iter 50/79 loss=0.0611 lr=1.00e-06 eta=0:00:10 |
| [████████████████████████████████████████] 100.0% iter 79/79 loss=0.0608 lr=1.00e-06 eta=0:00:00 |
| [92mTrain done: avg_loss=0.0608 time=0:00:27[0m |
|
|
| [1mValidating...[0m |
|
|
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
| [1m[93m Epoch 100 / 100 | Elapsed: 1:01:42[0m |
| [1m[93m──────────────────────────────────────────────────────────────────────[0m |
|
|
| Metric Value |
| ────────────────── ────────── |
| Train Loss 0.0608 |
| Val Loss 34.2195 |
| ────────────────── ────────── |
| [0m[1mOA [0m [0m[1m 10.33%[0m |
| [92m[1mmIoU [0m [92m[1m 1.30%[0m |
| [92m[1mmFscore [0m [92m[1m 2.37%[0m |
| [0m[1mmPrecision [0m [0m[1m 13.84%[0m |
| [0m[1mmRecall [0m [0m[1m 6.55%[0m |
| [0m[1mKappa [0m [0m[1m 2.26%[0m |
| ────────────────── ────────── |
| Best mFscore 4.50% |
| Val Time 5.8s |
|
|
| [1m[96m══════════════════════════════════════════════════════════════════════[0m |
| [1m[96m Final Test Evaluation[0m |
| [1m[96m══════════════════════════════════════════════════════════════════════[0m |
| Traceback (most recent call last): |
| File "/workspace/project/AgriFM_PASTIS/train.py", line 573, in <module> |
| main() |
| File "/workspace/project/AgriFM_PASTIS/train.py", line 512, in main |
| best_ckpt = torch.load(os.path.join(args.work_dir, 'best_model.pth'), |
| File "/opt/venv/lib/python3.10/site-packages/torch/serialization.py", line 1529, in load |
| raise pickle.UnpicklingError(_get_wo_message(str(e))) from None |
| _pickle.UnpicklingError: Weights only load failed. This file can still be loaded, to do so you have two options, [1mdo those steps only if you trust the source of the checkpoint[0m. |
| (1) In PyTorch 2.6, we changed the default value of the `weights_only` argument in `torch.load` from `False` to `True`. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source. |
| (2) Alternatively, to load with `weights_only=True` please check the recommended steps in the following error message. |
| WeightsUnpickler error: Unsupported global: GLOBAL numpy.core.multiarray.scalar was not an allowed global by default. Please use `torch.serialization.add_safe_globals([numpy.core.multiarray.scalar])` or the `torch.serialization.safe_globals([numpy.core.multiarray.scalar])` context manager to allowlist this global if you trust this class/function. |
|
|
| Check the documentation of torch.load to learn more about types accepted by default with weights_only https: |
|
|
