Training in progress epoch 42

README.md

@@ -14,24 +14,24 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.1856
-- Validation Loss: 0.4630
-- Validation Mean Iou: 0.3468
-- Validation Mean Accuracy: 0.4169
-- Validation Overall Accuracy: 0.8702
-- Validation Per Category Iou: [0.         0.79680775 0.87408906 0.80508886 0.7836208  0.54111501
-        nan 0.46906575 0.51571781 0.05906675 0.84646062 0.12752339
- 0.         0.02326951 0.         0.49396166 0.         0.
- 0.70301274 0.10455404 0.36326525 0.45432265 0.00288184        nan
- 0.06241517 0.29796314 0.27257073 0.         0.85824781 0.70264792
- 0.93738763 0.10944047 0.07468448 0.16378606 0.        ]
-- Validation Per Category Accuracy: [0.         0.92066362 0.93733642 0.8457505  0.80518061 0.72000372
-        nan 0.61879522 0.83036713 0.090212   0.93724404 0.17978977
- 0.         0.03259076 0.         0.52749727 0.         0.
- 0.80827055 0.12335237 0.6834038  0.55220964 0.00288184        nan
- 0.08086247 0.38878944 0.30794886 0.         0.93395437 0.8773043
- 0.97470902 0.14777538 0.20984564 0.21967583 0.        ]
-- Epoch: 41
+- Train Loss: 0.1886
+- Validation Loss: 0.4251
+- Validation Mean Iou: 0.3676
+- Validation Mean Accuracy: 0.4456
+- Validation Overall Accuracy: 0.8827
+- Validation Per Category Iou: [0.         0.81869055 0.88872516 0.83047488 0.84276443 0.50458334
+        nan 0.50154127 0.55514409 0.11767963 0.8593002  0.18142472
+ 0.         0.17150681 0.         0.52765579 0.         0.
+ 0.72523268 0.11768383 0.38784377 0.55537055 0.03125           nan
+ 0.04156492 0.2927821  0.28836848 0.         0.87210633 0.77489312
+ 0.94023927 0.01637101 0.07383087 0.2126436  0.        ]
+- Validation Per Category Accuracy: [0.         0.91039924 0.94692984 0.8782822  0.93049806 0.63547194
+        nan 0.64587233 0.81659018 0.1533604  0.95128203 0.25357001
+ 0.         0.5554868  0.         0.59909114 0.         0.
+ 0.81739862 0.14772157 0.70659589 0.64127558 0.03170029        nan
+ 0.05387168 0.38205471 0.34779739 0.         0.9516963  0.85983713
+ 0.97204659 0.02417058 0.18481435 0.30708968 0.        ]
+- Epoch: 42
 
 ## Model description
 
@@ -585,6 +585,17 @@ The following hyperparameters were used during training:
  0.80827055 0.12335237 0.6834038  0.55220964 0.00288184        nan
  0.08086247 0.38878944 0.30794886 0.         0.93395437 0.8773043
  0.97470902 0.14777538 0.20984564 0.21967583 0.        ]                                                                                                                                                         | 41    |
+| 0.1886     | 0.4251          | 0.3676              | 0.4456                   | 0.8827                      | [0.         0.81869055 0.88872516 0.83047488 0.84276443 0.50458334
+        nan 0.50154127 0.55514409 0.11767963 0.8593002  0.18142472
+ 0.         0.17150681 0.         0.52765579 0.         0.
+ 0.72523268 0.11768383 0.38784377 0.55537055 0.03125           nan
+ 0.04156492 0.2927821  0.28836848 0.         0.87210633 0.77489312
+ 0.94023927 0.01637101 0.07383087 0.2126436  0.        ]                                                                                                                                                        | [0.         0.91039924 0.94692984 0.8782822  0.93049806 0.63547194
+        nan 0.64587233 0.81659018 0.1533604  0.95128203 0.25357001
+ 0.         0.5554868  0.         0.59909114 0.         0.
+ 0.81739862 0.14772157 0.70659589 0.64127558 0.03170029        nan
+ 0.05387168 0.38205471 0.34779739 0.         0.9516963  0.85983713
+ 0.97204659 0.02417058 0.18481435 0.30708968 0.        ]                                                                                                                                                        | 42    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea6eb4d5571158b6e8b8e3cff15148862107e45ee792cac4e6351c3c3beaeca
+oid sha256:e24b69bc1bbed3a3eb0890c976bbd4ce42f391af7bd9e94af8a39f930d388ca6
 size 15167588