Training in progress epoch 39

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: 0.1915
-- Validation Loss: 0.6585
-- Validation Mean Iou: 0.3363
-- Validation Mean Accuracy: 0.4165
-- Validation Overall Accuracy: 0.8541
-- Validation Per Category Iou: [0.         0.73425746 0.86767757 0.51642012 0.54929322 0.33592131
-        nan 0.48682863 0.51510526 0.15484811 0.83659915 0.00656619
- 0.         0.         0.0101791  0.61002433 0.         0.
- 0.72048415 0.13423101 0.4704484  0.36911608 0.02287893        nan
- 0.00175316 0.397269   0.23985463 0.         0.85725197 0.8301346
- 0.91914906 0.0115664  0.20195343 0.29960584 0.        ]
-- Validation Per Category Accuracy: [0.         0.813902   0.96027158 0.62646143 0.65244904 0.456082
-        nan 0.65327663 0.65031732 0.19285309 0.91732039 0.00823723
- 0.                nan 0.01059265 0.72306713 0.         0.
- 0.89001466 0.15570204 0.60888206 0.43505313 0.02292264        nan
- 0.00280348 0.48167913 0.32633914 0.         0.95320389 0.90922448
- 0.96793836 0.01950869 0.51702552 0.37348128 0.        ]
-- Epoch: 38
+- Train Loss: 0.1809
+- Validation Loss: 0.6326
+- Validation Mean Iou: 0.3331
+- Validation Mean Accuracy: 0.4129
+- Validation Overall Accuracy: 0.8566
+- Validation Per Category Iou: [0.         0.75063837 0.86934939 0.50549019 0.55209939 0.34707223
+        nan 0.47793191 0.53247141 0.10026632 0.83361171 0.00349941
+ 0.         0.         0.01418999 0.58381467 0.         0.
+ 0.72707071 0.09868955 0.47826501 0.33864732 0.05377358        nan
+ 0.         0.39034504 0.23355263 0.         0.86185138 0.83043125
+ 0.92062586 0.00839127 0.19885764 0.28062092 0.        ]
+- Validation Per Category Accuracy: [0.         0.8441298  0.95747519 0.60339777 0.66980687 0.43263595
+        nan 0.65140571 0.72588258 0.1153148  0.92360505 0.00462854
+ 0.                nan 0.01448109 0.70674758 0.         0.
+ 0.90597464 0.1045428  0.61409389 0.40161341 0.05444126        nan
+ 0.         0.4704548  0.31055468 0.         0.94873549 0.91742269
+ 0.9695204  0.01226634 0.4993465  0.35417153 0.        ]
+- Epoch: 39
 
 ## Model description
 
@@ -552,6 +552,17 @@ The following hyperparameters were used during training:
  0.89001466 0.15570204 0.60888206 0.43505313 0.02292264        nan
  0.00280348 0.48167913 0.32633914 0.         0.95320389 0.90922448
  0.96793836 0.01950869 0.51702552 0.37348128 0.        ]                                                                                                                                                          | 38    |
+| 0.1809     | 0.6326          | 0.3331              | 0.4129                   | 0.8566                      | [0.         0.75063837 0.86934939 0.50549019 0.55209939 0.34707223
+        nan 0.47793191 0.53247141 0.10026632 0.83361171 0.00349941
+ 0.         0.         0.01418999 0.58381467 0.         0.
+ 0.72707071 0.09868955 0.47826501 0.33864732 0.05377358        nan
+ 0.         0.39034504 0.23355263 0.         0.86185138 0.83043125
+ 0.92062586 0.00839127 0.19885764 0.28062092 0.        ]                                                                                                                                                        | [0.         0.8441298  0.95747519 0.60339777 0.66980687 0.43263595
+        nan 0.65140571 0.72588258 0.1153148  0.92360505 0.00462854
+ 0.                nan 0.01448109 0.70674758 0.         0.
+ 0.90597464 0.1045428  0.61409389 0.40161341 0.05444126        nan
+ 0.         0.4704548  0.31055468 0.         0.94873549 0.91742269
+ 0.9695204  0.01226634 0.4993465  0.35417153 0.        ]                                                                                                                                                        | 39    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfa5f057cb95a8a859f5ea3b60c3cc4d0b6aefe5bc8656665dbaeb75789cd8ac
+oid sha256:40a7a6dfd8ff6ccebf36c89878a5dbb9bc2bbbc890501ad11b7ed987ee6da03d
 size 15167588