Training in progress epoch 15

README.md

@@ -15,29 +15,23 @@ 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: 0.3000
-- Validation Loss: 0.4196
-- Validation Mean Iou: 0.3263
-- Validation Mean Accuracy: 0.3833
-- Validation Overall Accuracy: 0.8720
-- Validation Per Category Iou: [0.00000000e+00 8.02547730e-01 8.74182776e-01 6.55641045e-01
- 8.69918767e-01 4.12920686e-01            nan 4.34054109e-01
- 5.54604573e-01 3.14830157e-03 8.29634841e-01 0.00000000e+00
- 0.00000000e+00 0.00000000e+00 0.00000000e+00 4.98619437e-01
- 0.00000000e+00 0.00000000e+00 7.20371619e-01 1.62799781e-02
- 3.73295478e-01 5.20323501e-01 0.00000000e+00            nan
- 3.48000087e-04 2.41829304e-01 1.50045164e-01 0.00000000e+00
- 8.67415087e-01 7.31957881e-01 9.29791719e-01 1.28032094e-01
- 2.77808135e-02 1.25956544e-01 0.00000000e+00]
-- Validation Per Category Accuracy: [0.00000000e+00 9.10809038e-01 9.53614030e-01 6.91330346e-01
- 9.25106631e-01 4.73740259e-01            nan 5.64222160e-01
- 7.49045544e-01 3.42805593e-03 9.38335743e-01 0.00000000e+00
- 0.00000000e+00 0.00000000e+00 0.00000000e+00 5.77484642e-01
- 0.00000000e+00 0.00000000e+00 8.68434883e-01 1.63507406e-02
- 5.76763406e-01 7.07811962e-01 0.00000000e+00            nan
- 3.51671539e-04 3.02660657e-01 1.55815731e-01 0.00000000e+00
- 9.39832349e-01 8.43146236e-01 9.70195728e-01 2.11579170e-01
- 1.06049228e-01 1.61502816e-01 0.00000000e+00]
-- Epoch: 14
+- Validation Loss: 0.4375
+- Validation Mean Iou: 0.3296
+- Validation Mean Accuracy: 0.4004
+- Validation Overall Accuracy: 0.8666
+- Validation Per Category Iou: [0.         0.78266617 0.87516084 0.70472612 0.86490176 0.45228049
+        nan 0.42625351 0.54739354 0.         0.82459025 0.
+ 0.         0.         0.         0.51809119 0.         0.
+ 0.69081711 0.12347692 0.35720113 0.50921058 0.                nan
+ 0.00489936 0.24630062 0.14805039 0.         0.86169724 0.71926146
+ 0.92796331 0.08257639 0.06410606 0.14539247 0.        ]
+- Validation Per Category Accuracy: [0.         0.9075929  0.9264549  0.93787289 0.92618179 0.57743083
+        nan 0.55003982 0.78286607 0.         0.94643176 0.
+ 0.         0.         0.         0.62538921 0.         0.
+ 0.80130182 0.13309691 0.69176706 0.69506169 0.                nan
+ 0.00507726 0.30979772 0.15393969 0.         0.93923901 0.84161243
+ 0.9636732  0.1240378  0.17630371 0.19733096 0.        ]
+- Epoch: 15
 
 ## Model description
 
@@ -252,6 +246,17 @@ The following hyperparameters were used during training:
  3.51671539e-04 3.02660657e-01 1.55815731e-01 0.00000000e+00
  9.39832349e-01 8.43146236e-01 9.70195728e-01 2.11579170e-01
  1.06049228e-01 1.61502816e-01 0.00000000e+00] | 14    |
+| 0.3000     | 0.4375          | 0.3296              | 0.4004                   | 0.8666                      | [0.         0.78266617 0.87516084 0.70472612 0.86490176 0.45228049
+        nan 0.42625351 0.54739354 0.         0.82459025 0.
+ 0.         0.         0.         0.51809119 0.         0.
+ 0.69081711 0.12347692 0.35720113 0.50921058 0.                nan
+ 0.00489936 0.24630062 0.14805039 0.         0.86169724 0.71926146
+ 0.92796331 0.08257639 0.06410606 0.14539247 0.        ]                                                                                                                                                                | [0.         0.9075929  0.9264549  0.93787289 0.92618179 0.57743083
+        nan 0.55003982 0.78286607 0.         0.94643176 0.
+ 0.         0.         0.         0.62538921 0.         0.
+ 0.80130182 0.13309691 0.69176706 0.69506169 0.                nan
+ 0.00507726 0.30979772 0.15393969 0.         0.93923901 0.84161243
+ 0.9636732  0.1240378  0.17630371 0.19733096 0.        ]                                                                                                                                                                | 15    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96cf625dd932a6eb6572da27cb7aacec0f0dcdd0ad676456a42c92de61f9ac29
+oid sha256:a3a40ab56f9b0a4decbe6ed78900324ce960cd12116b6bfb3ed2ed0f8c633fa2
 size 15167588