Training in progress epoch 6

README.md

@@ -14,30 +14,30 @@ 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: 0.5256
-- Validation Loss: 0.4741
-- Validation Mean Iou: 0.3045
-- Validation Mean Accuracy: 0.3598
-- Validation Overall Accuracy: 0.8558
-- Validation Per Category Iou: [0.00000000e+00 7.50159008e-01 8.53654462e-01 6.44928131e-01
- 7.90455244e-01 4.33599913e-01            nan 3.33472954e-01
- 4.74502513e-01 0.00000000e+00 8.01366017e-01 0.00000000e+00
- 0.00000000e+00 0.00000000e+00 0.00000000e+00 4.67653814e-01
- 0.00000000e+00 0.00000000e+00 7.27412479e-01 0.00000000e+00
- 4.18946113e-01 5.04714837e-01 0.00000000e+00            nan
- 0.00000000e+00 2.00373855e-01 0.00000000e+00 0.00000000e+00
- 8.50200795e-01 7.41636173e-01 9.08320534e-01 2.77259907e-04
- 0.00000000e+00 1.45430716e-01 0.00000000e+00]
-- Validation Per Category Accuracy: [0.00000000e+00 8.86487233e-01 9.05201886e-01 7.23139265e-01
- 8.91929263e-01 7.26675641e-01            nan 4.36386295e-01
- 6.64378543e-01 0.00000000e+00 8.89056843e-01 0.00000000e+00
- 0.00000000e+00 0.00000000e+00 0.00000000e+00 5.65450644e-01
- 0.00000000e+00 0.00000000e+00 9.27446136e-01 0.00000000e+00
- 5.36031025e-01 5.84198054e-01 0.00000000e+00            nan
- 0.00000000e+00 2.42514534e-01 0.00000000e+00 0.00000000e+00
- 9.31954754e-01 8.26849708e-01 9.59880377e-01 2.79039335e-04
- 0.00000000e+00 1.77106051e-01 0.00000000e+00]
-- Epoch: 5
+- Train Loss: 0.4761
+- Validation Loss: 0.4922
+- Validation Mean Iou: 0.3036
+- Validation Mean Accuracy: 0.3754
+- Validation Overall Accuracy: 0.8517
+- Validation Per Category Iou: [0.00000000e+00 7.18490241e-01 8.54701589e-01 5.90903088e-01
+ 8.21902743e-01 4.76229883e-01            nan 3.32447673e-01
+ 4.80642540e-01 0.00000000e+00 8.02904449e-01 0.00000000e+00
+ 0.00000000e+00 0.00000000e+00 0.00000000e+00 4.73285636e-01
+ 0.00000000e+00 0.00000000e+00 7.16608930e-01 0.00000000e+00
+ 3.16598081e-01 5.12540924e-01 0.00000000e+00            nan
+ 0.00000000e+00 2.27702968e-01 0.00000000e+00 0.00000000e+00
+ 8.51831675e-01 7.39827330e-01 9.07152231e-01 5.59070700e-04
+ 3.70370370e-02 1.56538301e-01 0.00000000e+00]
+- Validation Per Category Accuracy: [0.00000000e+00 9.20834531e-01 8.92075255e-01 7.48664032e-01
+ 9.03709011e-01 7.40703529e-01            nan 4.40828188e-01
+ 7.92719139e-01 0.00000000e+00 9.21593374e-01 0.00000000e+00
+ 0.00000000e+00 0.00000000e+00 0.00000000e+00 6.90292855e-01
+ 0.00000000e+00 0.00000000e+00 8.42229041e-01 0.00000000e+00
+ 4.75170857e-01 6.72591473e-01 0.00000000e+00            nan
+ 0.00000000e+00 2.94713089e-01 0.00000000e+00 0.00000000e+00
+ 9.26034809e-01 8.39522012e-01 9.66679296e-01 6.06188900e-04
+ 1.12807676e-01 2.07280968e-01 0.00000000e+00]
+- Epoch: 6
 
 ## Model description
 
@@ -135,6 +135,23 @@ The following hyperparameters were used during training:
  0.00000000e+00 2.42514534e-01 0.00000000e+00 0.00000000e+00
  9.31954754e-01 8.26849708e-01 9.59880377e-01 2.79039335e-04
  0.00000000e+00 1.77106051e-01 0.00000000e+00] | 5     |
+| 0.4761     | 0.4922          | 0.3036              | 0.3754                   | 0.8517                      | [0.00000000e+00 7.18490241e-01 8.54701589e-01 5.90903088e-01
+ 8.21902743e-01 4.76229883e-01            nan 3.32447673e-01
+ 4.80642540e-01 0.00000000e+00 8.02904449e-01 0.00000000e+00
+ 0.00000000e+00 0.00000000e+00 0.00000000e+00 4.73285636e-01
+ 0.00000000e+00 0.00000000e+00 7.16608930e-01 0.00000000e+00
+ 3.16598081e-01 5.12540924e-01 0.00000000e+00            nan
+ 0.00000000e+00 2.27702968e-01 0.00000000e+00 0.00000000e+00
+ 8.51831675e-01 7.39827330e-01 9.07152231e-01 5.59070700e-04
+ 3.70370370e-02 1.56538301e-01 0.00000000e+00] | [0.00000000e+00 9.20834531e-01 8.92075255e-01 7.48664032e-01
+ 9.03709011e-01 7.40703529e-01            nan 4.40828188e-01
+ 7.92719139e-01 0.00000000e+00 9.21593374e-01 0.00000000e+00
+ 0.00000000e+00 0.00000000e+00 0.00000000e+00 6.90292855e-01
+ 0.00000000e+00 0.00000000e+00 8.42229041e-01 0.00000000e+00
+ 4.75170857e-01 6.72591473e-01 0.00000000e+00            nan
+ 0.00000000e+00 2.94713089e-01 0.00000000e+00 0.00000000e+00
+ 9.26034809e-01 8.39522012e-01 9.66679296e-01 6.06188900e-04
+ 1.12807676e-01 2.07280968e-01 0.00000000e+00] | 6     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:290c60be67641026a83a4db3209f088433f519c85b0838182118a1e7448c614f
+oid sha256:a7611a8ad9a4c734af44fbf7c9b169a72fea76066d2bd008d40ef7098c10a1fc
 size 15167588