Training in progress epoch 41

README.md

@@ -14,24 +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: 0.1724
-- Validation Loss: 0.6214
-- Validation Mean Iou: 0.3480
-- Validation Mean Accuracy: 0.4171
-- Validation Overall Accuracy: 0.8578
-- Validation Per Category Iou: [0.         0.74880719 0.86593712 0.49493695 0.5518544  0.34969174
-        nan 0.49195896 0.52033907 0.11512718 0.82580176 0.00328132
- 0.                nan 0.         0.59486104 0.         0.
- 0.73993215 0.15080459 0.49618358 0.37658279 0.03053435        nan
- 0.         0.3952725  0.24578942 0.         0.85908382 0.81951817
- 0.92798658 0.0131274  0.21907077 0.30066306 0.        ]
-- Validation Per Category Accuracy: [0.         0.83828969 0.95996416 0.58419522 0.67456154 0.43248759
-        nan 0.64852862 0.73357258 0.13170732 0.93534151 0.00384404
- 0.                nan 0.         0.71573769 0.         0.
- 0.88939744 0.16873945 0.67884542 0.42818992 0.03056351        nan
- 0.         0.47664535 0.31638669 0.         0.94469242 0.92889975
- 0.96830227 0.01681728 0.47420376 0.36689909 0.        ]
-- Epoch: 40
+- Train Loss: 0.1700
+- Validation Loss: 0.6443
+- Validation Mean Iou: 0.3403
+- Validation Mean Accuracy: 0.4240
+- Validation Overall Accuracy: 0.8532
+- Validation Per Category Iou: [0.00000000e+00 7.24228056e-01 8.68129666e-01 5.21511493e-01
+ 5.57290409e-01 3.62881751e-01            nan 4.79856526e-01
+ 5.50234987e-01 1.16441909e-01 8.39479458e-01 2.26084595e-02
+ 0.00000000e+00 0.00000000e+00 3.64709037e-02 6.08090063e-01
+ 0.00000000e+00 0.00000000e+00 7.23460392e-01 1.44931232e-01
+ 4.69174359e-01 3.43091068e-01 2.37868696e-02            nan
+ 2.93491819e-04 4.00535432e-01 2.45157323e-01 0.00000000e+00
+ 8.62756146e-01 8.36036309e-01 9.28980262e-01 3.21989502e-02
+ 2.22340672e-01 3.10515477e-01 0.00000000e+00]
+- Validation Per Category Accuracy: [0.00000000e+00 8.16929831e-01 9.38586432e-01 6.15180142e-01
+ 6.92548207e-01 5.76970117e-01            nan 6.54117124e-01
+ 7.45098732e-01 1.27339762e-01 9.24663342e-01 2.61237938e-02
+ 0.00000000e+00            nan 3.64709037e-02 7.78980621e-01
+ 0.00000000e+00 0.00000000e+00 8.97366839e-01 1.56887258e-01
+ 6.13979302e-01 3.85112634e-01 2.38777459e-02            nan
+ 5.60695262e-04 4.70527101e-01 3.03264659e-01 0.00000000e+00
+ 9.54609903e-01 9.12592076e-01 9.66222983e-01 5.07291293e-02
+ 4.94978331e-01 4.04589503e-01 0.00000000e+00]
+- Epoch: 41
 
 ## Model description
 
@@ -574,6 +580,23 @@ The following hyperparameters were used during training:
  0.88939744 0.16873945 0.67884542 0.42818992 0.03056351        nan
  0.         0.47664535 0.31638669 0.         0.94469242 0.92889975
  0.96830227 0.01681728 0.47420376 0.36689909 0.        ]                                                                                                                                                        | 40    |
+| 0.1700     | 0.6443          | 0.3403              | 0.4240                   | 0.8532                      | [0.00000000e+00 7.24228056e-01 8.68129666e-01 5.21511493e-01
+ 5.57290409e-01 3.62881751e-01            nan 4.79856526e-01
+ 5.50234987e-01 1.16441909e-01 8.39479458e-01 2.26084595e-02
+ 0.00000000e+00 0.00000000e+00 3.64709037e-02 6.08090063e-01
+ 0.00000000e+00 0.00000000e+00 7.23460392e-01 1.44931232e-01
+ 4.69174359e-01 3.43091068e-01 2.37868696e-02            nan
+ 2.93491819e-04 4.00535432e-01 2.45157323e-01 0.00000000e+00
+ 8.62756146e-01 8.36036309e-01 9.28980262e-01 3.21989502e-02
+ 2.22340672e-01 3.10515477e-01 0.00000000e+00] | [0.00000000e+00 8.16929831e-01 9.38586432e-01 6.15180142e-01
+ 6.92548207e-01 5.76970117e-01            nan 6.54117124e-01
+ 7.45098732e-01 1.27339762e-01 9.24663342e-01 2.61237938e-02
+ 0.00000000e+00            nan 3.64709037e-02 7.78980621e-01
+ 0.00000000e+00 0.00000000e+00 8.97366839e-01 1.56887258e-01
+ 6.13979302e-01 3.85112634e-01 2.38777459e-02            nan
+ 5.60695262e-04 4.70527101e-01 3.03264659e-01 0.00000000e+00
+ 9.54609903e-01 9.12592076e-01 9.66222983e-01 5.07291293e-02
+ 4.94978331e-01 4.04589503e-01 0.00000000e+00] | 41    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ec8300d7156a8054c0f6c5417e77a1eae0de25907a5fcefb55a779d95172ea8
+oid sha256:0c8b55a02e7fdcec752add77c16b25b204c5944c5ece0b59517bedf0ca111b99
 size 15167588