Training in progress epoch 38

README.md

@@ -14,30 +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: 0.1828
-- Validation Loss: 0.4314
-- Validation Mean Iou: 0.3540
-- Validation Mean Accuracy: 0.4137
-- Validation Overall Accuracy: 0.8837
-- Validation Per Category Iou: [0.00000000e+00 8.08817183e-01 8.86533437e-01 8.29367464e-01
- 8.66921982e-01 5.02412424e-01            nan 4.88635866e-01
- 5.60640323e-01 8.39031061e-02 8.56029524e-01 1.48001648e-01
- 0.00000000e+00 2.88729590e-02 0.00000000e+00 5.27888135e-01
- 0.00000000e+00 0.00000000e+00 7.40145106e-01 5.94355934e-02
- 3.83677842e-01 5.51371204e-01 0.00000000e+00            nan
- 2.54484244e-02 2.99810052e-01 2.57164681e-01 0.00000000e+00
- 8.66461858e-01 7.59758000e-01 9.39794819e-01 8.55545803e-03
- 2.93707321e-04 2.00986041e-01 0.00000000e+00]
-- Validation Per Category Accuracy: [0.00000000e+00 9.20986697e-01 9.42897048e-01 8.79794678e-01
- 9.16674152e-01 6.25797872e-01            nan 6.53392696e-01
- 7.86385022e-01 1.54984213e-01 9.51069237e-01 1.78103927e-01
- 0.00000000e+00 2.99092409e-02 0.00000000e+00 6.40158209e-01
- 0.00000000e+00 0.00000000e+00 8.70579667e-01 6.04130053e-02
- 5.57868972e-01 7.35243038e-01 0.00000000e+00            nan
- 3.09031365e-02 3.74579444e-01 2.92419400e-01 0.00000000e+00
- 9.45130703e-01 8.41614926e-01 9.69892426e-01 8.91001463e-03
- 6.67501043e-04 2.82612669e-01 0.00000000e+00]
-- Epoch: 37
+- Train Loss: 0.1824
+- Validation Loss: 0.4277
+- Validation Mean Iou: 0.3516
+- Validation Mean Accuracy: 0.4128
+- Validation Overall Accuracy: 0.8808
+- Validation Per Category Iou: [0.         0.80850849 0.8835188  0.81832156 0.87084804 0.52909381
+        nan 0.48544633 0.57416469 0.06544565 0.86014741 0.09572506
+ 0.         0.04364361 0.         0.53546177 0.         0.
+ 0.72880369 0.07815572 0.36619794 0.45105441 0.                nan
+ 0.02904442 0.31295304 0.268757   0.         0.87009835 0.77016379
+ 0.93780115 0.02053909 0.00775031 0.19176263 0.        ]
+- Validation Per Category Accuracy: [0.         0.93462002 0.91830503 0.88981486 0.94415116 0.74919228
+        nan 0.63542345 0.80433651 0.09896256 0.95110348 0.11324871
+ 0.         0.04971122 0.         0.61501725 0.         0.
+ 0.85270915 0.08732425 0.54361868 0.58993825 0.                nan
+ 0.03250764 0.39146001 0.30016676 0.         0.9446708  0.87850239
+ 0.97614375 0.02966477 0.01535252 0.27686197 0.        ]
+- Epoch: 38
 
 ## Model description
 
@@ -547,6 +541,17 @@ The following hyperparameters were used during training:
  3.09031365e-02 3.74579444e-01 2.92419400e-01 0.00000000e+00
  9.45130703e-01 8.41614926e-01 9.69892426e-01 8.91001463e-03
  6.67501043e-04 2.82612669e-01 0.00000000e+00] | 37    |
+| 0.1824     | 0.4277          | 0.3516              | 0.4128                   | 0.8808                      | [0.         0.80850849 0.8835188  0.81832156 0.87084804 0.52909381
+        nan 0.48544633 0.57416469 0.06544565 0.86014741 0.09572506
+ 0.         0.04364361 0.         0.53546177 0.         0.
+ 0.72880369 0.07815572 0.36619794 0.45105441 0.                nan
+ 0.02904442 0.31295304 0.268757   0.         0.87009835 0.77016379
+ 0.93780115 0.02053909 0.00775031 0.19176263 0.        ]                                                                                                                                                        | [0.         0.93462002 0.91830503 0.88981486 0.94415116 0.74919228
+        nan 0.63542345 0.80433651 0.09896256 0.95110348 0.11324871
+ 0.         0.04971122 0.         0.61501725 0.         0.
+ 0.85270915 0.08732425 0.54361868 0.58993825 0.                nan
+ 0.03250764 0.39146001 0.30016676 0.         0.9446708  0.87850239
+ 0.97614375 0.02966477 0.01535252 0.27686197 0.        ]                                                                                                                                                        | 38    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78c0a6cd2be05c9498119809424bc0714872bd3b619fa6c324e4031bc56768ae
+oid sha256:dffdb1fc02f63a0b503eaa30aba67b2d24111e5fd2bc5e351ddce90aef902ecd
 size 15167588