Training in progress epoch 19

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: 0.2616
-- Validation Loss: 0.4510
-- Validation Mean Iou: 0.3349
-- Validation Mean Accuracy: 0.4009
-- Validation Overall Accuracy: 0.8726
-- Validation Per Category Iou: [0.         0.79136177 0.88249795 0.78534299 0.86229779 0.47690438
-        nan 0.43122561 0.54187893 0.01320356 0.83487865 0.01648963
- 0.         0.00144389 0.         0.51996092 0.         0.
- 0.70356624 0.09487574 0.37358034 0.43221057 0.                nan
- 0.05030614 0.28552575 0.19602978 0.         0.86214818 0.75003141
- 0.92402054 0.03367055 0.0295635  0.15961857 0.        ]
-- Validation Per Category Accuracy: [0.         0.9308775  0.94322916 0.85211162 0.90509242 0.57554177
-        nan 0.5785717  0.8193957  0.0157871  0.93896272 0.03232844
- 0.         0.00144389 0.         0.6718842  0.         0.
- 0.80146551 0.09782199 0.57800629 0.60986079 0.                nan
- 0.05345407 0.40116852 0.21407727 0.         0.93948742 0.87904777
- 0.97272876 0.03561119 0.11522737 0.2649179  0.        ]
-- Epoch: 18
+- Train Loss: 0.2570
+- Validation Loss: 0.4381
+- Validation Mean Iou: 0.3378
+- Validation Mean Accuracy: 0.4040
+- Validation Overall Accuracy: 0.8691
+- Validation Per Category Iou: [0.         0.78633412 0.8781239  0.70951789 0.85768155 0.49725305
+        nan 0.4385802  0.5419402  0.01325455 0.84049064 0.03469167
+ 0.         0.         0.         0.52032603 0.         0.
+ 0.68820155 0.07929718 0.30712852 0.51640481 0.                nan
+ 0.01769049 0.26803817 0.21887178 0.         0.85998636 0.71539146
+ 0.93235425 0.24885785 0.05621853 0.11969413 0.        ]
+- Validation Per Category Accuracy: [0.         0.91321796 0.93586512 0.7493935  0.91472526 0.63834931
+        nan 0.58292224 0.81417994 0.01497519 0.94252235 0.05394685
+ 0.         0.         0.         0.64331398 0.         0.
+ 0.82029437 0.08115742 0.56811405 0.59644195 0.                nan
+ 0.01995736 0.34179208 0.24586576 0.         0.94413845 0.83304234
+ 0.96807676 0.34801978 0.20125156 0.15898892 0.        ]
+- Epoch: 19
 
 ## Model description
 
@@ -302,6 +302,17 @@ The following hyperparameters were used during training:
  0.80146551 0.09782199 0.57800629 0.60986079 0.                nan
  0.05345407 0.40116852 0.21407727 0.         0.93948742 0.87904777
  0.97272876 0.03561119 0.11522737 0.2649179  0.        ]                                                                                                                                                        | 18    |
+| 0.2570     | 0.4381          | 0.3378              | 0.4040                   | 0.8691                      | [0.         0.78633412 0.8781239  0.70951789 0.85768155 0.49725305
+        nan 0.4385802  0.5419402  0.01325455 0.84049064 0.03469167
+ 0.         0.         0.         0.52032603 0.         0.
+ 0.68820155 0.07929718 0.30712852 0.51640481 0.                nan
+ 0.01769049 0.26803817 0.21887178 0.         0.85998636 0.71539146
+ 0.93235425 0.24885785 0.05621853 0.11969413 0.        ]                                                                                                                                                        | [0.         0.91321796 0.93586512 0.7493935  0.91472526 0.63834931
+        nan 0.58292224 0.81417994 0.01497519 0.94252235 0.05394685
+ 0.         0.         0.         0.64331398 0.         0.
+ 0.82029437 0.08115742 0.56811405 0.59644195 0.                nan
+ 0.01995736 0.34179208 0.24586576 0.         0.94413845 0.83304234
+ 0.96807676 0.34801978 0.20125156 0.15898892 0.        ]                                                                                                                                                        | 19    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d9b70872f985b2ec54d20462c981a6c6caae37234a2e9c01e10af7f5cbc7874
+oid sha256:f50edad3f048cf7b8e7b851a6e0bfd96f035a1125a0fd10bf56b09d7d7d2a1a1
 size 15167588