Training in progress epoch 29

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: 0.2245
-- Validation Loss: 0.4819
+- Train Loss: 0.2265
+- Validation Loss: 0.4246
 - Validation Mean Iou: 0.3481
-- Validation Mean Accuracy: 0.4183
-- Validation Overall Accuracy: 0.8677
-- Validation Per Category Iou: [0.         0.74754716 0.87589221 0.7595096  0.75176585 0.46424109
-        nan 0.43492805 0.55661905 0.04973311 0.85506372 0.1407866
- 0.         0.15455217 0.         0.4863142  0.         0.
- 0.72532016 0.16110796 0.37871237 0.54738549 0.                nan
- 0.03596414 0.27015132 0.27383189 0.         0.87155837 0.74696253
- 0.93097913 0.03859201 0.03974808 0.19051036 0.        ]
-- Validation Per Category Accuracy: [0.         0.92496748 0.93198417 0.91066332 0.76595448 0.59939476
-        nan 0.57168392 0.76530022 0.06892197 0.94636898 0.19843316
- 0.         0.30218647 0.         0.5681646  0.         0.
- 0.83417317 0.18737447 0.68308592 0.66512645 0.                nan
- 0.03932127 0.32249168 0.30377988 0.         0.94566641 0.86854326
- 0.97023299 0.04389577 0.11848144 0.26846741 0.        ]
-- Epoch: 28
+- Validation Mean Accuracy: 0.4050
+- Validation Overall Accuracy: 0.8802
+- Validation Per Category Iou: [0.         0.81690969 0.8780207  0.77104697 0.84868605 0.47437381
+        nan 0.4670048  0.56430385 0.0503272  0.85498949 0.10595414
+ 0.         0.11204925 0.         0.53524176 0.         0.
+ 0.74013112 0.04461066 0.39307836 0.51529041 0.                nan
+ 0.01267638 0.28575942 0.24784411 0.         0.87024598 0.76078812
+ 0.93874897 0.00447477 0.03791316 0.15759319 0.        ]
+- Validation Per Category Accuracy: [0.         0.90897891 0.95223635 0.79356326 0.91900275 0.59798835
+        nan 0.59817326 0.81432455 0.05827695 0.94238457 0.11364538
+ 0.         0.13139439 0.         0.65023563 0.         0.
+ 0.88394096 0.04698092 0.61423758 0.59820238 0.                nan
+ 0.01437457 0.35860267 0.28456782 0.         0.93586082 0.86061465
+ 0.96934172 0.00557116 0.10738423 0.20431221 0.        ]
+- Epoch: 29
 
 ## Model description
 
@@ -430,6 +430,17 @@ The following hyperparameters were used during training:
  0.83417317 0.18737447 0.68308592 0.66512645 0.                nan
  0.03932127 0.32249168 0.30377988 0.         0.94566641 0.86854326
  0.97023299 0.04389577 0.11848144 0.26846741 0.        ]                                                                                                                                                        | 28    |
+| 0.2265     | 0.4246          | 0.3481              | 0.4050                   | 0.8802                      | [0.         0.81690969 0.8780207  0.77104697 0.84868605 0.47437381
+        nan 0.4670048  0.56430385 0.0503272  0.85498949 0.10595414
+ 0.         0.11204925 0.         0.53524176 0.         0.
+ 0.74013112 0.04461066 0.39307836 0.51529041 0.                nan
+ 0.01267638 0.28575942 0.24784411 0.         0.87024598 0.76078812
+ 0.93874897 0.00447477 0.03791316 0.15759319 0.        ]                                                                                                                                                        | [0.         0.90897891 0.95223635 0.79356326 0.91900275 0.59798835
+        nan 0.59817326 0.81432455 0.05827695 0.94238457 0.11364538
+ 0.         0.13139439 0.         0.65023563 0.         0.
+ 0.88394096 0.04698092 0.61423758 0.59820238 0.                nan
+ 0.01437457 0.35860267 0.28456782 0.         0.93586082 0.86061465
+ 0.96934172 0.00557116 0.10738423 0.20431221 0.        ]                                                                                                                                                        | 29    |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a690f664ae42c286f59c0a4144cdf5c8348ff852bd36fcde04c96d72b9eb10bf
+oid sha256:e214721ff798b7b3ebde044cebcdad14f8e572068e7da70d03941e9615caf6c9
 size 15167588