Training in progress epoch 8

README.md

@@ -15,28 +15,28 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [nvidia/segformer-b3-finetuned-ade-512-512](https://huggingface.co/nvidia/segformer-b3-finetuned-ade-512-512) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.3610
-- Validation Loss: 0.4006
-- Validation Mean Iou: 0.0121
-- Validation Mean Accuracy: 0.0518
-- Validation Overall Accuracy: 0.0421
-- Validation Accuracy Clutter: 0.0300
-- Validation Accuracy Building: 0.0162
-- Validation Accuracy Road: 0.1272
-- Validation Accuracy Static Car: 0.0004
-- Validation Accuracy Tree: 0.1675
-- Validation Accuracy Vegetation: 0.0215
+- Train Loss: 0.3428
+- Validation Loss: 0.3923
+- Validation Mean Iou: 0.0119
+- Validation Mean Accuracy: 0.0465
+- Validation Overall Accuracy: 0.0430
+- Validation Accuracy Clutter: 0.0327
+- Validation Accuracy Building: 0.0166
+- Validation Accuracy Road: 0.0977
+- Validation Accuracy Static Car: 0.0003
+- Validation Accuracy Tree: 0.1670
+- Validation Accuracy Vegetation: 0.0113
 - Validation Accuracy Human: 0.0
 - Validation Accuracy Moving Car: nan
-- Validation Iou Clutter: 0.0207
-- Validation Iou Building: 0.0026
-- Validation Iou Road: 0.0096
-- Validation Iou Static Car: 0.0004
-- Validation Iou Tree: 0.0631
-- Validation Iou Vegetation: 0.0001
+- Validation Iou Clutter: 0.0223
+- Validation Iou Building: 0.0027
+- Validation Iou Road: 0.0078
+- Validation Iou Static Car: 0.0003
+- Validation Iou Tree: 0.0617
+- Validation Iou Vegetation: 0.0000
 - Validation Iou Human: 0.0
 - Validation Iou Moving Car: 0.0
-- Epoch: 7
+- Epoch: 8
 
 ## Model description
 
@@ -70,6 +70,7 @@ The following hyperparameters were used during training:
 | 0.4229     | 0.4257          | 0.0116              | 0.0436                   | 0.0445                      | 0.0515                      | 0.0120                       | 0.1162                   | 0.0002                         | 0.1222                   | 0.0031                         | 0.0                       | nan                            | 0.0344                 | 0.0020                  | 0.0087              | 0.0002                    | 0.0471              | 0.0000                    | 0.0                  | 0.0                       | 5     |
 | 0.3823     | 0.4131          | 0.0127              | 0.0504                   | 0.0455                      | 0.0374                      | 0.0124                       | 0.1251                   | 0.0004                         | 0.1705                   | 0.0072                         | 0.0                       | nan                            | 0.0251                 | 0.0020                  | 0.0098              | 0.0004                    | 0.0639              | 0.0000                    | 0.0                  | 0.0                       | 6     |
 | 0.3610     | 0.4006          | 0.0121              | 0.0518                   | 0.0421                      | 0.0300                      | 0.0162                       | 0.1272                   | 0.0004                         | 0.1675                   | 0.0215                         | 0.0                       | nan                            | 0.0207                 | 0.0026                  | 0.0096              | 0.0004                    | 0.0631              | 0.0001                    | 0.0                  | 0.0                       | 7     |
+| 0.3428     | 0.3923          | 0.0119              | 0.0465                   | 0.0430                      | 0.0327                      | 0.0166                       | 0.0977                   | 0.0003                         | 0.1670                   | 0.0113                         | 0.0                       | nan                            | 0.0223                 | 0.0027                  | 0.0078              | 0.0003                    | 0.0617              | 0.0000                    | 0.0                  | 0.0                       | 8     |
 
 
 ### Framework versions

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baca0df13d40dd62a0ccdb81cd2326e0c1d8091666f96d6b510f5aa74ffeaf99
+oid sha256:4841cfa90da101905ae67a4343abb0ccd786a11c05fa80c755631b89293331d7
 size 189768152