Training in progress epoch 9
Browse files- README.md +18 -17
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -15,28 +15,28 @@ probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
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.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss: 0.
|
19 |
-
- Validation Loss: 0.
|
20 |
-
- Validation Mean Iou: 0.
|
21 |
-
- Validation Mean Accuracy: 0.
|
22 |
-
- Validation Overall Accuracy: 0.
|
23 |
-
- Validation Accuracy Clutter: 0.
|
24 |
-
- Validation Accuracy Building: 0.
|
25 |
-
- Validation Accuracy Road: 0.
|
26 |
-
- Validation Accuracy Static Car: 0.
|
27 |
-
- Validation Accuracy Tree: 0.
|
28 |
-
- Validation Accuracy Vegetation: 0.
|
29 |
- Validation Accuracy Human: 0.0
|
30 |
- Validation Accuracy Moving Car: nan
|
31 |
-
- Validation Iou Clutter: 0.
|
32 |
-
- Validation Iou Building: 0.
|
33 |
-
- Validation Iou Road: 0.
|
34 |
-
- Validation Iou Static Car: 0.
|
35 |
-
- Validation Iou Tree: 0.
|
36 |
- Validation Iou Vegetation: 0.0000
|
37 |
- Validation Iou Human: 0.0
|
38 |
- Validation Iou Moving Car: 0.0
|
39 |
-
- Epoch:
|
40 |
|
41 |
## Model description
|
42 |
|
@@ -71,6 +71,7 @@ The following hyperparameters were used during training:
|
|
71 |
| 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 |
|
72 |
| 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 |
|
73 |
| 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 |
|
|
|
74 |
|
75 |
|
76 |
### Framework versions
|
|
|
15 |
|
16 |
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.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 0.3207
|
19 |
+
- Validation Loss: 0.3852
|
20 |
+
- Validation Mean Iou: 0.0093
|
21 |
+
- Validation Mean Accuracy: 0.0378
|
22 |
+
- Validation Overall Accuracy: 0.0336
|
23 |
+
- Validation Accuracy Clutter: 0.0293
|
24 |
+
- Validation Accuracy Building: 0.0228
|
25 |
+
- Validation Accuracy Road: 0.0896
|
26 |
+
- Validation Accuracy Static Car: 0.0006
|
27 |
+
- Validation Accuracy Tree: 0.1118
|
28 |
+
- Validation Accuracy Vegetation: 0.0103
|
29 |
- Validation Accuracy Human: 0.0
|
30 |
- Validation Accuracy Moving Car: nan
|
31 |
+
- Validation Iou Clutter: 0.0199
|
32 |
+
- Validation Iou Building: 0.0037
|
33 |
+
- Validation Iou Road: 0.0072
|
34 |
+
- Validation Iou Static Car: 0.0006
|
35 |
+
- Validation Iou Tree: 0.0427
|
36 |
- Validation Iou Vegetation: 0.0000
|
37 |
- Validation Iou Human: 0.0
|
38 |
- Validation Iou Moving Car: 0.0
|
39 |
+
- Epoch: 9
|
40 |
|
41 |
## Model description
|
42 |
|
|
|
71 |
| 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 |
|
72 |
| 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 |
|
73 |
| 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 |
|
74 |
+
| 0.3207 | 0.3852 | 0.0093 | 0.0378 | 0.0336 | 0.0293 | 0.0228 | 0.0896 | 0.0006 | 0.1118 | 0.0103 | 0.0 | nan | 0.0199 | 0.0037 | 0.0072 | 0.0006 | 0.0427 | 0.0000 | 0.0 | 0.0 | 9 |
|
75 |
|
76 |
|
77 |
### Framework versions
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 189768152
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbded4202668a64fbbb8199232b96452672833a25ad0a8ff2a989d5f76ee7b86
|
3 |
size 189768152
|