chribark commited on
Commit
ae36d9c
1 Parent(s): 686af7f

Training in progress epoch 5

Browse files
Files changed (2) hide show
  1. README.md +18 -17
  2. 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: 0.4501
19
- - Validation Loss: 0.4507
20
- - Validation Mean Iou: 0.0107
21
- - Validation Mean Accuracy: 0.0504
22
- - Validation Overall Accuracy: 0.0370
23
- - Validation Accuracy Clutter: 0.0343
24
- - Validation Accuracy Building: 0.0176
25
- - Validation Accuracy Road: 0.1737
26
- - Validation Accuracy Static Car: 0.0001
27
- - Validation Accuracy Tree: 0.1191
28
- - Validation Accuracy Vegetation: 0.0082
29
  - Validation Accuracy Human: 0.0
30
  - Validation Accuracy Moving Car: nan
31
- - Validation Iou Clutter: 0.0228
32
- - Validation Iou Building: 0.0028
33
- - Validation Iou Road: 0.0130
34
- - Validation Iou Static Car: 0.0001
35
- - Validation Iou Tree: 0.0469
36
  - Validation Iou Vegetation: 0.0000
37
  - Validation Iou Human: 0.0
38
  - Validation Iou Moving Car: 0.0
39
- - Epoch: 4
40
 
41
  ## Model description
42
 
@@ -67,6 +67,7 @@ The following hyperparameters were used during training:
67
  | 0.5679 | 0.4969 | 0.0151 | 0.0710 | 0.0516 | 0.0295 | 0.0240 | 0.2164 | 0.0000 | 0.2230 | 0.0041 | 0.0 | nan | 0.0206 | 0.0039 | 0.0151 | 0.0000 | 0.0814 | 0.0000 | 0.0 | 0.0 | 2 |
68
  | 0.5010 | 0.4654 | 0.0135 | 0.0553 | 0.0499 | 0.0437 | 0.0160 | 0.1503 | 0.0000 | 0.1773 | 0.0 | 0.0 | nan | 0.0301 | 0.0026 | 0.0096 | 0.0000 | 0.0660 | 0.0 | 0.0 | 0.0 | 3 |
69
  | 0.4501 | 0.4507 | 0.0107 | 0.0504 | 0.0370 | 0.0343 | 0.0176 | 0.1737 | 0.0001 | 0.1191 | 0.0082 | 0.0 | nan | 0.0228 | 0.0028 | 0.0130 | 0.0001 | 0.0469 | 0.0000 | 0.0 | 0.0 | 4 |
 
70
 
71
 
72
  ### 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: 0.4229
19
+ - Validation Loss: 0.4257
20
+ - Validation Mean Iou: 0.0116
21
+ - Validation Mean Accuracy: 0.0436
22
+ - Validation Overall Accuracy: 0.0445
23
+ - Validation Accuracy Clutter: 0.0515
24
+ - Validation Accuracy Building: 0.0120
25
+ - Validation Accuracy Road: 0.1162
26
+ - Validation Accuracy Static Car: 0.0002
27
+ - Validation Accuracy Tree: 0.1222
28
+ - Validation Accuracy Vegetation: 0.0031
29
  - Validation Accuracy Human: 0.0
30
  - Validation Accuracy Moving Car: nan
31
+ - Validation Iou Clutter: 0.0344
32
+ - Validation Iou Building: 0.0020
33
+ - Validation Iou Road: 0.0087
34
+ - Validation Iou Static Car: 0.0002
35
+ - Validation Iou Tree: 0.0471
36
  - Validation Iou Vegetation: 0.0000
37
  - Validation Iou Human: 0.0
38
  - Validation Iou Moving Car: 0.0
39
+ - Epoch: 5
40
 
41
  ## Model description
42
 
 
67
  | 0.5679 | 0.4969 | 0.0151 | 0.0710 | 0.0516 | 0.0295 | 0.0240 | 0.2164 | 0.0000 | 0.2230 | 0.0041 | 0.0 | nan | 0.0206 | 0.0039 | 0.0151 | 0.0000 | 0.0814 | 0.0000 | 0.0 | 0.0 | 2 |
68
  | 0.5010 | 0.4654 | 0.0135 | 0.0553 | 0.0499 | 0.0437 | 0.0160 | 0.1503 | 0.0000 | 0.1773 | 0.0 | 0.0 | nan | 0.0301 | 0.0026 | 0.0096 | 0.0000 | 0.0660 | 0.0 | 0.0 | 0.0 | 3 |
69
  | 0.4501 | 0.4507 | 0.0107 | 0.0504 | 0.0370 | 0.0343 | 0.0176 | 0.1737 | 0.0001 | 0.1191 | 0.0082 | 0.0 | nan | 0.0228 | 0.0028 | 0.0130 | 0.0001 | 0.0469 | 0.0000 | 0.0 | 0.0 | 4 |
70
+ | 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 |
71
 
72
 
73
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d6da028f3d7765610ab94cdc25e1fc54d7636d4dd9b245234b0f114d0b275f0
3
  size 189768152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b151994ff44ce97b8f411c3321d04a452f6679d0ba847b4adb579b61f7262ce0
3
  size 189768152