Hugging Face's logo

mrkprc1
/
segformer-b0-finetuned-sudoku

Image Segmentation
Transformers
Safetensors
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Community
mrkprc1 commited on
Commit
40435e4
•
1 Parent(s): b589cee

End of training

Browse files
Files changed (4) hide show
  1. README.md +16 -18
  2. config.json +1 -3
  3. model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
  license: other
 
3
  tags:
4
  - vision
5
  - image-segmentation
6
  - generated_from_trainer
7
- base_model: nvidia/mit-b0
8
  model-index:
9
  - name: segformer-b0-finetuned-sudoku
10
  results: []
@@ -17,16 +17,14 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the mrkprc1/SudokuBoundaries2 dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.2536
21
- - Mean Iou: 0.1093
22
- - Mean Accuracy: 0.4923
23
- - Overall Accuracy: 0.2822
24
  - Accuracy Unlabelled: nan
25
- - Accuracy Sudoku-boundary: 0.1483
26
- - Accuracy Background: 0.8363
27
  - Iou Unlabelled: 0.0
28
- - Iou Sudoku-boundary: 0.1428
29
- - Iou Background: 0.1853
30
 
31
  ## Model description
32
 
@@ -55,15 +53,15 @@ The following hyperparameters were used during training:
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabelled | Accuracy Sudoku-boundary | Accuracy Background | Iou Unlabelled | Iou Sudoku-boundary | Iou Background |
59
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------:|:------------------------:|:-------------------:|:--------------:|:-------------------:|:--------------:|
60
- | 0.9286 | 6.67 | 20 | 1.2109 | 0.0764 | 0.4936 | 0.2133 | nan | 0.0346 | 0.9525 | 0.0 | 0.0343 | 0.1949 |
61
- | 0.91 | 13.33 | 40 | 1.4893 | 0.0685 | 0.4976 | 0.2013 | nan | 0.0124 | 0.9828 | 0.0 | 0.0123 | 0.1933 |
62
- | 1.11 | 20.0 | 60 | 1.5897 | 0.0694 | 0.4972 | 0.2029 | nan | 0.0152 | 0.9793 | 0.0 | 0.0151 | 0.1932 |
63
- | 0.8025 | 26.67 | 80 | 1.4568 | 0.0829 | 0.4959 | 0.2288 | nan | 0.0585 | 0.9333 | 0.0 | 0.0576 | 0.1910 |
64
- | 0.7468 | 33.33 | 100 | 1.3384 | 0.0890 | 0.4947 | 0.2403 | nan | 0.0781 | 0.9112 | 0.0 | 0.0766 | 0.1903 |
65
- | 0.9548 | 40.0 | 120 | 1.3006 | 0.1586 | 0.4953 | 0.2752 | nan | 0.1348 | 0.8557 | nan | 0.1303 | 0.1869 |
66
- | 0.7295 | 46.67 | 140 | 1.2536 | 0.1093 | 0.4923 | 0.2822 | nan | 0.1483 | 0.8363 | 0.0 | 0.1428 | 0.1853 |
67
 
68
 
69
  ### Framework versions
 
1
  ---
2
  license: other
3
+ base_model: nvidia/mit-b0
4
  tags:
5
  - vision
6
  - image-segmentation
7
  - generated_from_trainer
 
8
  model-index:
9
  - name: segformer-b0-finetuned-sudoku
10
  results: []
 
17
 
18
  This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the mrkprc1/SudokuBoundaries2 dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.8316
21
+ - Mean Iou: 0.0042
22
+ - Mean Accuracy: 0.0084
23
+ - Overall Accuracy: 0.0084
24
  - Accuracy Unlabelled: nan
25
+ - Accuracy Sudoku-boundary: 0.0084
 
26
  - Iou Unlabelled: 0.0
27
+ - Iou Sudoku-boundary: 0.0084
 
28
 
29
  ## Model description
30
 
 
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabelled | Accuracy Sudoku-boundary | Iou Unlabelled | Iou Sudoku-boundary |
57
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------:|:------------------------:|:--------------:|:-------------------:|
58
+ | 0.5058 | 6.67 | 20 | 0.6883 | 0.2729 | 0.5458 | 0.5458 | nan | 0.5458 | 0.0 | 0.5458 |
59
+ | 0.7613 | 13.33 | 40 | 1.2442 | 0.0157 | 0.0315 | 0.0315 | nan | 0.0315 | 0.0 | 0.0315 |
60
+ | 0.58 | 20.0 | 60 | 1.6787 | 0.0052 | 0.0104 | 0.0104 | nan | 0.0104 | 0.0 | 0.0104 |
61
+ | 0.7488 | 26.67 | 80 | 1.7276 | 0.0098 | 0.0197 | 0.0197 | nan | 0.0197 | 0.0 | 0.0197 |
62
+ | 0.6967 | 33.33 | 100 | 1.6509 | 0.0062 | 0.0124 | 0.0124 | nan | 0.0124 | 0.0 | 0.0124 |
63
+ | 0.4491 | 40.0 | 120 | 1.8284 | 0.0078 | 0.0157 | 0.0157 | nan | 0.0157 | 0.0 | 0.0157 |
64
+ | 0.4383 | 46.67 | 140 | 1.8316 | 0.0042 | 0.0084 | 0.0084 | nan | 0.0084 | 0.0 | 0.0084 |
65
 
66
 
67
  ### Framework versions
config.json CHANGED
@@ -29,13 +29,11 @@
29
  ],
30
  "id2label": {
31
  "0": "unlabelled",
32
- "1": "sudoku-boundary",
33
- "2": "background"
34
  },
35
  "image_size": 224,
36
  "initializer_range": 0.02,
37
  "label2id": {
38
- "background": 2,
39
  "sudoku-boundary": 1,
40
  "unlabelled": 0
41
  },
 
29
  ],
30
  "id2label": {
31
  "0": "unlabelled",
32
+ "1": "sudoku-boundary"
 
33
  },
34
  "image_size": 224,
35
  "initializer_range": 0.02,
36
  "label2id": {
 
37
  "sudoku-boundary": 1,
38
  "unlabelled": 0
39
  },
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25a579844ce7e8b856fc22ce23d52f74a3c08020bc8b7dab294566241685d9c8
3
- size 14885804
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e2a7a8a8472f93071f5a240c3a59767650a2be11d39d78581b197088875d02f
3
+ size 14884776
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50fac63cfe278f0c04e71fa0f6771b8faab8db8b67db422078dacef05162df58
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3961d505f254bef3cf604348f6c4d8fcb52c8e7336f5e0e911fc4b617df02dfc
3
  size 4728