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
6668b7a
•
1 Parent(s): c60e0ef

End of training

Browse files
Files changed (3) hide show
  1. README.md +25 -25
  2. model.safetensors +1 -1
  3. 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: []
@@ -17,14 +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: 0.7558
21
- - Mean Iou: 0.2452
22
- - Mean Accuracy: 0.5000
23
- - Overall Accuracy: 0.4904
24
- - Accuracy Unlabelled: 0.9998
25
- - Accuracy Sudoku-boundary: 0.0001
26
- - Iou Unlabelled: 0.4904
27
- - Iou Sudoku-boundary: 0.0001
28
 
29
  ## Model description
30
 
@@ -43,7 +43,7 @@ More information needed
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
- - learning_rate: 0.0006
47
  - train_batch_size: 2
48
  - eval_batch_size: 2
49
  - seed: 42
@@ -55,21 +55,21 @@ The following hyperparameters were used during training:
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
- | 0.7903 | 3.33 | 20 | 1.0683 | 0.2548 | 0.5 | 0.5096 | 0.0 | 1.0 | 0.0 | 0.5096 |
59
- | 1.2926 | 6.67 | 40 | 0.7308 | 0.3256 | 0.4988 | 0.4963 | 0.6307 | 0.3669 | 0.3804 | 0.2707 |
60
- | 0.475 | 10.0 | 60 | 1.0960 | 0.2452 | 0.5 | 0.4904 | 1.0 | 0.0 | 0.4904 | 0.0 |
61
- | 0.542 | 13.33 | 80 | 0.7003 | 0.3276 | 0.4935 | 0.4938 | 0.4741 | 0.5128 | 0.3148 | 0.3405 |
62
- | 1.0182 | 16.67 | 100 | 0.7115 | 0.3075 | 0.4824 | 0.4792 | 0.6510 | 0.3139 | 0.3801 | 0.2350 |
63
- | 0.7504 | 20.0 | 120 | 0.9472 | 0.2452 | 0.5 | 0.4904 | 1.0 | 0.0 | 0.4904 | 0.0 |
64
- | 0.3973 | 23.33 | 140 | 0.7083 | 0.2548 | 0.4949 | 0.4861 | 0.9559 | 0.0339 | 0.4771 | 0.0325 |
65
- | 0.4065 | 26.67 | 160 | 0.7714 | 0.2452 | 0.5 | 0.4904 | 1.0 | 0.0 | 0.4904 | 0.0 |
66
- | 0.3868 | 30.0 | 180 | 0.7314 | 0.2456 | 0.4980 | 0.4886 | 0.9923 | 0.0037 | 0.4876 | 0.0037 |
67
- | 0.2217 | 33.33 | 200 | 0.8411 | 0.2452 | 0.5 | 0.4904 | 1.0 | 0.0 | 0.4904 | 0.0 |
68
- | 0.3505 | 36.67 | 220 | 1.1413 | 0.2452 | 0.5 | 0.4904 | 1.0 | 0.0 | 0.4904 | 0.0 |
69
- | 0.2739 | 40.0 | 240 | 0.6943 | 0.3064 | 0.5081 | 0.5021 | 0.8231 | 0.1931 | 0.4477 | 0.1650 |
70
- | 0.5896 | 43.33 | 260 | 0.6978 | 0.2639 | 0.5025 | 0.4939 | 0.9562 | 0.0489 | 0.4809 | 0.0469 |
71
- | 0.3411 | 46.67 | 280 | 0.7024 | 0.2580 | 0.5002 | 0.4913 | 0.9656 | 0.0349 | 0.4821 | 0.0338 |
72
- | 0.5801 | 50.0 | 300 | 0.7558 | 0.2452 | 0.5000 | 0.4904 | 0.9998 | 0.0001 | 0.4904 | 0.0001 |
73
 
74
 
75
  ### 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: 0.7037
21
+ - Mean Iou: 0.2505
22
+ - Mean Accuracy: 0.4978
23
+ - Overall Accuracy: 0.4887
24
+ - Accuracy Unlabelled: 0.9784
25
+ - Accuracy Sudoku-boundary: 0.0173
26
+ - Iou Unlabelled: 0.4841
27
+ - Iou Sudoku-boundary: 0.0169
28
 
29
  ## Model description
30
 
 
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
+ - learning_rate: 6e-06
47
  - train_batch_size: 2
48
  - eval_batch_size: 2
49
  - seed: 42
 
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
+ | 0.5388 | 3.33 | 20 | 0.6914 | 0.3096 | 0.5259 | 0.5336 | 0.1248 | 0.9270 | 0.1160 | 0.5031 |
59
+ | 1.1103 | 6.67 | 40 | 0.6909 | 0.3320 | 0.5329 | 0.5393 | 0.1982 | 0.8677 | 0.1742 | 0.4897 |
60
+ | 0.2978 | 10.0 | 60 | 0.6971 | 0.2671 | 0.4987 | 0.4904 | 0.9321 | 0.0653 | 0.4729 | 0.0613 |
61
+ | 0.4739 | 13.33 | 80 | 0.6927 | 0.3257 | 0.5147 | 0.5101 | 0.7585 | 0.2709 | 0.4316 | 0.2198 |
62
+ | 0.562 | 16.67 | 100 | 0.6974 | 0.2695 | 0.4975 | 0.4894 | 0.9194 | 0.0756 | 0.4690 | 0.0701 |
63
+ | 0.8487 | 20.0 | 120 | 0.6944 | 0.2945 | 0.5041 | 0.4974 | 0.8555 | 0.1527 | 0.4550 | 0.1341 |
64
+ | 0.3803 | 23.33 | 140 | 0.6953 | 0.2906 | 0.5054 | 0.4983 | 0.8768 | 0.1339 | 0.4615 | 0.1197 |
65
+ | 0.4106 | 26.67 | 160 | 0.7065 | 0.2482 | 0.4999 | 0.4905 | 0.9917 | 0.0081 | 0.4884 | 0.0080 |
66
+ | 0.4016 | 30.0 | 180 | 0.7057 | 0.2507 | 0.4988 | 0.4896 | 0.9811 | 0.0165 | 0.4853 | 0.0162 |
67
+ | 0.3198 | 33.33 | 200 | 0.7114 | 0.2476 | 0.4987 | 0.4893 | 0.9896 | 0.0079 | 0.4873 | 0.0078 |
68
+ | 0.374 | 36.67 | 220 | 0.7286 | 0.2452 | 0.4997 | 0.4901 | 0.9989 | 0.0004 | 0.4900 | 0.0004 |
69
+ | 0.2486 | 40.0 | 240 | 0.6986 | 0.2751 | 0.4974 | 0.4897 | 0.9002 | 0.0946 | 0.4639 | 0.0863 |
70
+ | 0.513 | 43.33 | 260 | 0.6917 | 0.3192 | 0.5139 | 0.5086 | 0.7909 | 0.2369 | 0.4411 | 0.1972 |
71
+ | 0.3839 | 46.67 | 280 | 0.6934 | 0.3002 | 0.5079 | 0.5013 | 0.8495 | 0.1662 | 0.4552 | 0.1452 |
72
+ | 0.6526 | 50.0 | 300 | 0.7037 | 0.2505 | 0.4978 | 0.4887 | 0.9784 | 0.0173 | 0.4841 | 0.0169 |
73
 
74
 
75
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2c55278918cf4b96d520ca0e1581ae817af9b5884152f20c65764567ff877f8
3
  size 14884776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66999c78837cad51e508679638146fe915de8aa3f52bd0b171ccdf9f0d024fb6
3
  size 14884776
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e920496db3ee24aae9b482fa3ab20b5a88c6465c4b86c148f62bb9cd7cc491a4
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c25e77a27bd0ac8d329722c4685e8366e9d23318824e73a7a94fecab7f8bab3b
3
  size 4728