Hugging Face's logo

DiTo97
/
binarization-segformer-b3

Image Segmentation
Transformers
PyTorch
Safetensors
segformer
Generated from Trainer
document-image-binarization
Inference Endpoints
Model card Files Community
2
DiTo97 commited on
Commit
84e5ba1
•
1 Parent(s): 172f844

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +77 -75
README.md CHANGED
@@ -1,13 +1,12 @@
1
  ---
2
- license: openrail
 
3
  tags:
4
- - document-image-binarization
5
- - image-segmentation
6
  - generated_from_trainer
7
  model-index:
8
  - name: binarization-segformer-b3
9
  results: []
10
- pipeline_tag: image-segmentation
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,29 +14,17 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # binarization-segformer-b3
17
 
18
- This model is a fine-tuned version of [nvidia/segformer-b3](https://huggingface.co/nvidia/segformer-b3-finetuned-cityscapes-1024-1024)
19
- on the same ensemble of 13 datasets as the [SauvolaNet](https://arxiv.org/pdf/2105.05521.pdf) work publicly available
20
- in their GitHub [repository](https://github.com/Leedeng/SauvolaNet#datasets).
21
-
22
- It achieves the following results on the evaluation set on DIBCO metrics:
23
- - loss: 0.1017
24
- - F-measure: 0.9776
25
- - pseudo F-measure: 0.9531
26
- - PSNR: 14.5040
27
- - DRD: 5.3749
28
-
29
- with PSNR the peak signal-to-noise ratio and DRD the distance reciprocal distortion.
30
-
31
- For more information on the above DIBCO metrics, see the 2017 introductory [paper](https://ieeexplore.ieee.org/document/8270159).
32
-
33
- **Warning:** This model only accepts images with a resolution of 640 due to GPU compute constraints on Colab free tier during training.
34
 
35
  ## Model description
36
 
37
- This model is part of on-going research on pure semantic segmentation models as a formulation of document image binarization (DIBCO).
38
- This is in contrast to the late trend of adapting classic binarization algorithms with neural networks,
39
- such as [DeepOtsu](https://arxiv.org/abs/1901.06081) or the aforementioned SauvolaNet work
40
- as extensions of the classical Otsu's method and Sauvola thresholding algorithm, respectively.
41
 
42
  ## Intended uses & limitations
43
 
@@ -65,58 +52,73 @@ The following hyperparameters were used during training:
65
 
66
  ### Training results
67
 
68
- | training loss | epoch | step | validation loss | F-measure | pseudo F-measure | PSNR | DRD |
69
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:-------:|:--------:|
70
- | 0.6667 | 1.03 | 10 | 0.6683 | 0.7127 | 0.6831 | 4.8248 | 107.2894 |
71
- | 0.6371 | 2.05 | 20 | 0.6390 | 0.8173 | 0.7360 | 6.1079 | 69.7770 |
72
- | 0.587 | 3.08 | 30 | 0.5652 | 0.8934 | 0.8187 | 7.9143 | 40.5464 |
73
- | 0.5288 | 4.1 | 40 | 0.4926 | 0.9240 | 0.8554 | 9.2247 | 27.4220 |
74
- | 0.4601 | 5.13 | 50 | 0.4244 | 0.9490 | 0.8944 | 10.8830 | 16.8051 |
75
- | 0.3864 | 6.15 | 60 | 0.3446 | 0.9638 | 0.9218 | 12.3460 | 10.6997 |
76
- | 0.3331 | 7.18 | 70 | 0.3055 | 0.9693 | 0.9317 | 13.0531 | 8.5298 |
77
- | 0.2821 | 8.21 | 80 | 0.2512 | 0.9736 | 0.9427 | 13.6929 | 6.8343 |
78
- | 0.2392 | 9.23 | 90 | 0.2112 | 0.9744 | 0.9462 | 13.8825 | 6.4094 |
79
- | 0.2126 | 10.26 | 100 | 0.1948 | 0.9743 | 0.9433 | 13.8424 | 6.5637 |
80
- | 0.1889 | 11.28 | 110 | 0.1710 | 0.9749 | 0.9499 | 13.9784 | 6.1757 |
81
- | 0.1662 | 12.31 | 120 | 0.1604 | 0.9753 | 0.9495 | 14.0450 | 6.0929 |
82
- | 0.1506 | 13.33 | 130 | 0.1451 | 0.9750 | 0.9550 | 14.0028 | 6.1031 |
83
- | 0.1359 | 14.36 | 140 | 0.1362 | 0.9759 | 0.9501 | 14.1383 | 5.9699 |
84
- | 0.1321 | 15.38 | 150 | 0.1351 | 0.9761 | 0.9485 | 14.1907 | 5.9045 |
85
- | 0.1283 | 16.41 | 160 | 0.1266 | 0.9758 | 0.9541 | 14.1515 | 5.8287 |
86
- | 0.1198 | 17.44 | 170 | 0.1232 | 0.9763 | 0.9535 | 14.2411 | 5.7300 |
87
- | 0.1151 | 18.46 | 180 | 0.1232 | 0.9765 | 0.9482 | 14.2788 | 5.8266 |
88
- | 0.1146 | 19.49 | 190 | 0.1183 | 0.9764 | 0.9530 | 14.2363 | 5.7922 |
89
- | 0.1027 | 20.51 | 200 | 0.1162 | 0.9765 | 0.9535 | 14.2867 | 5.6246 |
90
- | 0.1051 | 21.54 | 210 | 0.1146 | 0.9766 | 0.9551 | 14.2963 | 5.6159 |
91
- | 0.1095 | 22.56 | 220 | 0.1159 | 0.9767 | 0.9497 | 14.3153 | 5.8966 |
92
- | 0.1076 | 23.59 | 230 | 0.1106 | 0.9768 | 0.9533 | 14.3267 | 5.6436 |
93
- | 0.1006 | 24.62 | 240 | 0.1113 | 0.9769 | 0.9483 | 14.3683 | 5.6679 |
94
- | 0.1077 | 25.64 | 250 | 0.1086 | 0.9770 | 0.9544 | 14.3843 | 5.4949 |
95
- | 0.0966 | 26.67 | 260 | 0.1077 | 0.9770 | 0.9553 | 14.3660 | 5.5337 |
96
- | 0.0958 | 27.69 | 270 | 0.1071 | 0.9773 | 0.9529 | 14.4405 | 5.4582 |
97
- | 0.0984 | 28.72 | 280 | 0.1055 | 0.9772 | 0.9536 | 14.4405 | 5.4365 |
98
- | 0.0936 | 29.74 | 290 | 0.1056 | 0.9774 | 0.9528 | 14.4634 | 5.4066 |
99
- | 0.0958 | 30.77 | 300 | 0.1049 | 0.9772 | 0.9544 | 14.4138 | 5.4854 |
100
- | 0.0896 | 31.79 | 310 | 0.1043 | 0.9774 | 0.9533 | 14.4593 | 5.4351 |
101
- | 0.0973 | 32.82 | 320 | 0.1035 | 0.9774 | 0.9528 | 14.4633 | 5.4430 |
102
- | 0.0943 | 33.85 | 330 | 0.1033 | 0.9775 | 0.9527 | 14.4809 | 5.4193 |
103
- | 0.0956 | 34.87 | 340 | 0.1026 | 0.9774 | 0.9543 | 14.4576 | 5.4070 |
104
- | 0.0936 | 35.9 | 350 | 0.1031 | 0.9775 | 0.9531 | 14.4827 | 5.4137 |
105
- | 0.0937 | 36.92 | 360 | 0.1028 | 0.9773 | 0.9551 | 14.4420 | 5.4084 |
106
- | 0.0952 | 37.95 | 370 | 0.1023 | 0.9775 | 0.9541 | 14.4809 | 5.3769 |
107
- | 0.0952 | 38.97 | 380 | 0.1023 | 0.9776 | 0.9525 | 14.5086 | 5.3839 |
108
- | 0.0948 | 40.0 | 390 | 0.1020 | 0.9774 | 0.9546 | 14.4667 | 5.3800 |
109
- | 0.0931 | 41.03 | 400 | 0.1020 | 0.9776 | 0.9534 | 14.5043 | 5.3728 |
110
- | 0.0906 | 42.05 | 410 | 0.1023 | 0.9774 | 0.9544 | 14.4771 | 5.3773 |
111
- | 0.0974 | 43.08 | 420 | 0.1019 | 0.9776 | 0.9536 | 14.5024 | 5.3718 |
112
- | 0.0908 | 44.1 | 430 | 0.1025 | 0.9776 | 0.9536 | 14.4995 | 5.3730 |
113
- | 0.0935 | 45.13 | 440 | 0.1024 | 0.9775 | 0.9537 | 14.4978 | 5.3715 |
114
- | 0.0927 | 46.15 | 450 | 0.1017 | 0.9776 | 0.9531 | 14.5040 | 5.3749 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
115
 
116
 
117
  ### Framework versions
118
 
119
- - Transformers 4.27.4
120
- - Pytorch 2.0.0+cu118
121
- - Datasets 2.11.0
122
- - Tokenizers 0.13.3
 
1
  ---
2
+ license: other
3
+ base_model: nvidia/segformer-b3-finetuned-cityscapes-1024-1024
4
  tags:
5
+ - document-image-binarizationimage-segmentation
 
6
  - generated_from_trainer
7
  model-index:
8
  - name: binarization-segformer-b3
9
  results: []
 
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
14
 
15
  # binarization-segformer-b3
16
 
17
+ This model is a fine-tuned version of [nvidia/segformer-b3-finetuned-cityscapes-1024-1024](https://huggingface.co/nvidia/segformer-b3-finetuned-cityscapes-1024-1024) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0743
20
+ - Drd: 5.9548
21
+ - F-measure: 0.9840
22
+ - Pseudo-f-measure: 0.9740
23
+ - Psnr: 16.0119
 
 
 
 
 
 
 
 
 
24
 
25
  ## Model description
26
 
27
+ More information needed
 
 
 
28
 
29
  ## Intended uses & limitations
30
 
 
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Drd | F-measure | Pseudo-f-measure | Psnr |
56
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:----------------:|:-------:|
57
+ | 0.6983 | 0.26 | 10 | 0.7079 | 199.5096 | 0.5945 | 0.5801 | 3.4552 |
58
+ | 0.6657 | 0.52 | 20 | 0.6755 | 149.2346 | 0.7006 | 0.6165 | 4.6752 |
59
+ | 0.6145 | 0.77 | 30 | 0.6433 | 109.7298 | 0.7831 | 0.6520 | 5.5489 |
60
+ | 0.5553 | 1.03 | 40 | 0.5443 | 53.7149 | 0.8952 | 0.8000 | 8.1736 |
61
+ | 0.4627 | 1.29 | 50 | 0.4896 | 32.7649 | 0.9321 | 0.8603 | 9.8706 |
62
+ | 0.3969 | 1.55 | 60 | 0.4327 | 21.5508 | 0.9526 | 0.8985 | 11.3400 |
63
+ | 0.3414 | 1.81 | 70 | 0.3002 | 11.0094 | 0.9732 | 0.9462 | 13.5901 |
64
+ | 0.2898 | 2.06 | 80 | 0.2839 | 10.1064 | 0.9748 | 0.9563 | 13.9796 |
65
+ | 0.2292 | 2.32 | 90 | 0.2427 | 9.4437 | 0.9761 | 0.9584 | 14.2161 |
66
+ | 0.2153 | 2.58 | 100 | 0.2095 | 8.8696 | 0.9771 | 0.9621 | 14.4319 |
67
+ | 0.1767 | 2.84 | 110 | 0.1916 | 8.6152 | 0.9776 | 0.9646 | 14.5528 |
68
+ | 0.1509 | 3.1 | 120 | 0.1704 | 8.0761 | 0.9791 | 0.9632 | 14.7961 |
69
+ | 0.1265 | 3.35 | 130 | 0.1561 | 8.5627 | 0.9784 | 0.9655 | 14.7400 |
70
+ | 0.132 | 3.61 | 140 | 0.1318 | 8.1849 | 0.9788 | 0.9670 | 14.8469 |
71
+ | 0.1115 | 3.87 | 150 | 0.1317 | 7.8438 | 0.9790 | 0.9657 | 14.9072 |
72
+ | 0.0983 | 4.13 | 160 | 0.1273 | 7.9405 | 0.9791 | 0.9673 | 14.9701 |
73
+ | 0.1001 | 4.39 | 170 | 0.1234 | 8.4132 | 0.9788 | 0.9691 | 14.8573 |
74
+ | 0.0862 | 4.65 | 180 | 0.1147 | 8.0838 | 0.9797 | 0.9678 | 15.0433 |
75
+ | 0.0713 | 4.9 | 190 | 0.1134 | 7.6027 | 0.9806 | 0.9687 | 15.2235 |
76
+ | 0.0905 | 5.16 | 200 | 0.1061 | 7.2973 | 0.9803 | 0.9699 | 15.1646 |
77
+ | 0.0902 | 5.42 | 210 | 0.1061 | 8.4049 | 0.9787 | 0.9699 | 14.8460 |
78
+ | 0.0759 | 5.68 | 220 | 0.1062 | 7.7147 | 0.9809 | 0.9695 | 15.2426 |
79
+ | 0.0638 | 5.94 | 230 | 0.1019 | 7.7449 | 0.9806 | 0.9695 | 15.2195 |
80
+ | 0.0852 | 6.19 | 240 | 0.0962 | 7.0221 | 0.9817 | 0.9693 | 15.4730 |
81
+ | 0.0677 | 6.45 | 250 | 0.0961 | 7.2520 | 0.9814 | 0.9710 | 15.3878 |
82
+ | 0.0668 | 6.71 | 260 | 0.0972 | 6.6658 | 0.9823 | 0.9689 | 15.6106 |
83
+ | 0.0701 | 6.97 | 270 | 0.0909 | 6.9454 | 0.9820 | 0.9713 | 15.5458 |
84
+ | 0.0567 | 7.23 | 280 | 0.0925 | 6.5498 | 0.9824 | 0.9718 | 15.5965 |
85
+ | 0.0624 | 7.48 | 290 | 0.0899 | 7.3125 | 0.9813 | 0.9717 | 15.3255 |
86
+ | 0.0649 | 7.74 | 300 | 0.0932 | 7.4915 | 0.9816 | 0.9684 | 15.5666 |
87
+ | 0.0524 | 8.0 | 310 | 0.0905 | 7.1666 | 0.9815 | 0.9711 | 15.4526 |
88
+ | 0.0693 | 8.26 | 320 | 0.0901 | 6.5627 | 0.9827 | 0.9704 | 15.7335 |
89
+ | 0.0528 | 8.52 | 330 | 0.0845 | 6.6690 | 0.9826 | 0.9734 | 15.5950 |
90
+ | 0.0632 | 8.77 | 340 | 0.0822 | 6.2661 | 0.9833 | 0.9723 | 15.8631 |
91
+ | 0.0522 | 9.03 | 350 | 0.0844 | 6.0073 | 0.9836 | 0.9715 | 15.9393 |
92
+ | 0.0568 | 9.29 | 360 | 0.0817 | 5.9460 | 0.9837 | 0.9721 | 15.9523 |
93
+ | 0.057 | 9.55 | 370 | 0.0900 | 7.9726 | 0.9812 | 0.9730 | 15.1229 |
94
+ | 0.052 | 9.81 | 380 | 0.0836 | 6.5444 | 0.9822 | 0.9712 | 15.6388 |
95
+ | 0.0568 | 10.06 | 390 | 0.0810 | 6.0359 | 0.9836 | 0.9714 | 15.9796 |
96
+ | 0.0481 | 10.32 | 400 | 0.0784 | 6.2110 | 0.9835 | 0.9724 | 15.9235 |
97
+ | 0.0513 | 10.58 | 410 | 0.0803 | 6.0990 | 0.9835 | 0.9715 | 15.9502 |
98
+ | 0.0595 | 10.84 | 420 | 0.0798 | 6.0829 | 0.9835 | 0.9720 | 15.9052 |
99
+ | 0.047 | 11.1 | 430 | 0.0779 | 5.8847 | 0.9838 | 0.9725 | 16.0043 |
100
+ | 0.0406 | 11.35 | 440 | 0.0802 | 5.7944 | 0.9838 | 0.9713 | 16.0620 |
101
+ | 0.0493 | 11.61 | 450 | 0.0781 | 6.0947 | 0.9836 | 0.9731 | 15.9033 |
102
+ | 0.064 | 11.87 | 460 | 0.0769 | 6.1257 | 0.9837 | 0.9736 | 15.9080 |
103
+ | 0.0622 | 12.13 | 470 | 0.0765 | 6.2964 | 0.9835 | 0.9739 | 15.8188 |
104
+ | 0.0457 | 12.39 | 480 | 0.0773 | 5.9826 | 0.9838 | 0.9728 | 16.0119 |
105
+ | 0.0447 | 12.65 | 490 | 0.0761 | 5.7977 | 0.9841 | 0.9728 | 16.0900 |
106
+ | 0.0515 | 12.9 | 500 | 0.0750 | 5.8569 | 0.9840 | 0.9729 | 16.0633 |
107
+ | 0.0357 | 13.16 | 510 | 0.0796 | 5.7990 | 0.9837 | 0.9713 | 16.0818 |
108
+ | 0.0503 | 13.42 | 520 | 0.0749 | 5.8323 | 0.9841 | 0.9736 | 16.0510 |
109
+ | 0.0508 | 13.68 | 530 | 0.0746 | 6.0361 | 0.9839 | 0.9735 | 15.9709 |
110
+ | 0.0533 | 13.94 | 540 | 0.0768 | 6.1596 | 0.9836 | 0.9740 | 15.9193 |
111
+ | 0.0503 | 14.19 | 550 | 0.0739 | 5.5900 | 0.9843 | 0.9723 | 16.1883 |
112
+ | 0.0515 | 14.45 | 560 | 0.0740 | 5.4660 | 0.9845 | 0.9727 | 16.2745 |
113
+ | 0.0502 | 14.71 | 570 | 0.0740 | 5.5895 | 0.9844 | 0.9736 | 16.2054 |
114
+ | 0.0401 | 14.97 | 580 | 0.0741 | 5.9694 | 0.9840 | 0.9747 | 15.9603 |
115
+ | 0.0495 | 15.23 | 590 | 0.0745 | 5.9136 | 0.9841 | 0.9740 | 16.0458 |
116
+ | 0.0413 | 15.48 | 600 | 0.0743 | 5.9548 | 0.9840 | 0.9740 | 16.0119 |
117
 
118
 
119
  ### Framework versions
120
 
121
+ - Transformers 4.31.0
122
+ - Pytorch 2.0.0
123
+ - Datasets 2.13.1
124
+ - Tokenizers 0.13.3