Hugging Face's logo

Saumya-Mundra
/
segformer-finetuned-tt-2k-b1

Image Segmentation
Transformers
Safetensors
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Community
Saumya-Mundra commited on
Commit
84322e8
·
verified ·
1 Parent(s): 5617f21

Model save

Browse files
Files changed (2) hide show
  1. README.md +25 -27
  2. training_args.bin +1 -1
README.md CHANGED
@@ -3,8 +3,6 @@ library_name: transformers
3
  license: other
4
  base_model: nvidia/mit-b1
5
  tags:
6
- - image-segmentation
7
- - vision
8
  - generated_from_trainer
9
  model-index:
10
  - name: segformer-finetuned-tt-2k-b1
@@ -16,16 +14,16 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # segformer-finetuned-tt-2k-b1
18
 
19
- This model is a fine-tuned version of [nvidia/mit-b1](https://huggingface.co/nvidia/mit-b1) on the Saumya-Mundra/text255 dataset.
20
  It achieves the following results on the evaluation set:
 
 
 
 
21
  - Loss: 0.0929
22
- - Mean Iou: 0.4897
23
  - Mean Accuracy: 0.9793
 
24
  - Overall Accuracy: 0.9793
25
- - Accuracy Text: nan
26
- - Accuracy No Text: 0.9793
27
- - Iou Text: 0.0
28
- - Iou No Text: 0.9793
29
 
30
  ## Model description
31
 
@@ -44,7 +42,7 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - learning_rate: 6e-05
48
  - train_batch_size: 8
49
  - eval_batch_size: 8
50
  - seed: 1337
@@ -54,24 +52,24 @@ The following hyperparameters were used during training:
54
 
55
  ### Training results
56
 
57
- | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Text | Accuracy No Text | Iou Text | Iou No Text |
58
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------:|:----------------:|:--------:|:-----------:|
59
- | 0.3305 | 1.0 | 125 | 0.1846 | 0.4793 | 0.9586 | 0.9586 | nan | 0.9586 | 0.0 | 0.9586 |
60
- | 0.2037 | 2.0 | 250 | 0.1322 | 0.4853 | 0.9706 | 0.9706 | nan | 0.9706 | 0.0 | 0.9706 |
61
- | 0.1534 | 3.0 | 375 | 0.1074 | 0.4892 | 0.9784 | 0.9784 | nan | 0.9784 | 0.0 | 0.9784 |
62
- | 0.1313 | 4.0 | 500 | 0.0976 | 0.4920 | 0.9839 | 0.9839 | nan | 0.9839 | 0.0 | 0.9839 |
63
- | 0.1156 | 5.0 | 625 | 0.1001 | 0.4900 | 0.9799 | 0.9799 | nan | 0.9799 | 0.0 | 0.9799 |
64
- | 0.1123 | 6.0 | 750 | 0.0920 | 0.4933 | 0.9866 | 0.9866 | nan | 0.9866 | 0.0 | 0.9866 |
65
- | 0.108 | 7.0 | 875 | 0.0946 | 0.4908 | 0.9815 | 0.9815 | nan | 0.9815 | 0.0 | 0.9815 |
66
- | 0.1017 | 8.0 | 1000 | 0.0943 | 0.4903 | 0.9805 | 0.9805 | nan | 0.9805 | 0.0 | 0.9805 |
67
- | 0.0994 | 9.0 | 1125 | 0.0927 | 0.4904 | 0.9808 | 0.9808 | nan | 0.9808 | 0.0 | 0.9808 |
68
- | 0.0926 | 10.0 | 1250 | 0.0957 | 0.4891 | 0.9783 | 0.9783 | nan | 0.9783 | 0.0 | 0.9783 |
69
- | 0.0907 | 11.0 | 1375 | 0.0913 | 0.4915 | 0.9830 | 0.9830 | nan | 0.9830 | 0.0 | 0.9830 |
70
- | 0.0893 | 12.0 | 1500 | 0.0893 | 0.4919 | 0.9838 | 0.9838 | nan | 0.9838 | 0.0 | 0.9838 |
71
- | 0.0853 | 13.0 | 1625 | 0.0913 | 0.4902 | 0.9804 | 0.9804 | nan | 0.9804 | 0.0 | 0.9804 |
72
- | 0.0834 | 14.0 | 1750 | 0.0899 | 0.4910 | 0.9820 | 0.9820 | nan | 0.9820 | 0.0 | 0.9820 |
73
- | 0.0861 | 15.0 | 1875 | 0.0902 | 0.4907 | 0.9815 | 0.9815 | nan | 0.9815 | 0.0 | 0.9815 |
74
- | 0.0803 | 16.0 | 2000 | 0.0929 | 0.4897 | 0.9793 | 0.9793 | nan | 0.9793 | 0.0 | 0.9793 |
75
 
76
 
77
  ### Framework versions
 
3
  license: other
4
  base_model: nvidia/mit-b1
5
  tags:
 
 
6
  - generated_from_trainer
7
  model-index:
8
  - name: segformer-finetuned-tt-2k-b1
 
14
 
15
  # segformer-finetuned-tt-2k-b1
16
 
17
+ This model is a fine-tuned version of [nvidia/mit-b1](https://huggingface.co/nvidia/mit-b1) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Accuracy No Text: 0.9793
20
+ - Accuracy Text: nan
21
+ - Iou No Text: 0.9793
22
+ - Iou Text: 0.0
23
  - Loss: 0.0929
 
24
  - Mean Accuracy: 0.9793
25
+ - Mean Iou: 0.4897
26
  - Overall Accuracy: 0.9793
 
 
 
 
27
 
28
  ## Model description
29
 
 
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
+ - learning_rate: 6e-07
46
  - train_batch_size: 8
47
  - eval_batch_size: 8
48
  - seed: 1337
 
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Accuracy No Text | Accuracy Text | Iou No Text | Iou Text | Validation Loss | Mean Accuracy | Mean Iou | Overall Accuracy |
56
+ |:-------------:|:-----:|:----:|:----------------:|:-------------:|:-----------:|:--------:|:---------------:|:-------------:|:--------:|:----------------:|
57
+ | 0.3305 | 1.0 | 125 | 0.9586 | nan | 0.9586 | 0.0 | 0.1846 | 0.9586 | 0.4793 | 0.9586 |
58
+ | 0.2037 | 2.0 | 250 | 0.9706 | nan | 0.9706 | 0.0 | 0.1322 | 0.9706 | 0.4853 | 0.9706 |
59
+ | 0.1534 | 3.0 | 375 | 0.9784 | nan | 0.9784 | 0.0 | 0.1074 | 0.9784 | 0.4892 | 0.9784 |
60
+ | 0.1313 | 4.0 | 500 | 0.9839 | nan | 0.9839 | 0.0 | 0.0976 | 0.9839 | 0.4920 | 0.9839 |
61
+ | 0.1156 | 5.0 | 625 | 0.9799 | nan | 0.9799 | 0.0 | 0.1001 | 0.9799 | 0.4900 | 0.9799 |
62
+ | 0.1123 | 6.0 | 750 | 0.9866 | nan | 0.9866 | 0.0 | 0.0920 | 0.9866 | 0.4933 | 0.9866 |
63
+ | 0.108 | 7.0 | 875 | 0.9815 | nan | 0.9815 | 0.0 | 0.0946 | 0.9815 | 0.4908 | 0.9815 |
64
+ | 0.1017 | 8.0 | 1000 | 0.9805 | nan | 0.9805 | 0.0 | 0.0943 | 0.9805 | 0.4903 | 0.9805 |
65
+ | 0.0994 | 9.0 | 1125 | 0.9808 | nan | 0.9808 | 0.0 | 0.0927 | 0.9808 | 0.4904 | 0.9808 |
66
+ | 0.0926 | 10.0 | 1250 | 0.9783 | nan | 0.9783 | 0.0 | 0.0957 | 0.9783 | 0.4891 | 0.9783 |
67
+ | 0.0907 | 11.0 | 1375 | 0.9830 | nan | 0.9830 | 0.0 | 0.0913 | 0.9830 | 0.4915 | 0.9830 |
68
+ | 0.0893 | 12.0 | 1500 | 0.9838 | nan | 0.9838 | 0.0 | 0.0893 | 0.9838 | 0.4919 | 0.9838 |
69
+ | 0.0853 | 13.0 | 1625 | 0.9804 | nan | 0.9804 | 0.0 | 0.0913 | 0.9804 | 0.4902 | 0.9804 |
70
+ | 0.0834 | 14.0 | 1750 | 0.9820 | nan | 0.9820 | 0.0 | 0.0899 | 0.9820 | 0.4910 | 0.9820 |
71
+ | 0.0861 | 15.0 | 1875 | 0.9815 | nan | 0.9815 | 0.0 | 0.0902 | 0.9815 | 0.4907 | 0.9815 |
72
+ | 0.0803 | 16.0 | 2000 | 0.9793 | nan | 0.9793 | 0.0 | 0.0929 | 0.9793 | 0.4897 | 0.9793 |
73
 
74
 
75
  ### Framework versions
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e884b89824d04ecb34b46c9cc0febf50ce2aa03ab4ec473e243942b5705cb89f
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c5de8d5d860a07dc2f30b76db52bf378a3ff4563c6059551d27878574cb9350
3
  size 5368