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
9b85988
·
verified ·
1 Parent(s): ecad7b4

Model save

Browse files
Files changed (1) hide show
  1. README.md +32 -10
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
 
@@ -50,7 +48,7 @@ The following hyperparameters were used during training:
50
  - seed: 1337
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: polynomial
53
- - training_steps: 2000
54
 
55
  ### Training results
56
 
@@ -72,6 +70,30 @@ The following hyperparameters were used during training:
72
  | 0.0834 | 14.0 | 1750 | 0.9820 | nan | 0.9820 | 0.0 | 0.0899 | 0.9820 | 0.4910 | 0.9820 |
73
  | 0.0861 | 15.0 | 1875 | 0.9815 | nan | 0.9815 | 0.0 | 0.0902 | 0.9815 | 0.4907 | 0.9815 |
74
  | 0.0803 | 16.0 | 2000 | 0.9793 | nan | 0.9793 | 0.0 | 0.0929 | 0.9793 | 0.4897 | 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
+ - Loss: 0.0912
20
+ - Mean Iou: 0.4902
21
+ - Mean Accuracy: 0.9805
22
+ - Overall Accuracy: 0.9805
23
  - Accuracy Text: nan
24
+ - Accuracy No Text: 0.9805
25
  - Iou Text: 0.0
26
+ - Iou No Text: 0.9805
27
 
28
  ## Model description
29
 
 
48
  - seed: 1337
49
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
  - lr_scheduler_type: polynomial
51
+ - training_steps: 5000
52
 
53
  ### Training results
54
 
 
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
+ | 0.0884 | 17.0 | 2125 | 0.1001 | 0.4875 | 0.9751 | 0.9751 | nan | 0.9751 | 0.0 | 0.9751 |
74
+ | 0.0871 | 18.0 | 2250 | 0.0907 | 0.4892 | 0.9783 | 0.9783 | nan | 0.9783 | 0.0 | 0.9783 |
75
+ | 0.0854 | 19.0 | 2375 | 0.0893 | 0.4924 | 0.9849 | 0.9849 | nan | 0.9849 | 0.0 | 0.9849 |
76
+ | 0.0852 | 20.0 | 2500 | 0.0870 | 0.4915 | 0.9831 | 0.9831 | nan | 0.9831 | 0.0 | 0.9831 |
77
+ | 0.0858 | 21.0 | 2625 | 0.0925 | 0.4896 | 0.9792 | 0.9792 | nan | 0.9792 | 0.0 | 0.9792 |
78
+ | 0.0804 | 22.0 | 2750 | 0.0964 | 0.4887 | 0.9774 | 0.9774 | nan | 0.9774 | 0.0 | 0.9774 |
79
+ | 0.076 | 23.0 | 2875 | 0.0934 | 0.4893 | 0.9786 | 0.9786 | nan | 0.9786 | 0.0 | 0.9786 |
80
+ | 0.0753 | 24.0 | 3000 | 0.0906 | 0.4890 | 0.9781 | 0.9781 | nan | 0.9781 | 0.0 | 0.9781 |
81
+ | 0.0742 | 25.0 | 3125 | 0.0962 | 0.4900 | 0.9801 | 0.9801 | nan | 0.9801 | 0.0 | 0.9801 |
82
+ | 0.0724 | 26.0 | 3250 | 0.0892 | 0.4920 | 0.9840 | 0.9840 | nan | 0.9840 | 0.0 | 0.9840 |
83
+ | 0.0794 | 27.0 | 3375 | 0.0885 | 0.4902 | 0.9803 | 0.9803 | nan | 0.9803 | 0.0 | 0.9803 |
84
+ | 0.0685 | 28.0 | 3500 | 0.0932 | 0.4911 | 0.9821 | 0.9821 | nan | 0.9821 | 0.0 | 0.9821 |
85
+ | 0.0695 | 29.0 | 3625 | 0.0890 | 0.4906 | 0.9812 | 0.9812 | nan | 0.9812 | 0.0 | 0.9812 |
86
+ | 0.065 | 30.0 | 3750 | 0.0877 | 0.4904 | 0.9808 | 0.9808 | nan | 0.9808 | 0.0 | 0.9808 |
87
+ | 0.0699 | 31.0 | 3875 | 0.0947 | 0.4877 | 0.9754 | 0.9754 | nan | 0.9754 | 0.0 | 0.9754 |
88
+ | 0.0742 | 32.0 | 4000 | 0.0875 | 0.4902 | 0.9805 | 0.9805 | nan | 0.9805 | 0.0 | 0.9805 |
89
+ | 0.0646 | 33.0 | 4125 | 0.0895 | 0.4903 | 0.9805 | 0.9805 | nan | 0.9805 | 0.0 | 0.9805 |
90
+ | 0.0677 | 34.0 | 4250 | 0.0915 | 0.4909 | 0.9818 | 0.9818 | nan | 0.9818 | 0.0 | 0.9818 |
91
+ | 0.0666 | 35.0 | 4375 | 0.0932 | 0.4890 | 0.9781 | 0.9781 | nan | 0.9781 | 0.0 | 0.9781 |
92
+ | 0.062 | 36.0 | 4500 | 0.0893 | 0.4901 | 0.9803 | 0.9803 | nan | 0.9803 | 0.0 | 0.9803 |
93
+ | 0.0623 | 37.0 | 4625 | 0.0934 | 0.4895 | 0.9789 | 0.9789 | nan | 0.9789 | 0.0 | 0.9789 |
94
+ | 0.0658 | 38.0 | 4750 | 0.0907 | 0.4913 | 0.9826 | 0.9826 | nan | 0.9826 | 0.0 | 0.9826 |
95
+ | 0.0596 | 39.0 | 4875 | 0.0904 | 0.4915 | 0.9831 | 0.9831 | nan | 0.9831 | 0.0 | 0.9831 |
96
+ | 0.0628 | 40.0 | 5000 | 0.0912 | 0.4902 | 0.9805 | 0.9805 | nan | 0.9805 | 0.0 | 0.9805 |
97
 
98
 
99
  ### Framework versions