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
9209ed4
·
verified ·
1 Parent(s): 788ff7a

Model save

Browse files
Files changed (1) hide show
  1. README.md +80 -0
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
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
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
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: 0.0929
20
+ - Mean Iou: 0.4897
21
+ - Mean Accuracy: 0.9793
22
+ - Overall Accuracy: 0.9793
23
+ - Accuracy Text: nan
24
+ - Accuracy No Text: 0.9793
25
+ - Iou Text: 0.0
26
+ - Iou No Text: 0.9793
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 6e-05
46
+ - train_batch_size: 8
47
+ - eval_batch_size: 8
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: 2000
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Text | Accuracy No Text | Iou Text | Iou No Text |
56
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------:|:----------------:|:--------:|:-----------:|
57
+ | 0.3305 | 1.0 | 125 | 0.1846 | 0.4793 | 0.9586 | 0.9586 | nan | 0.9586 | 0.0 | 0.9586 |
58
+ | 0.2037 | 2.0 | 250 | 0.1322 | 0.4853 | 0.9706 | 0.9706 | nan | 0.9706 | 0.0 | 0.9706 |
59
+ | 0.1534 | 3.0 | 375 | 0.1074 | 0.4892 | 0.9784 | 0.9784 | nan | 0.9784 | 0.0 | 0.9784 |
60
+ | 0.1313 | 4.0 | 500 | 0.0976 | 0.4920 | 0.9839 | 0.9839 | nan | 0.9839 | 0.0 | 0.9839 |
61
+ | 0.1156 | 5.0 | 625 | 0.1001 | 0.4900 | 0.9799 | 0.9799 | nan | 0.9799 | 0.0 | 0.9799 |
62
+ | 0.1123 | 6.0 | 750 | 0.0920 | 0.4933 | 0.9866 | 0.9866 | nan | 0.9866 | 0.0 | 0.9866 |
63
+ | 0.108 | 7.0 | 875 | 0.0946 | 0.4908 | 0.9815 | 0.9815 | nan | 0.9815 | 0.0 | 0.9815 |
64
+ | 0.1017 | 8.0 | 1000 | 0.0943 | 0.4903 | 0.9805 | 0.9805 | nan | 0.9805 | 0.0 | 0.9805 |
65
+ | 0.0994 | 9.0 | 1125 | 0.0927 | 0.4904 | 0.9808 | 0.9808 | nan | 0.9808 | 0.0 | 0.9808 |
66
+ | 0.0926 | 10.0 | 1250 | 0.0957 | 0.4891 | 0.9783 | 0.9783 | nan | 0.9783 | 0.0 | 0.9783 |
67
+ | 0.0907 | 11.0 | 1375 | 0.0913 | 0.4915 | 0.9830 | 0.9830 | nan | 0.9830 | 0.0 | 0.9830 |
68
+ | 0.0893 | 12.0 | 1500 | 0.0893 | 0.4919 | 0.9838 | 0.9838 | nan | 0.9838 | 0.0 | 0.9838 |
69
+ | 0.0853 | 13.0 | 1625 | 0.0913 | 0.4902 | 0.9804 | 0.9804 | nan | 0.9804 | 0.0 | 0.9804 |
70
+ | 0.0834 | 14.0 | 1750 | 0.0899 | 0.4910 | 0.9820 | 0.9820 | nan | 0.9820 | 0.0 | 0.9820 |
71
+ | 0.0861 | 15.0 | 1875 | 0.0902 | 0.4907 | 0.9815 | 0.9815 | nan | 0.9815 | 0.0 | 0.9815 |
72
+ | 0.0803 | 16.0 | 2000 | 0.0929 | 0.4897 | 0.9793 | 0.9793 | nan | 0.9793 | 0.0 | 0.9793 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - Transformers 4.49.0.dev0
78
+ - Pytorch 2.5.1+cu124
79
+ - Datasets 3.2.0
80
+ - Tokenizers 0.21.0