Hugging Face's logo

blzncz
/
segformer-finetuned-4ss1st3r_s3gs3m_24Jan_all-10k-steps

Image Segmentation
Transformers
PyTorch
TensorBoard
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
blzncz commited on
Commit
e77c624
•
1 Parent(s): 5731d58

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +81 -0
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: segformer-finetuned-4ss1st3r_s3gs3m_24Jan_all-10k-steps
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # segformer-finetuned-4ss1st3r_s3gs3m_24Jan_all-10k-steps
14
+
15
+ This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.3095
18
+ - Mean Iou: 0.5513
19
+ - Mean Accuracy: 0.7874
20
+ - Overall Accuracy: 0.9260
21
+ - Accuracy Bg: nan
22
+ - Accuracy Fallo cohesivo: 0.9668
23
+ - Accuracy Fallo malla: 0.6808
24
+ - Accuracy Fallo adhesivo: 0.9727
25
+ - Accuracy Fallo burbuja: 0.5291
26
+ - Iou Bg: 0.0
27
+ - Iou Fallo cohesivo: 0.9167
28
+ - Iou Fallo malla: 0.6189
29
+ - Iou Fallo adhesivo: 0.7307
30
+ - Iou Fallo burbuja: 0.4903
31
+
32
+ ## Model description
33
+
34
+ More information needed
35
+
36
+ ## Intended uses & limitations
37
+
38
+ More information needed
39
+
40
+ ## Training and evaluation data
41
+
42
+ More information needed
43
+
44
+ ## Training procedure
45
+
46
+ ### Training hyperparameters
47
+
48
+ The following hyperparameters were used during training:
49
+ - learning_rate: 6e-05
50
+ - train_batch_size: 8
51
+ - eval_batch_size: 8
52
+ - seed: 1337
53
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
+ - lr_scheduler_type: polynomial
55
+ - training_steps: 10000
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Bg | Accuracy Fallo cohesivo | Accuracy Fallo malla | Accuracy Fallo adhesivo | Accuracy Fallo burbuja | Iou Bg | Iou Fallo cohesivo | Iou Fallo malla | Iou Fallo adhesivo | Iou Fallo burbuja |
60
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:-------------:|:----------------:|:-----------:|:-----------------------:|:--------------------:|:-----------------------:|:----------------------:|:------:|:------------------:|:---------------:|:------------------:|:-----------------:|
61
+ | 0.1378 | 1.0 | 783 | 0.2677 | 0.4895 | 0.7143 | 0.9122 | nan | 0.9724 | 0.5531 | 0.9663 | 0.3654 | 0.0 | 0.9038 | 0.5327 | 0.6757 | 0.3351 |
62
+ | 0.1117 | 2.0 | 1566 | 0.2305 | 0.5289 | 0.7978 | 0.9246 | nan | 0.9507 | 0.7727 | 0.9705 | 0.4974 | 0.0 | 0.9214 | 0.6808 | 0.5876 | 0.4549 |
63
+ | 0.0881 | 3.0 | 2349 | 0.2041 | 0.5556 | 0.7867 | 0.9354 | nan | 0.9712 | 0.7391 | 0.9389 | 0.4975 | 0.0 | 0.9273 | 0.6790 | 0.7323 | 0.4394 |
64
+ | 0.0878 | 4.0 | 3132 | 0.1984 | 0.5584 | 0.8003 | 0.9346 | nan | 0.9556 | 0.8247 | 0.9602 | 0.4606 | 0.0 | 0.9261 | 0.6935 | 0.7373 | 0.4352 |
65
+ | 0.0895 | 5.0 | 3915 | 0.2841 | 0.5246 | 0.8086 | 0.9088 | nan | 0.9137 | 0.8834 | 0.9719 | 0.4652 | 0.0 | 0.8964 | 0.6309 | 0.6593 | 0.4365 |
66
+ | 0.0773 | 6.0 | 4698 | 0.2547 | 0.5652 | 0.7823 | 0.9336 | nan | 0.9775 | 0.6843 | 0.9384 | 0.5291 | 0.0 | 0.9251 | 0.6378 | 0.7820 | 0.4813 |
67
+ | 0.0667 | 7.0 | 5481 | 0.2726 | 0.5609 | 0.7932 | 0.9295 | nan | 0.9741 | 0.6609 | 0.9689 | 0.5689 | 0.0 | 0.9203 | 0.6202 | 0.7548 | 0.5093 |
68
+ | 0.0678 | 8.0 | 6264 | 0.2950 | 0.5276 | 0.8002 | 0.9175 | nan | 0.9443 | 0.7561 | 0.9713 | 0.5292 | 0.0 | 0.9089 | 0.6570 | 0.5900 | 0.4822 |
69
+ | 0.0653 | 9.0 | 7047 | 0.2712 | 0.5467 | 0.7682 | 0.9288 | nan | 0.9690 | 0.6971 | 0.9641 | 0.4425 | 0.0 | 0.9189 | 0.6330 | 0.7588 | 0.4228 |
70
+ | 0.0646 | 10.0 | 7830 | 0.2841 | 0.5499 | 0.7819 | 0.9272 | nan | 0.9681 | 0.6840 | 0.9688 | 0.5068 | 0.0 | 0.9178 | 0.6243 | 0.7345 | 0.4728 |
71
+ | 0.057 | 11.0 | 8613 | 0.3373 | 0.5257 | 0.7782 | 0.9166 | nan | 0.9593 | 0.6555 | 0.9739 | 0.5242 | 0.0 | 0.9075 | 0.6040 | 0.6319 | 0.4848 |
72
+ | 0.0591 | 12.0 | 9396 | 0.3082 | 0.5504 | 0.7900 | 0.9247 | nan | 0.9656 | 0.6776 | 0.9705 | 0.5463 | 0.0 | 0.9148 | 0.6172 | 0.7182 | 0.5019 |
73
+ | 0.053 | 12.77 | 10000 | 0.3095 | 0.5513 | 0.7874 | 0.9260 | nan | 0.9668 | 0.6808 | 0.9727 | 0.5291 | 0.0 | 0.9167 | 0.6189 | 0.7307 | 0.4903 |
74
+
75
+
76
+ ### Framework versions
77
+
78
+ - Transformers 4.31.0.dev0
79
+ - Pytorch 2.0.1+cpu
80
+ - Datasets 2.13.1
81
+ - Tokenizers 0.13.3