Hugging Face's logo

sshk
/
segformer-b3-fashion-finetuned-polo-segments-aug-07-v1.2

Image Segmentation
Safetensors
segformer
vision
Generated from Trainer
Model card Files Community
sshk commited on
Commit
2bd1bfc
•
1 Parent(s): b768453

End of training

Browse files
Files changed (3) hide show
  1. README.md +23 -23
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -17,24 +17,24 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [sayeed99/segformer-b3-fashion](https://huggingface.co/sayeed99/segformer-b3-fashion) on the sshk/polo-badges-segmentation dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0582
21
- - Mean Iou: 0.8583
22
- - Mean Accuracy: 0.9104
23
- - Overall Accuracy: 0.9803
24
  - Accuracy Unlabeled: nan
25
- - Accuracy Collar: 0.8741
26
- - Accuracy Polo: 0.9786
27
- - Accuracy Lines-cuff: 0.7185
28
- - Accuracy Lines-chest: 0.9188
29
- - Accuracy Human: 0.9805
30
- - Accuracy Background: 0.9920
31
  - Iou Unlabeled: nan
32
- - Iou Collar: 0.8111
33
- - Iou Polo: 0.9580
34
- - Iou Lines-cuff: 0.6290
35
- - Iou Lines-chest: 0.8101
36
- - Iou Human: 0.9553
37
- - Iou Background: 0.9863
38
 
39
  ## Model description
40
 
@@ -65,13 +65,13 @@ The following hyperparameters were used during training:
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Collar | Accuracy Polo | Accuracy Lines-cuff | Accuracy Lines-chest | Accuracy Human | Accuracy Background | Iou Unlabeled | Iou Collar | Iou Polo | Iou Lines-cuff | Iou Lines-chest | Iou Human | Iou Background |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:---------------:|:-------------:|:-------------------:|:--------------------:|:--------------:|:-------------------:|:-------------:|:----------:|:--------:|:--------------:|:---------------:|:---------:|:--------------:|
68
- | 0.1564 | 4.0 | 20 | 0.1474 | 0.5073 | 0.6210 | 0.9633 | nan | 0.7561 | 0.9797 | 0.0183 | 0.0138 | 0.9829 | 0.9750 | 0.0 | 0.6873 | 0.9282 | 0.0182 | 0.0131 | 0.9332 | 0.9714 |
69
- | 0.0912 | 8.0 | 40 | 0.0812 | 0.7332 | 0.7637 | 0.9751 | nan | 0.8012 | 0.9798 | 0.1221 | 0.7058 | 0.9886 | 0.9847 | nan | 0.7652 | 0.9512 | 0.1220 | 0.6314 | 0.9483 | 0.9811 |
70
- | 0.0724 | 12.0 | 60 | 0.0693 | 0.8345 | 0.8765 | 0.9791 | nan | 0.8651 | 0.9817 | 0.5794 | 0.8633 | 0.9810 | 0.9888 | nan | 0.8025 | 0.9570 | 0.5407 | 0.7688 | 0.9537 | 0.9844 |
71
- | 0.0609 | 16.0 | 80 | 0.0633 | 0.8506 | 0.9022 | 0.9796 | nan | 0.8697 | 0.9771 | 0.6806 | 0.9123 | 0.9826 | 0.9907 | nan | 0.8093 | 0.9573 | 0.6053 | 0.7921 | 0.9541 | 0.9853 |
72
- | 0.0602 | 20.0 | 100 | 0.0629 | 0.8493 | 0.8960 | 0.9794 | nan | 0.8576 | 0.9789 | 0.6686 | 0.8987 | 0.9818 | 0.9904 | nan | 0.8024 | 0.9569 | 0.6004 | 0.7974 | 0.9532 | 0.9855 |
73
- | 0.0536 | 24.0 | 120 | 0.0588 | 0.8556 | 0.9083 | 0.9801 | nan | 0.8709 | 0.9788 | 0.7104 | 0.9172 | 0.9823 | 0.9902 | nan | 0.8090 | 0.9581 | 0.6244 | 0.8011 | 0.9552 | 0.9856 |
74
- | 0.0459 | 28.0 | 140 | 0.0582 | 0.8583 | 0.9104 | 0.9803 | nan | 0.8741 | 0.9786 | 0.7185 | 0.9188 | 0.9805 | 0.9920 | nan | 0.8111 | 0.9580 | 0.6290 | 0.8101 | 0.9553 | 0.9863 |
75
 
76
 
77
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [sayeed99/segformer-b3-fashion](https://huggingface.co/sayeed99/segformer-b3-fashion) on the sshk/polo-badges-segmentation dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0801
21
+ - Mean Iou: 0.8698
22
+ - Mean Accuracy: 0.9244
23
+ - Overall Accuracy: 0.9721
24
  - Accuracy Unlabeled: nan
25
+ - Accuracy Collar: 0.8554
26
+ - Accuracy Polo: 0.9713
27
+ - Accuracy Lines-cuff: 0.8045
28
+ - Accuracy Lines-chest: 0.9543
29
+ - Accuracy Human: 0.9710
30
+ - Accuracy Background: 0.9896
31
  - Iou Unlabeled: nan
32
+ - Iou Collar: 0.7817
33
+ - Iou Polo: 0.9387
34
+ - Iou Lines-cuff: 0.7252
35
+ - Iou Lines-chest: 0.8492
36
+ - Iou Human: 0.9456
37
+ - Iou Background: 0.9783
38
 
39
  ## Model description
40
 
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Unlabeled | Accuracy Collar | Accuracy Polo | Accuracy Lines-cuff | Accuracy Lines-chest | Accuracy Human | Accuracy Background | Iou Unlabeled | Iou Collar | Iou Polo | Iou Lines-cuff | Iou Lines-chest | Iou Human | Iou Background |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:------------------:|:---------------:|:-------------:|:-------------------:|:--------------------:|:--------------:|:-------------------:|:-------------:|:----------:|:--------:|:--------------:|:---------------:|:---------:|:--------------:|
68
+ | 0.1958 | 4.0 | 20 | 0.1935 | 0.5473 | 0.5809 | 0.9484 | nan | 0.5688 | 0.9710 | 0.0 | 0.0 | 0.9699 | 0.9754 | nan | 0.5048 | 0.8825 | 0.0 | 0.0 | 0.9291 | 0.9676 |
69
+ | 0.0878 | 8.0 | 40 | 0.1158 | 0.7585 | 0.7864 | 0.9643 | nan | 0.7548 | 0.9721 | 0.3063 | 0.7322 | 0.9787 | 0.9740 | nan | 0.7084 | 0.9275 | 0.3054 | 0.7048 | 0.9353 | 0.9694 |
70
+ | 0.0737 | 12.0 | 60 | 0.0929 | 0.8595 | 0.9043 | 0.9708 | nan | 0.8229 | 0.9704 | 0.7743 | 0.8982 | 0.9757 | 0.9842 | nan | 0.7641 | 0.9366 | 0.7031 | 0.8330 | 0.9436 | 0.9766 |
71
+ | 0.0646 | 16.0 | 80 | 0.0868 | 0.8643 | 0.9140 | 0.9711 | nan | 0.8521 | 0.9747 | 0.7778 | 0.9226 | 0.9662 | 0.9909 | nan | 0.7807 | 0.9359 | 0.7101 | 0.8379 | 0.9435 | 0.9774 |
72
+ | 0.0688 | 20.0 | 100 | 0.0819 | 0.8665 | 0.9176 | 0.9720 | nan | 0.8502 | 0.9721 | 0.7841 | 0.9386 | 0.9709 | 0.9899 | nan | 0.7814 | 0.9384 | 0.7139 | 0.8418 | 0.9459 | 0.9778 |
73
+ | 0.052 | 24.0 | 120 | 0.0821 | 0.8652 | 0.9207 | 0.9716 | nan | 0.8302 | 0.9646 | 0.8053 | 0.9590 | 0.9769 | 0.9883 | nan | 0.7694 | 0.9381 | 0.7210 | 0.8400 | 0.9445 | 0.9781 |
74
+ | 0.0483 | 28.0 | 140 | 0.0801 | 0.8698 | 0.9244 | 0.9721 | nan | 0.8554 | 0.9713 | 0.8045 | 0.9543 | 0.9710 | 0.9896 | nan | 0.7817 | 0.9387 | 0.7252 | 0.8492 | 0.9456 | 0.9783 |
75
 
76
 
77
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91ec1e7cd185fdbcc688a5f1b12829720bd4bebc687734c2108492fafd6a61c0
3
  size 188995156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:349f68f18c84f4aee2e3a234d218d706a670e5249de7df194208ae15e3437ec7
3
  size 188995156
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08716ca9ba65cf09a0539aa51c3a4e15292c9a05b907a25dcf19e57a765353bf
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3ce14c808c74da724376f5c2d07a7ba6f0cb6d696e821d898f6514667efac02
3
  size 5304