Hugging Face's logo

Hasano20
/
SegFormer_Mixed_Set2_Grayscale_mit-b5

Transformers
Safetensors
segformer
Generated from Trainer
Inference Endpoints
Model card Files Community
Hasano20 commited on
Commit
c62ec6a
·
verified ·
1 Parent(s): 2f27910

End of training

Browse files
Files changed (3) hide show
  1. README.md +42 -31
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -1,8 +1,10 @@
1
  ---
2
  license: other
 
3
  tags:
 
 
4
  - generated_from_trainer
5
- base_model: nvidia/mit-b5
6
  model-index:
7
  - name: SegFormer_Mixed_Set2_Grayscale_mit-b5
8
  results: []
@@ -13,18 +15,18 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # SegFormer_Mixed_Set2_Grayscale_mit-b5
15
 
16
- This model is a fine-tuned version of [nvidia/mit-b5](https://huggingface.co/nvidia/mit-b5) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.0178
19
- - Mean Iou: 0.9762
20
- - Mean Accuracy: 0.9867
21
- - Overall Accuracy: 0.9938
22
- - Accuracy Background: 0.9926
23
- - Accuracy Melt: 0.9695
24
- - Accuracy Substrate: 0.9981
25
- - Iou Background: 0.9905
26
- - Iou Melt: 0.9469
27
- - Iou Substrate: 0.9913
28
 
29
  ## Model description
30
 
@@ -56,25 +58,34 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Background | Accuracy Melt | Accuracy Substrate | Iou Background | Iou Melt | Iou Substrate |
58
  |:-------------:|:-------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------:|:-------------:|:------------------:|:--------------:|:--------:|:-------------:|
59
- | 0.2842 | 0.7042 | 50 | 0.1653 | 0.7872 | 0.8326 | 0.9457 | 0.9693 | 0.5454 | 0.9831 | 0.9409 | 0.4996 | 0.9212 |
60
- | 0.0534 | 1.4085 | 100 | 0.0704 | 0.9016 | 0.9292 | 0.9751 | 0.9884 | 0.8114 | 0.9878 | 0.9688 | 0.7722 | 0.9639 |
61
- | 0.0309 | 2.1127 | 150 | 0.0424 | 0.9389 | 0.9618 | 0.9854 | 0.9948 | 0.9004 | 0.9901 | 0.9808 | 0.8551 | 0.9807 |
62
- | 0.0358 | 2.8169 | 200 | 0.0390 | 0.9443 | 0.9710 | 0.9858 | 0.9797 | 0.9360 | 0.9972 | 0.9778 | 0.8732 | 0.9820 |
63
- | 0.031 | 3.5211 | 250 | 0.0373 | 0.9447 | 0.9838 | 0.9866 | 0.9869 | 0.9767 | 0.9878 | 0.9842 | 0.8681 | 0.9819 |
64
- | 0.026 | 4.2254 | 300 | 0.0254 | 0.9629 | 0.9734 | 0.9912 | 0.9946 | 0.9283 | 0.9973 | 0.9893 | 0.9124 | 0.9871 |
65
- | 0.0167 | 4.9296 | 350 | 0.0194 | 0.9710 | 0.9832 | 0.9928 | 0.9949 | 0.9589 | 0.9959 | 0.9900 | 0.9331 | 0.9899 |
66
- | 0.0309 | 5.6338 | 400 | 0.0204 | 0.9705 | 0.9862 | 0.9927 | 0.9935 | 0.9697 | 0.9953 | 0.9899 | 0.9316 | 0.9901 |
67
- | 0.0129 | 6.3380 | 450 | 0.0187 | 0.9731 | 0.9853 | 0.9932 | 0.9929 | 0.9659 | 0.9972 | 0.9901 | 0.9385 | 0.9906 |
68
- | 0.0149 | 7.0423 | 500 | 0.0187 | 0.9729 | 0.9872 | 0.9933 | 0.9939 | 0.9718 | 0.9957 | 0.9902 | 0.9375 | 0.9909 |
69
- | 0.0132 | 7.7465 | 550 | 0.0171 | 0.9746 | 0.9860 | 0.9936 | 0.9948 | 0.9669 | 0.9965 | 0.9910 | 0.9416 | 0.9911 |
70
- | 0.0149 | 8.4507 | 600 | 0.0178 | 0.9739 | 0.9870 | 0.9935 | 0.9936 | 0.9707 | 0.9965 | 0.9907 | 0.9401 | 0.9910 |
71
- | 0.0142 | 9.1549 | 650 | 0.0161 | 0.9760 | 0.9900 | 0.9940 | 0.9932 | 0.9805 | 0.9964 | 0.9909 | 0.9450 | 0.9920 |
72
- | 0.0124 | 9.8592 | 700 | 0.0160 | 0.9768 | 0.9876 | 0.9941 | 0.9946 | 0.9712 | 0.9969 | 0.9913 | 0.9473 | 0.9918 |
73
- | 0.0077 | 10.5634 | 750 | 0.0170 | 0.9766 | 0.9871 | 0.9942 | 0.9951 | 0.9693 | 0.9969 | 0.9914 | 0.9464 | 0.9920 |
74
- | 0.0104 | 11.2676 | 800 | 0.0182 | 0.9756 | 0.9857 | 0.9937 | 0.9933 | 0.9661 | 0.9978 | 0.9903 | 0.9452 | 0.9913 |
75
- | 0.0081 | 11.9718 | 850 | 0.0169 | 0.9759 | 0.9872 | 0.9937 | 0.9924 | 0.9716 | 0.9978 | 0.9903 | 0.9460 | 0.9913 |
76
- | 0.0108 | 12.6761 | 900 | 0.0167 | 0.9770 | 0.9882 | 0.9942 | 0.9951 | 0.9732 | 0.9963 | 0.9913 | 0.9476 | 0.9919 |
77
- | 0.0087 | 13.3803 | 950 | 0.0178 | 0.9762 | 0.9867 | 0.9938 | 0.9926 | 0.9695 | 0.9981 | 0.9905 | 0.9469 | 0.9913 |
 
 
 
 
 
 
 
 
 
78
 
79
 
80
  ### Framework versions
 
1
  ---
2
  license: other
3
+ base_model: nvidia/mit-b5
4
  tags:
5
+ - vision
6
+ - image-segmentation
7
  - generated_from_trainer
 
8
  model-index:
9
  - name: SegFormer_Mixed_Set2_Grayscale_mit-b5
10
  results: []
 
15
 
16
  # SegFormer_Mixed_Set2_Grayscale_mit-b5
17
 
18
+ This model is a fine-tuned version of [nvidia/mit-b5](https://huggingface.co/nvidia/mit-b5) on the Hasano20/Mixed_Set2_Grayscale dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0138
21
+ - Mean Iou: 0.9805
22
+ - Mean Accuracy: 0.9909
23
+ - Overall Accuracy: 0.9952
24
+ - Accuracy Background: 0.9959
25
+ - Accuracy Melt: 0.9801
26
+ - Accuracy Substrate: 0.9967
27
+ - Iou Background: 0.9926
28
+ - Iou Melt: 0.9554
29
+ - Iou Substrate: 0.9934
30
 
31
  ## Model description
32
 
 
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Background | Accuracy Melt | Accuracy Substrate | Iou Background | Iou Melt | Iou Substrate |
60
  |:-------------:|:-------:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------:|:-------------:|:------------------:|:--------------:|:--------:|:-------------:|
61
+ | 0.1464 | 0.7042 | 50 | 0.1373 | 0.8536 | 0.9233 | 0.9584 | 0.9574 | 0.8385 | 0.9741 | 0.9444 | 0.6783 | 0.9381 |
62
+ | 0.0813 | 1.4085 | 100 | 0.0616 | 0.9196 | 0.9481 | 0.9808 | 0.9873 | 0.8668 | 0.9902 | 0.9748 | 0.8112 | 0.9728 |
63
+ | 0.0415 | 2.1127 | 150 | 0.0608 | 0.9074 | 0.9281 | 0.9802 | 0.9931 | 0.7978 | 0.9934 | 0.9769 | 0.7718 | 0.9734 |
64
+ | 0.0486 | 2.8169 | 200 | 0.0344 | 0.9475 | 0.9675 | 0.9876 | 0.9859 | 0.9190 | 0.9976 | 0.9836 | 0.8764 | 0.9824 |
65
+ | 0.028 | 3.5211 | 250 | 0.0226 | 0.9663 | 0.9845 | 0.9922 | 0.9929 | 0.9658 | 0.9949 | 0.9894 | 0.9205 | 0.9892 |
66
+ | 0.0309 | 4.2254 | 300 | 0.0214 | 0.9686 | 0.9839 | 0.9924 | 0.9931 | 0.9630 | 0.9956 | 0.9894 | 0.9273 | 0.9891 |
67
+ | 0.0136 | 4.9296 | 350 | 0.0248 | 0.9637 | 0.9828 | 0.9913 | 0.9901 | 0.9623 | 0.9959 | 0.9885 | 0.9151 | 0.9873 |
68
+ | 0.021 | 5.6338 | 400 | 0.0182 | 0.9717 | 0.9881 | 0.9933 | 0.9942 | 0.9752 | 0.9949 | 0.9908 | 0.9338 | 0.9906 |
69
+ | 0.0178 | 6.3380 | 450 | 0.0163 | 0.9747 | 0.9907 | 0.9940 | 0.9945 | 0.9826 | 0.9950 | 0.9913 | 0.9409 | 0.9918 |
70
+ | 0.0211 | 7.0423 | 500 | 0.0167 | 0.9746 | 0.9877 | 0.9939 | 0.9949 | 0.9725 | 0.9958 | 0.9911 | 0.9414 | 0.9913 |
71
+ | 0.0161 | 7.7465 | 550 | 0.0162 | 0.9751 | 0.9883 | 0.9939 | 0.9936 | 0.9747 | 0.9966 | 0.9910 | 0.9429 | 0.9914 |
72
+ | 0.0128 | 8.4507 | 600 | 0.0145 | 0.9769 | 0.9903 | 0.9944 | 0.9940 | 0.9805 | 0.9965 | 0.9916 | 0.9468 | 0.9924 |
73
+ | 0.0132 | 9.1549 | 650 | 0.0150 | 0.9780 | 0.9891 | 0.9946 | 0.9946 | 0.9757 | 0.9970 | 0.9918 | 0.9498 | 0.9923 |
74
+ | 0.0118 | 9.8592 | 700 | 0.0144 | 0.9775 | 0.9907 | 0.9946 | 0.9938 | 0.9815 | 0.9968 | 0.9915 | 0.9483 | 0.9927 |
75
+ | 0.0088 | 10.5634 | 750 | 0.0136 | 0.9792 | 0.9907 | 0.9949 | 0.9952 | 0.9804 | 0.9965 | 0.9922 | 0.9524 | 0.9930 |
76
+ | 0.0085 | 11.2676 | 800 | 0.0140 | 0.9789 | 0.9904 | 0.9948 | 0.9947 | 0.9797 | 0.9968 | 0.9921 | 0.9517 | 0.9929 |
77
+ | 0.0109 | 11.9718 | 850 | 0.0142 | 0.9782 | 0.9919 | 0.9948 | 0.9950 | 0.9849 | 0.9959 | 0.9921 | 0.9497 | 0.9929 |
78
+ | 0.009 | 12.6761 | 900 | 0.0134 | 0.9799 | 0.9908 | 0.9951 | 0.9951 | 0.9804 | 0.9969 | 0.9923 | 0.9542 | 0.9933 |
79
+ | 0.0105 | 13.3803 | 950 | 0.0135 | 0.9797 | 0.9912 | 0.9951 | 0.9953 | 0.9817 | 0.9966 | 0.9923 | 0.9536 | 0.9933 |
80
+ | 0.0094 | 14.0845 | 1000 | 0.0142 | 0.9786 | 0.9868 | 0.9948 | 0.9953 | 0.9673 | 0.9979 | 0.9923 | 0.9509 | 0.9927 |
81
+ | 0.0089 | 14.7887 | 1050 | 0.0136 | 0.9799 | 0.9907 | 0.9951 | 0.9955 | 0.9800 | 0.9967 | 0.9924 | 0.9541 | 0.9933 |
82
+ | 0.0118 | 15.4930 | 1100 | 0.0140 | 0.9794 | 0.9897 | 0.9950 | 0.9962 | 0.9763 | 0.9965 | 0.9924 | 0.9528 | 0.9932 |
83
+ | 0.0101 | 16.1972 | 1150 | 0.0142 | 0.9792 | 0.9914 | 0.9950 | 0.9950 | 0.9828 | 0.9965 | 0.9922 | 0.9521 | 0.9933 |
84
+ | 0.0081 | 16.9014 | 1200 | 0.0182 | 0.9748 | 0.9844 | 0.9942 | 0.9961 | 0.9601 | 0.9970 | 0.9923 | 0.9405 | 0.9915 |
85
+ | 0.0111 | 17.6056 | 1250 | 0.0154 | 0.9772 | 0.9913 | 0.9945 | 0.9942 | 0.9837 | 0.9961 | 0.9918 | 0.9471 | 0.9925 |
86
+ | 0.0078 | 18.3099 | 1300 | 0.0136 | 0.9800 | 0.9905 | 0.9951 | 0.9958 | 0.9791 | 0.9966 | 0.9925 | 0.9544 | 0.9933 |
87
+ | 0.0059 | 19.0141 | 1350 | 0.0139 | 0.9802 | 0.9915 | 0.9952 | 0.9953 | 0.9824 | 0.9967 | 0.9926 | 0.9545 | 0.9934 |
88
+ | 0.0081 | 19.7183 | 1400 | 0.0138 | 0.9805 | 0.9909 | 0.9952 | 0.9959 | 0.9801 | 0.9967 | 0.9926 | 0.9554 | 0.9934 |
89
 
90
 
91
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd447ccf12ffc574c6d105ca70ab232a9552555b5d347e4fc891fbd2feee64fc
3
  size 338531516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d75c4f4671fd5cb36f997c385b07c92f155959b8d0b757c7f70722c1726cfeca
3
  size 338531516
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:008041c46ed27721360ce72ebd76f2d3ec45227241bd293b5df0a378c46cfeaa
3
  size 4667
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a558eeaca350fc45438acfe535e1ceff7981996ecf7ca9cec1296e7b7e267e6
3
  size 4667