Hugging Face's logo

NbAiLab
/
autocrop-bilder

Image Segmentation
Transformers
TensorBoard
Safetensors
segformer
vision
Generated from Trainer
Model card Files
xet
 Metrics Community
Rolv-Arild commited on
Commit
d53c74a
·
verified ·
1 Parent(s): bfe59c7

Model save

Browse files
Files changed (2) hide show
  1. README.md +38 -40
  2. model.safetensors +1 -1
README.md CHANGED
@@ -3,8 +3,6 @@ library_name: transformers
3
  license: other
4
  base_model: nvidia/mit-b0
5
  tags:
6
- - image-segmentation
7
- - vision
8
  - generated_from_trainer
9
  datasets:
10
  - generator
@@ -18,16 +16,16 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # autocrop-bilder
20
 
21
- This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the /mnt/disk1/autocrop-data/datasets/bilder/ dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.1087
24
- - Mean Iou: 0.4908
25
- - Mean Accuracy: 0.9816
26
- - Overall Accuracy: 0.9816
27
  - Accuracy Background: nan
28
- - Accuracy Crop: 0.9816
29
  - Iou Background: 0.0
30
- - Iou Crop: 0.9816
31
 
32
  ## Model description
33
 
@@ -60,37 +58,37 @@ The following hyperparameters were used during training:
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Background | Accuracy Crop | Iou Background | Iou Crop |
62
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------:|:-------------:|:--------------:|:--------:|
63
- | No log | 1.0 | 7 | 0.6694 | 0.3399 | 0.6798 | 0.6798 | nan | 0.6798 | 0.0 | 0.6798 |
64
- | No log | 2.0 | 14 | 0.5930 | 0.4623 | 0.9246 | 0.9246 | nan | 0.9246 | 0.0 | 0.9246 |
65
- | No log | 3.0 | 21 | 0.4610 | 0.4706 | 0.9412 | 0.9412 | nan | 0.9412 | 0.0 | 0.9412 |
66
- | No log | 4.0 | 28 | 0.3075 | 0.4705 | 0.9411 | 0.9411 | nan | 0.9411 | 0.0 | 0.9411 |
67
- | No log | 5.0 | 35 | 0.2037 | 0.4709 | 0.9417 | 0.9417 | nan | 0.9417 | 0.0 | 0.9417 |
68
- | No log | 6.0 | 42 | 0.1668 | 0.4662 | 0.9324 | 0.9324 | nan | 0.9324 | 0.0 | 0.9324 |
69
- | No log | 7.0 | 49 | 0.1421 | 0.4752 | 0.9503 | 0.9503 | nan | 0.9503 | 0.0 | 0.9503 |
70
- | No log | 8.0 | 56 | 0.1382 | 0.4773 | 0.9547 | 0.9547 | nan | 0.9547 | 0.0 | 0.9547 |
71
- | No log | 9.0 | 63 | 0.1588 | 0.4737 | 0.9473 | 0.9473 | nan | 0.9473 | 0.0 | 0.9473 |
72
- | No log | 10.0 | 70 | 0.1317 | 0.4845 | 0.9690 | 0.9690 | nan | 0.9690 | 0.0 | 0.9690 |
73
- | No log | 11.0 | 77 | 0.1307 | 0.4836 | 0.9671 | 0.9671 | nan | 0.9671 | 0.0 | 0.9671 |
74
- | No log | 12.0 | 84 | 0.1328 | 0.4899 | 0.9798 | 0.9798 | nan | 0.9798 | 0.0 | 0.9798 |
75
- | No log | 13.0 | 91 | 0.1265 | 0.4863 | 0.9725 | 0.9725 | nan | 0.9725 | 0.0 | 0.9725 |
76
- | No log | 14.0 | 98 | 0.1283 | 0.4886 | 0.9772 | 0.9772 | nan | 0.9772 | 0.0 | 0.9772 |
77
- | No log | 15.0 | 105 | 0.1286 | 0.4887 | 0.9775 | 0.9775 | nan | 0.9775 | 0.0 | 0.9775 |
78
- | No log | 16.0 | 112 | 0.1235 | 0.4894 | 0.9788 | 0.9788 | nan | 0.9788 | 0.0 | 0.9788 |
79
- | No log | 17.0 | 119 | 0.1213 | 0.4898 | 0.9795 | 0.9795 | nan | 0.9795 | 0.0 | 0.9795 |
80
- | No log | 18.0 | 126 | 0.1223 | 0.4910 | 0.9821 | 0.9821 | nan | 0.9821 | 0.0 | 0.9821 |
81
- | No log | 19.0 | 133 | 0.1179 | 0.4882 | 0.9763 | 0.9763 | nan | 0.9763 | 0.0 | 0.9763 |
82
- | No log | 20.0 | 140 | 0.1169 | 0.4914 | 0.9829 | 0.9829 | nan | 0.9829 | 0.0 | 0.9829 |
83
- | No log | 21.0 | 147 | 0.1153 | 0.4908 | 0.9816 | 0.9816 | nan | 0.9816 | 0.0 | 0.9816 |
84
- | No log | 22.0 | 154 | 0.1155 | 0.4902 | 0.9804 | 0.9804 | nan | 0.9804 | 0.0 | 0.9804 |
85
- | No log | 23.0 | 161 | 0.1143 | 0.4919 | 0.9839 | 0.9839 | nan | 0.9839 | 0.0 | 0.9839 |
86
- | No log | 24.0 | 168 | 0.1115 | 0.4913 | 0.9825 | 0.9825 | nan | 0.9825 | 0.0 | 0.9825 |
87
- | No log | 25.0 | 175 | 0.1113 | 0.4920 | 0.9841 | 0.9841 | nan | 0.9841 | 0.0 | 0.9841 |
88
- | No log | 26.0 | 182 | 0.1106 | 0.4923 | 0.9846 | 0.9846 | nan | 0.9846 | 0.0 | 0.9846 |
89
- | No log | 27.0 | 189 | 0.1097 | 0.4907 | 0.9814 | 0.9814 | nan | 0.9814 | 0.0 | 0.9814 |
90
- | No log | 28.0 | 196 | 0.1087 | 0.4908 | 0.9816 | 0.9816 | nan | 0.9816 | 0.0 | 0.9816 |
91
- | No log | 29.0 | 203 | 0.1094 | 0.4920 | 0.9840 | 0.9840 | nan | 0.9840 | 0.0 | 0.9840 |
92
- | No log | 30.0 | 210 | 0.1093 | 0.4911 | 0.9821 | 0.9821 | nan | 0.9821 | 0.0 | 0.9821 |
93
- | No log | 31.0 | 217 | 0.1091 | 0.4907 | 0.9814 | 0.9814 | nan | 0.9814 | 0.0 | 0.9814 |
94
 
95
 
96
  ### Framework versions
 
3
  license: other
4
  base_model: nvidia/mit-b0
5
  tags:
 
 
6
  - generated_from_trainer
7
  datasets:
8
  - generator
 
16
 
17
  # autocrop-bilder
18
 
19
+ This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the generator dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0335
22
+ - Mean Iou: 0.4974
23
+ - Mean Accuracy: 0.9949
24
+ - Overall Accuracy: 0.9949
25
  - Accuracy Background: nan
26
+ - Accuracy Crop: 0.9949
27
  - Iou Background: 0.0
28
+ - Iou Crop: 0.9949
29
 
30
  ## Model description
31
 
 
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Background | Accuracy Crop | Iou Background | Iou Crop |
60
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------:|:-------------:|:--------------:|:--------:|
61
+ | 0.3441 | 1.0 | 112 | 0.3192 | 0.4538 | 0.9076 | 0.9076 | nan | 0.9076 | 0.0 | 0.9076 |
62
+ | 0.1932 | 2.0 | 224 | 0.1654 | 0.4766 | 0.9533 | 0.9533 | nan | 0.9533 | 0.0 | 0.9533 |
63
+ | 0.1221 | 3.0 | 336 | 0.1087 | 0.4917 | 0.9834 | 0.9834 | nan | 0.9834 | 0.0 | 0.9834 |
64
+ | 0.0911 | 4.0 | 448 | 0.0790 | 0.4938 | 0.9877 | 0.9877 | nan | 0.9877 | 0.0 | 0.9877 |
65
+ | 0.0819 | 5.0 | 560 | 0.0690 | 0.4939 | 0.9879 | 0.9879 | nan | 0.9879 | 0.0 | 0.9879 |
66
+ | 0.0767 | 6.0 | 672 | 0.0615 | 0.4915 | 0.9830 | 0.9830 | nan | 0.9830 | 0.0 | 0.9830 |
67
+ | 0.0587 | 7.0 | 784 | 0.0567 | 0.4966 | 0.9931 | 0.9931 | nan | 0.9931 | 0.0 | 0.9931 |
68
+ | 0.0702 | 8.0 | 896 | 0.0528 | 0.4951 | 0.9902 | 0.9902 | nan | 0.9902 | 0.0 | 0.9902 |
69
+ | 0.0721 | 9.0 | 1008 | 0.0472 | 0.4963 | 0.9926 | 0.9926 | nan | 0.9926 | 0.0 | 0.9926 |
70
+ | 0.0584 | 10.0 | 1120 | 0.0456 | 0.4943 | 0.9886 | 0.9886 | nan | 0.9886 | 0.0 | 0.9886 |
71
+ | 0.0497 | 11.0 | 1232 | 0.0461 | 0.4923 | 0.9846 | 0.9846 | nan | 0.9846 | 0.0 | 0.9846 |
72
+ | 0.0457 | 12.0 | 1344 | 0.0412 | 0.4949 | 0.9897 | 0.9897 | nan | 0.9897 | 0.0 | 0.9897 |
73
+ | 0.0434 | 13.0 | 1456 | 0.0439 | 0.4913 | 0.9826 | 0.9826 | nan | 0.9826 | 0.0 | 0.9826 |
74
+ | 0.0446 | 14.0 | 1568 | 0.0392 | 0.4956 | 0.9912 | 0.9912 | nan | 0.9912 | 0.0 | 0.9912 |
75
+ | 0.0382 | 15.0 | 1680 | 0.0386 | 0.4951 | 0.9901 | 0.9901 | nan | 0.9901 | 0.0 | 0.9901 |
76
+ | 0.0505 | 16.0 | 1792 | 0.0384 | 0.4938 | 0.9876 | 0.9876 | nan | 0.9876 | 0.0 | 0.9876 |
77
+ | 0.0428 | 17.0 | 1904 | 0.0376 | 0.4958 | 0.9915 | 0.9915 | nan | 0.9915 | 0.0 | 0.9915 |
78
+ | 0.0399 | 18.0 | 2016 | 0.0378 | 0.4968 | 0.9935 | 0.9935 | nan | 0.9935 | 0.0 | 0.9935 |
79
+ | 0.0411 | 19.0 | 2128 | 0.0362 | 0.4965 | 0.9931 | 0.9931 | nan | 0.9931 | 0.0 | 0.9931 |
80
+ | 0.0393 | 20.0 | 2240 | 0.0368 | 0.4952 | 0.9904 | 0.9904 | nan | 0.9904 | 0.0 | 0.9904 |
81
+ | 0.0364 | 21.0 | 2352 | 0.0357 | 0.4968 | 0.9936 | 0.9936 | nan | 0.9936 | 0.0 | 0.9936 |
82
+ | 0.0382 | 22.0 | 2464 | 0.0367 | 0.4963 | 0.9926 | 0.9926 | nan | 0.9926 | 0.0 | 0.9926 |
83
+ | 0.0397 | 23.0 | 2576 | 0.0353 | 0.4972 | 0.9944 | 0.9944 | nan | 0.9944 | 0.0 | 0.9944 |
84
+ | 0.0357 | 24.0 | 2688 | 0.0331 | 0.4958 | 0.9916 | 0.9916 | nan | 0.9916 | 0.0 | 0.9916 |
85
+ | 0.0433 | 25.0 | 2800 | 0.0332 | 0.4957 | 0.9914 | 0.9914 | nan | 0.9914 | 0.0 | 0.9914 |
86
+ | 0.0404 | 26.0 | 2912 | 0.0355 | 0.4962 | 0.9924 | 0.9924 | nan | 0.9924 | 0.0 | 0.9924 |
87
+ | 0.0308 | 27.0 | 3024 | 0.0329 | 0.4963 | 0.9925 | 0.9925 | nan | 0.9925 | 0.0 | 0.9925 |
88
+ | 0.0391 | 28.0 | 3136 | 0.0315 | 0.4959 | 0.9918 | 0.9918 | nan | 0.9918 | 0.0 | 0.9918 |
89
+ | 0.0321 | 29.0 | 3248 | 0.0317 | 0.4968 | 0.9936 | 0.9936 | nan | 0.9936 | 0.0 | 0.9936 |
90
+ | 0.0292 | 30.0 | 3360 | 0.0332 | 0.4972 | 0.9945 | 0.9945 | nan | 0.9945 | 0.0 | 0.9945 |
91
+ | 0.0258 | 31.0 | 3472 | 0.0335 | 0.4974 | 0.9949 | 0.9949 | nan | 0.9949 | 0.0 | 0.9949 |
92
 
93
 
94
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a626dfbf5196d7af47d5b6b392ce93dc90605d4983966b4e5942e7227bd10dff
3
  size 14884776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8629293ea2977ffe981057728b3833d43e760edcb44096f26bf5438f5a0a029b
3
  size 14884776