Hugging Face's logo

PushkarA07
/
segformer-b0-finetuned-breastcancer-oct-1

Image Segmentation
Transformers
TensorBoard
Safetensors
segformer
vision
Generated from Trainer
Model card Files Metrics Community
PushkarA07 commited on
Commit
204f30c
·
verified ·
1 Parent(s): ed43aa2

End of training

Browse files
Files changed (3) hide show
  1. README.md +31 -31
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
- base_model: nvidia/mit-b0
3
  library_name: transformers
4
  license: other
 
5
  tags:
6
  - vision
7
  - image-segmentation
@@ -18,18 +18,18 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the as-cle-bert/breastcancer-semantic-segmentation dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.5516
22
- - Mean Iou: 0.3444
23
- - Mean Accuracy: 0.3844
24
- - Overall Accuracy: 0.9236
25
- - Accuracy Ignore: 0.0056
26
- - Accuracy Benign Breast Cancer: 0.4177
27
- - Accuracy Malignant Breast Cancer: 0.1359
28
- - Accuracy Background: 0.9785
29
- - Iou Ignore: 0.0056
30
- - Iou Benign Breast Cancer: 0.3797
31
- - Iou Malignant Breast Cancer: 0.0582
32
- - Iou Background: 0.9340
33
 
34
  ## Model description
35
 
@@ -60,27 +60,27 @@ The following hyperparameters were used during training:
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Ignore | Accuracy Benign Breast Cancer | Accuracy Malignant Breast Cancer | Accuracy Background | Iou Ignore | Iou Benign Breast Cancer | Iou Malignant Breast Cancer | Iou Background |
62
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:---------------:|:-----------------------------:|:--------------------------------:|:-------------------:|:----------:|:------------------------:|:---------------------------:|:--------------:|
63
- | 1.1479 | 0.625 | 10 | 1.3331 | 0.1737 | 0.2588 | 0.6397 | 0.0 | 0.0031 | 0.3436 | 0.6886 | 0.0 | 0.0027 | 0.0201 | 0.6721 |
64
- | 1.1481 | 1.25 | 20 | 1.2194 | 0.2470 | 0.3065 | 0.7987 | 0.0 | 0.3653 | 0.0126 | 0.8483 | 0.0 | 0.1676 | 0.0021 | 0.8182 |
65
- | 1.0335 | 1.875 | 30 | 1.0848 | 0.2702 | 0.3128 | 0.8358 | 0.0355 | 0.2158 | 0.1048 | 0.8949 | 0.0222 | 0.1806 | 0.0160 | 0.8620 |
66
- | 0.9269 | 2.5 | 40 | 0.9807 | 0.2538 | 0.2823 | 0.8538 | 0.0348 | 0.0961 | 0.0763 | 0.9220 | 0.0284 | 0.0859 | 0.0127 | 0.8881 |
67
- | 0.8648 | 3.125 | 50 | 0.8266 | 0.2618 | 0.2886 | 0.8743 | 0.0219 | 0.1346 | 0.0553 | 0.9427 | 0.0202 | 0.1158 | 0.0123 | 0.8990 |
68
- | 0.7287 | 3.75 | 60 | 0.8243 | 0.2666 | 0.3122 | 0.8618 | 0.0182 | 0.1573 | 0.1473 | 0.9258 | 0.0175 | 0.1320 | 0.0273 | 0.8895 |
69
- | 0.7918 | 4.375 | 70 | 0.7138 | 0.2950 | 0.3269 | 0.8923 | 0.0195 | 0.2674 | 0.0664 | 0.9544 | 0.0181 | 0.2342 | 0.0183 | 0.9094 |
70
- | 0.7872 | 5.0 | 80 | 0.7139 | 0.3070 | 0.3538 | 0.8940 | 0.0191 | 0.3154 | 0.1284 | 0.9521 | 0.0173 | 0.2639 | 0.0354 | 0.9115 |
71
- | 0.7064 | 5.625 | 90 | 0.6391 | 0.3200 | 0.3536 | 0.9148 | 0.0157 | 0.3358 | 0.0884 | 0.9745 | 0.0150 | 0.3025 | 0.0331 | 0.9294 |
72
- | 0.6489 | 6.25 | 100 | 0.6452 | 0.3183 | 0.3616 | 0.9046 | 0.0121 | 0.3251 | 0.1465 | 0.9628 | 0.0117 | 0.2952 | 0.0416 | 0.9245 |
73
- | 0.5608 | 6.875 | 110 | 0.5897 | 0.3331 | 0.3705 | 0.9197 | 0.0064 | 0.3715 | 0.1271 | 0.9770 | 0.0063 | 0.3441 | 0.0483 | 0.9337 |
74
- | 0.5968 | 7.5 | 120 | 0.5886 | 0.2983 | 0.3347 | 0.9089 | 0.0062 | 0.2228 | 0.1360 | 0.9737 | 0.0062 | 0.2149 | 0.0419 | 0.9301 |
75
- | 0.5498 | 8.125 | 130 | 0.5839 | 0.3071 | 0.3412 | 0.9112 | 0.0086 | 0.2622 | 0.1197 | 0.9743 | 0.0084 | 0.2511 | 0.0389 | 0.9300 |
76
- | 0.5045 | 8.75 | 140 | 0.5960 | 0.3218 | 0.3669 | 0.9062 | 0.0061 | 0.3473 | 0.1508 | 0.9633 | 0.0061 | 0.3127 | 0.0453 | 0.9229 |
77
- | 0.5396 | 9.375 | 150 | 0.5783 | 0.3193 | 0.3597 | 0.9125 | 0.0066 | 0.3140 | 0.1464 | 0.9721 | 0.0066 | 0.2925 | 0.0482 | 0.9298 |
78
- | 0.6604 | 10.0 | 160 | 0.5516 | 0.3444 | 0.3844 | 0.9236 | 0.0056 | 0.4177 | 0.1359 | 0.9785 | 0.0056 | 0.3797 | 0.0582 | 0.9340 |
79
 
80
 
81
  ### Framework versions
82
 
83
  - Transformers 4.44.2
84
- - Pytorch 2.4.1+cu121
85
- - Datasets 3.0.1
86
  - Tokenizers 0.19.1
 
1
  ---
 
2
  library_name: transformers
3
  license: other
4
+ base_model: nvidia/mit-b0
5
  tags:
6
  - vision
7
  - image-segmentation
 
18
 
19
  This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the as-cle-bert/breastcancer-semantic-segmentation dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.5929
22
+ - Mean Iou: 0.3697
23
+ - Mean Accuracy: 0.4304
24
+ - Overall Accuracy: 0.8938
25
+ - Accuracy Ignore: 0.1439
26
+ - Accuracy Benign Breast Cancer: 0.2911
27
+ - Accuracy Malignant Breast Cancer: 0.3033
28
+ - Accuracy Background: 0.9835
29
+ - Iou Ignore: 0.1083
30
+ - Iou Benign Breast Cancer: 0.2002
31
+ - Iou Malignant Breast Cancer: 0.2707
32
+ - Iou Background: 0.8995
33
 
34
  ## Model description
35
 
 
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Ignore | Accuracy Benign Breast Cancer | Accuracy Malignant Breast Cancer | Accuracy Background | Iou Ignore | Iou Benign Breast Cancer | Iou Malignant Breast Cancer | Iou Background |
62
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:---------------:|:-----------------------------:|:--------------------------------:|:-------------------:|:----------:|:------------------------:|:---------------------------:|:--------------:|
63
+ | 1.2085 | 0.625 | 10 | 1.3371 | 0.2725 | 0.3749 | 0.7828 | 0.0304 | 0.2701 | 0.3474 | 0.8519 | 0.0035 | 0.0999 | 0.1818 | 0.8046 |
64
+ | 1.0916 | 1.25 | 20 | 1.2205 | 0.3076 | 0.3659 | 0.8755 | 0.0790 | 0.1894 | 0.2199 | 0.9754 | 0.0266 | 0.1231 | 0.1986 | 0.8820 |
65
+ | 1.0192 | 1.875 | 30 | 1.0365 | 0.3451 | 0.4120 | 0.8845 | 0.1439 | 0.2225 | 0.3074 | 0.9744 | 0.0524 | 0.1782 | 0.2617 | 0.8879 |
66
+ | 0.8858 | 2.5 | 40 | 0.9036 | 0.3147 | 0.3957 | 0.8707 | 0.1926 | 0.0816 | 0.3512 | 0.9573 | 0.0443 | 0.0738 | 0.2648 | 0.8761 |
67
+ | 0.7886 | 3.125 | 50 | 0.8572 | 0.3055 | 0.3844 | 0.8596 | 0.1766 | 0.1460 | 0.2618 | 0.9531 | 0.0620 | 0.0901 | 0.2061 | 0.8637 |
68
+ | 0.7061 | 3.75 | 60 | 0.7466 | 0.3229 | 0.3884 | 0.8787 | 0.1641 | 0.1298 | 0.2871 | 0.9727 | 0.0662 | 0.1029 | 0.2407 | 0.8820 |
69
+ | 0.7679 | 4.375 | 70 | 0.7367 | 0.3172 | 0.3833 | 0.8790 | 0.1766 | 0.0952 | 0.2873 | 0.9740 | 0.0659 | 0.0746 | 0.2458 | 0.8824 |
70
+ | 0.754 | 5.0 | 80 | 0.7271 | 0.3196 | 0.3846 | 0.8800 | 0.1746 | 0.1306 | 0.2556 | 0.9778 | 0.0707 | 0.0976 | 0.2264 | 0.8837 |
71
+ | 0.6705 | 5.625 | 90 | 0.6677 | 0.3286 | 0.3967 | 0.8815 | 0.1714 | 0.1968 | 0.2388 | 0.9796 | 0.0777 | 0.1352 | 0.2146 | 0.8871 |
72
+ | 0.7758 | 6.25 | 100 | 0.6278 | 0.3315 | 0.3980 | 0.8835 | 0.1630 | 0.2416 | 0.2025 | 0.9848 | 0.0979 | 0.1462 | 0.1896 | 0.8922 |
73
+ | 0.6866 | 6.875 | 110 | 0.6230 | 0.3489 | 0.4119 | 0.8887 | 0.1641 | 0.2351 | 0.2649 | 0.9837 | 0.0981 | 0.1614 | 0.2424 | 0.8938 |
74
+ | 0.5664 | 7.5 | 120 | 0.6334 | 0.3545 | 0.4154 | 0.8903 | 0.1638 | 0.2064 | 0.3102 | 0.9811 | 0.0982 | 0.1506 | 0.2751 | 0.8940 |
75
+ | 0.6008 | 8.125 | 130 | 0.6034 | 0.3478 | 0.4016 | 0.8907 | 0.1418 | 0.2122 | 0.2660 | 0.9866 | 0.1012 | 0.1477 | 0.2470 | 0.8952 |
76
+ | 0.5459 | 8.75 | 140 | 0.5930 | 0.3661 | 0.4277 | 0.8934 | 0.1616 | 0.2505 | 0.3161 | 0.9828 | 0.1042 | 0.1866 | 0.2734 | 0.9001 |
77
+ | 0.5619 | 9.375 | 150 | 0.5966 | 0.3695 | 0.4306 | 0.8937 | 0.1365 | 0.3089 | 0.2929 | 0.9841 | 0.1078 | 0.2067 | 0.2633 | 0.9000 |
78
+ | 0.5807 | 10.0 | 160 | 0.5929 | 0.3697 | 0.4304 | 0.8938 | 0.1439 | 0.2911 | 0.3033 | 0.9835 | 0.1083 | 0.2002 | 0.2707 | 0.8995 |
79
 
80
 
81
  ### Framework versions
82
 
83
  - Transformers 4.44.2
84
+ - Pytorch 2.5.0+cu121
85
+ - Datasets 3.1.0
86
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed8304b2ec843e704e310de54a34aeb7a47d9aff06b0bb9154022fbab24698db
3
  size 14886832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06c22ee3dac3ad7a7a0a17a622d991152ff63f9dd279b41692b6f59e59c0cb7d
3
  size 14886832
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:811ec3ac684e0a03d9cb0047ba4a920751bce650222698db0b81f5f2d7618285
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fa56347747d287feca1ff67ec9f7080eb404afd99feb9f83c9671a6110d5e66
3
  size 5240