Hugging Face's logo

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

Image Segmentation
Transformers
TensorBoard
Safetensors
segformer
vision
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
PushkarA07 commited on
Commit
431fcfd
·
verified ·
1 Parent(s): 6c154b0

End of training

Browse files
Files changed (5) hide show
  1. README.md +32 -24
  2. config.json +4 -4
  3. model.safetensors +1 -1
  4. runs/Oct01_09-07-39_085488a1e323/events.out.tfevents.1727773671.085488a1e323.1115.0 +3 -0
  5. 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: 0.8847
22
- - Mean Iou: 0.3706
23
- - Mean Accuracy: 0.6794
24
- - Overall Accuracy: 0.9001
25
- - Accuracy Background: nan
26
- - Accuracy Benign Breast Cancer: 0.4671
27
- - Accuracy Malignant Breast Cancer: 0.6340
28
- - Accuracy Ignore: 0.9373
29
- - Iou Background: 0.0
30
- - Iou Benign Breast Cancer: 0.2793
31
- - Iou Malignant Breast Cancer: 0.2886
32
- - Iou Ignore: 0.9144
33
 
34
  ## Model description
35
 
@@ -54,20 +54,28 @@ The following hyperparameters were used during training:
54
  - seed: 42
55
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
56
  - lr_scheduler_type: linear
57
- - num_epochs: 5
58
 
59
  ### Training results
60
 
61
- | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy Background | Accuracy Benign Breast Cancer | Accuracy Malignant Breast Cancer | Accuracy Ignore | Iou Background | Iou Benign Breast Cancer | Iou Malignant Breast Cancer | Iou Ignore |
62
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------:|:-----------------------------:|:--------------------------------:|:---------------:|:--------------:|:------------------------:|:---------------------------:|:----------:|
63
- | 1.1874 | 0.625 | 10 | 1.3226 | 0.2354 | 0.6369 | 0.6665 | nan | 0.5183 | 0.7181 | 0.6743 | 0.0 | 0.1107 | 0.1633 | 0.6677 |
64
- | 1.1383 | 1.25 | 20 | 1.1954 | 0.3233 | 0.6755 | 0.8512 | nan | 0.4058 | 0.7368 | 0.8840 | 0.0 | 0.2166 | 0.2110 | 0.8656 |
65
- | 1.0144 | 1.875 | 30 | 1.1280 | 0.3353 | 0.7478 | 0.8223 | nan | 0.7394 | 0.6711 | 0.8329 | 0.0 | 0.2411 | 0.2773 | 0.8228 |
66
- | 0.9034 | 2.5 | 40 | 0.9430 | 0.3031 | 0.6187 | 0.8756 | nan | 0.1216 | 0.8078 | 0.9267 | 0.0 | 0.0987 | 0.2063 | 0.9073 |
67
- | 1.0802 | 3.125 | 50 | 0.8730 | 0.3152 | 0.6227 | 0.8809 | nan | 0.1788 | 0.7588 | 0.9306 | 0.0 | 0.1297 | 0.2209 | 0.9101 |
68
- | 0.8259 | 3.75 | 60 | 0.8087 | 0.3601 | 0.6257 | 0.9087 | nan | 0.3522 | 0.5685 | 0.9564 | 0.0 | 0.2487 | 0.2669 | 0.9247 |
69
- | 0.8869 | 4.375 | 70 | 0.8426 | 0.3574 | 0.6592 | 0.8962 | nan | 0.4059 | 0.6350 | 0.9369 | 0.0 | 0.2526 | 0.2641 | 0.9129 |
70
- | 0.8538 | 5.0 | 80 | 0.8847 | 0.3706 | 0.6794 | 0.9001 | nan | 0.4671 | 0.6340 | 0.9373 | 0.0 | 0.2793 | 0.2886 | 0.9144 |
 
 
 
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
 
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: 0.4728
22
+ - Mean Iou: 0.3187
23
+ - Mean Accuracy: 0.4465
24
+ - Overall Accuracy: 0.9385
25
+ - Accuracy Ignore: nan
26
+ - Accuracy Benign Breast Cancer: 0.0
27
+ - Accuracy Malignant Breast Cancer: 0.3489
28
+ - Accuracy Background: 0.9906
29
+ - Iou Ignore: 0.0
30
+ - Iou Benign Breast Cancer: 0.0
31
+ - Iou Malignant Breast Cancer: 0.3338
32
+ - Iou Background: 0.9412
33
 
34
  ## Model description
35
 
 
54
  - seed: 42
55
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
56
  - lr_scheduler_type: linear
57
+ - num_epochs: 10
58
 
59
  ### Training results
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
+ | 1.1385 | 0.625 | 10 | 1.2920 | 0.2845 | 0.6989 | 0.8518 | nan | 0.8653 | 0.3362 | 0.8953 | 0.0 | 0.0204 | 0.2461 | 0.8714 |
64
+ | 1.0733 | 1.25 | 20 | 1.1383 | 0.2877 | 0.4681 | 0.8785 | nan | 0.1718 | 0.3038 | 0.9287 | 0.0 | 0.0050 | 0.2442 | 0.9017 |
65
+ | 0.9911 | 1.875 | 30 | 0.9850 | 0.3005 | 0.6236 | 0.8853 | nan | 0.5131 | 0.4335 | 0.9243 | 0.0 | 0.0242 | 0.2787 | 0.8990 |
66
+ | 0.9285 | 2.5 | 40 | 0.7954 | 0.3396 | 0.6975 | 0.9164 | nan | 0.6465 | 0.4931 | 0.9527 | 0.0 | 0.0906 | 0.3522 | 0.9156 |
67
+ | 0.7114 | 3.125 | 50 | 0.6539 | 0.3229 | 0.5058 | 0.9292 | nan | 0.1553 | 0.3852 | 0.9770 | 0.0 | 0.0249 | 0.3372 | 0.9296 |
68
+ | 0.725 | 3.75 | 60 | 0.5886 | 0.3291 | 0.4826 | 0.9261 | nan | 0.0 | 0.4822 | 0.9658 | 0.0 | 0.0 | 0.3890 | 0.9272 |
69
+ | 0.7755 | 4.375 | 70 | 0.5801 | 0.3060 | 0.4322 | 0.9225 | nan | 0.0 | 0.3210 | 0.9755 | 0.0 | 0.0 | 0.2909 | 0.9331 |
70
+ | 0.5846 | 5.0 | 80 | 0.6225 | 0.2787 | 0.4098 | 0.9204 | nan | 0.0624 | 0.1822 | 0.9848 | 0.0 | 0.0049 | 0.1761 | 0.9340 |
71
+ | 0.5753 | 5.625 | 90 | 0.5340 | 0.3242 | 0.4586 | 0.9365 | nan | 0.0 | 0.3909 | 0.9848 | 0.0 | 0.0 | 0.3568 | 0.9401 |
72
+ | 0.5912 | 6.25 | 100 | 0.5389 | 0.3212 | 0.4580 | 0.9352 | nan | 0.0 | 0.3907 | 0.9834 | 0.0 | 0.0 | 0.3478 | 0.9368 |
73
+ | 0.5518 | 6.875 | 110 | 0.5188 | 0.3151 | 0.4470 | 0.9340 | nan | 0.0 | 0.3558 | 0.9851 | 0.0 | 0.0 | 0.3230 | 0.9373 |
74
+ | 0.4876 | 7.5 | 120 | 0.5076 | 0.3452 | 0.4905 | 0.9435 | nan | 0.0 | 0.4873 | 0.9843 | 0.0 | 0.0 | 0.4360 | 0.9450 |
75
+ | 0.5017 | 8.125 | 130 | 0.4774 | 0.3104 | 0.4356 | 0.9351 | nan | 0.0009 | 0.3164 | 0.9896 | 0.0 | 0.0001 | 0.3023 | 0.9391 |
76
+ | 0.4706 | 8.75 | 140 | 0.4785 | 0.3149 | 0.4514 | 0.9357 | nan | 0.0349 | 0.3304 | 0.9889 | 0.0 | 0.0057 | 0.3153 | 0.9388 |
77
+ | 0.5787 | 9.375 | 150 | 0.4723 | 0.3203 | 0.4492 | 0.9390 | nan | 0.0 | 0.3571 | 0.9904 | 0.0 | 0.0 | 0.3402 | 0.9411 |
78
+ | 0.5399 | 10.0 | 160 | 0.4728 | 0.3187 | 0.4465 | 0.9385 | nan | 0.0 | 0.3489 | 0.9906 | 0.0 | 0.0 | 0.3338 | 0.9412 |
79
 
80
 
81
  ### Framework versions
config.json CHANGED
@@ -28,17 +28,17 @@
28
  256
29
  ],
30
  "id2label": {
31
- "0": "background",
32
  "1": "benign_breast_cancer",
33
  "2": "malignant_breast_cancer",
34
- "3": "ignore"
35
  },
36
  "image_size": 224,
37
  "initializer_range": 0.02,
38
  "label2id": {
39
- "background": 0,
40
  "benign_breast_cancer": 1,
41
- "ignore": 3,
42
  "malignant_breast_cancer": 2
43
  },
44
  "layer_norm_eps": 1e-06,
 
28
  256
29
  ],
30
  "id2label": {
31
+ "0": "ignore",
32
  "1": "benign_breast_cancer",
33
  "2": "malignant_breast_cancer",
34
+ "3": "background"
35
  },
36
  "image_size": 224,
37
  "initializer_range": 0.02,
38
  "label2id": {
39
+ "background": 3,
40
  "benign_breast_cancer": 1,
41
+ "ignore": 0,
42
  "malignant_breast_cancer": 2
43
  },
44
  "layer_norm_eps": 1e-06,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbda491b36617c5eac8265b75dfb281dcf3c16277fdc2d97330b6fdeb2050589
3
  size 14886832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:689bbf6b51ac74f0eb7c5df59be048b1de4b0e591fa53f982970063fdf7f432a
3
  size 14886832
runs/Oct01_09-07-39_085488a1e323/events.out.tfevents.1727773671.085488a1e323.1115.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e22e84f1fb6d58a2da3f3c6e8d70feac22fb0fb79979e2b0636a9da868d5bb0
3
+ size 54412
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b581094af81420d418c6568955267ed08a83c3da4a7bfb14dcbf97ea33ca4b82
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0711a15757309c60b67c00037bcf7d9184d52da180e9250f9ae0ff9e665204e4
3
  size 5240