Hugging Face's logo

bombshelll
/
swin-brain-abnormalities-classification

Image Classification
Transformers
Safetensors
swin
Generated from Trainer
Model card Files
xet
Community
bombshelll commited on
Commit
d4097c6
·
verified ·
1 Parent(s): 1bb094a

Model save

Browse files
Files changed (2) hide show
  1. README.md +15 -25
  2. model.safetensors +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.1044
22
- - Accuracy: 0.9729
23
 
24
  ## Model description
25
 
@@ -47,32 +47,22 @@ The following hyperparameters were used during training:
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_ratio: 0.1
50
- - num_epochs: 20
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
- |:-------------:|:-------:|:----:|:---------------:|:--------:|
56
- | 0.772 | 0.9639 | 20 | 0.7443 | 0.7186 |
57
- | 0.4795 | 1.9759 | 41 | 0.2960 | 0.8949 |
58
- | 0.2744 | 2.9880 | 62 | 0.2202 | 0.9254 |
59
- | 0.2865 | 4.0 | 83 | 0.1597 | 0.9525 |
60
- | 0.1684 | 4.9639 | 103 | 0.1245 | 0.9559 |
61
- | 0.1821 | 5.9759 | 124 | 0.1032 | 0.9695 |
62
- | 0.1717 | 6.9880 | 145 | 0.0971 | 0.9661 |
63
- | 0.1524 | 8.0 | 166 | 0.1139 | 0.9695 |
64
- | 0.1455 | 8.9639 | 186 | 0.0923 | 0.9695 |
65
- | 0.105 | 9.9759 | 207 | 0.0939 | 0.9695 |
66
- | 0.1215 | 10.9880 | 228 | 0.0969 | 0.9695 |
67
- | 0.0752 | 12.0 | 249 | 0.1031 | 0.9593 |
68
- | 0.0987 | 12.9639 | 269 | 0.0960 | 0.9695 |
69
- | 0.1087 | 13.9759 | 290 | 0.1018 | 0.9661 |
70
- | 0.0976 | 14.9880 | 311 | 0.1114 | 0.9695 |
71
- | 0.0868 | 16.0 | 332 | 0.1007 | 0.9695 |
72
- | 0.0719 | 16.9639 | 352 | 0.1068 | 0.9695 |
73
- | 0.0733 | 17.9759 | 373 | 0.1067 | 0.9695 |
74
- | 0.0883 | 18.9880 | 394 | 0.1047 | 0.9729 |
75
- | 0.0686 | 19.2771 | 400 | 0.1044 | 0.9729 |
76
 
77
 
78
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.1182
22
+ - Accuracy: 0.9593
23
 
24
  ## Model description
25
 
 
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 10
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
56
+ | 0.6863 | 0.9639 | 20 | 0.5909 | 0.7220 |
57
+ | 0.3386 | 1.9759 | 41 | 0.2170 | 0.9288 |
58
+ | 0.2839 | 2.9880 | 62 | 0.2721 | 0.8983 |
59
+ | 0.2548 | 4.0 | 83 | 0.1851 | 0.9288 |
60
+ | 0.1693 | 4.9639 | 103 | 0.1446 | 0.9424 |
61
+ | 0.1564 | 5.9759 | 124 | 0.1409 | 0.9458 |
62
+ | 0.1755 | 6.9880 | 145 | 0.1392 | 0.9559 |
63
+ | 0.1487 | 8.0 | 166 | 0.1254 | 0.9593 |
64
+ | 0.1453 | 8.9639 | 186 | 0.1220 | 0.9559 |
65
+ | 0.1215 | 9.6386 | 200 | 0.1182 | 0.9593 |
 
 
 
 
 
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f0628e577495a16e288e6d146968cfc5d3305d67fcccae1ff5da2eef7e96726
3
  size 110345908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c20bb0f2e4ca78d6678cbc24e58c651cb11e6a1698191be4c5a0827489e934b
3
  size 110345908