Hugging Face's logo

bombshelll
/
swin-brain-modality-classification

Image Classification
Transformers
Safetensors
swin
Generated from Trainer
Inference Endpoints
Model card Files Community
bombshelll commited on
Commit
ae399dd
·
verified ·
1 Parent(s): 3cd8a62

Model save

Browse files
Files changed (1) hide show
  1. README.md +7 -23
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: 0.2871
22
- - Accuracy: 0.9116
23
 
24
  ## Model description
25
 
@@ -51,27 +51,11 @@ The following hyperparameters were used during training:
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
- |:-------------:|:-------:|:----:|:---------------:|:--------:|
56
- | 1.3069 | 0.9412 | 12 | 1.0000 | 0.6077 |
57
- | 0.8924 | 1.9608 | 25 | 0.4334 | 0.8785 |
58
- | 0.5365 | 2.9804 | 38 | 0.3143 | 0.9006 |
59
- | 0.3814 | 4.0 | 51 | 0.2871 | 0.9116 |
60
- | 0.3336 | 4.9412 | 63 | 0.2963 | 0.9116 |
61
- | 0.353 | 5.9608 | 76 | 0.3195 | 0.8729 |
62
- | 0.3069 | 6.9804 | 89 | 0.2952 | 0.9116 |
63
- | 0.293 | 8.0 | 102 | 0.3174 | 0.8895 |
64
- | 0.2667 | 8.9412 | 114 | 0.3226 | 0.8950 |
65
- | 0.2424 | 9.9608 | 127 | 0.3213 | 0.8895 |
66
- | 0.2605 | 10.9804 | 140 | 0.3172 | 0.8895 |
67
- | 0.232 | 12.0 | 153 | 0.3385 | 0.8895 |
68
- | 0.242 | 12.9412 | 165 | 0.3274 | 0.8950 |
69
- | 0.215 | 13.9608 | 178 | 0.3385 | 0.8950 |
70
- | 0.2131 | 14.9804 | 191 | 0.3422 | 0.8950 |
71
- | 0.201 | 16.0 | 204 | 0.3419 | 0.8785 |
72
- | 0.1976 | 16.9412 | 216 | 0.3448 | 0.9006 |
73
- | 0.1886 | 17.9608 | 229 | 0.3460 | 0.8895 |
74
- | 0.1972 | 18.8235 | 240 | 0.3453 | 0.8895 |
75
 
76
 
77
  ### 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: 0.0268
22
+ - Accuracy: 0.9911
23
 
24
  ## Model description
25
 
 
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
56
+ | 1.364 | 1.0 | 16 | 0.6508 | 0.8267 |
57
+ | 0.2053 | 2.0 | 32 | 0.0802 | 0.9556 |
58
+ | 0.0841 | 3.0 | 48 | 0.0268 | 0.9911 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions