bombshelll
/

swin-brain-abnormalities-classification

Image Classification

Generated from Trainer

Model card Files Files and versions

bombshelll commited on Nov 2, 2024

Commit

e4b3017

·

verified ·

1 Parent(s): fcccb22

Model save

Files changed (1) hide show

README.md +6 -7

README.md CHANGED Viewed

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 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.
 It achieves the following results on the evaluation set:
-- Loss: 0.1269
-- Accuracy: 0.9540
 ## Model description
@@ -53,11 +53,10 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.3828        | 0.9778 | 33   | 0.1775          | 0.9477   |
-| 0.2035        | 1.9852 | 67   | 0.1269          | 0.9540   |
-| 0.1169        | 2.9926 | 101  | 0.2979          | 0.8954   |
-| 0.1092        | 4.0    | 135  | 0.1345          | 0.9498   |
-| 0.0882        | 4.8889 | 165  | 0.1955          | 0.9268   |
 ### Framework versions

 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.
 It achieves the following results on the evaluation set:
+- Loss: 0.0734
+- Accuracy: 0.9833
 ## Model description
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.3104        | 0.9778 | 33   | 0.2580          | 0.8996   |
+| 0.2147        | 1.9852 | 67   | 0.1770          | 0.9289   |
+| 0.1687        | 2.9926 | 101  | 0.1266          | 0.9519   |
+| 0.1158        | 4.0    | 135  | 0.0734          | 0.9833   |
 ### Framework versions