Update README.md
Browse files
README.md
CHANGED
@@ -31,7 +31,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
31 |
This model returns the artwork style of any image input.
|
32 |
|
33 |
|
34 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset. This is a subset of the artbench-10 dataset, with a train set of 1000 artworks per class and a test set of 100 artworks per class.
|
35 |
It achieves the following results on the evaluation set:
|
36 |
- Loss: 1.1392
|
37 |
- Accuracy: 0.5948
|
|
|
31 |
This model returns the artwork style of any image input.
|
32 |
|
33 |
|
34 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset. This is a subset of the artbench-10 dataset (https://www.kaggle.com/datasets/alexanderliao/artbench10), with a train set of 1000 artworks per class and a test set of 100 artworks per class.
|
35 |
It achieves the following results on the evaluation set:
|
36 |
- Loss: 1.1392
|
37 |
- Accuracy: 0.5948
|