Update README.md
Browse files
README.md
CHANGED
@@ -15,24 +15,21 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# vitforimcls
|
17 |
|
18 |
-
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
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.1199
|
21 |
- Accuracy: 0.9678
|
22 |
|
23 |
## Model description
|
24 |
|
25 |
-
|
26 |
-
|
27 |
-
## Intended uses & limitations
|
28 |
-
|
29 |
-
More information needed
|
30 |
|
31 |
## Training and evaluation data
|
32 |
|
33 |
-
|
34 |
|
35 |
## Training procedure
|
|
|
36 |
|
37 |
### Training hyperparameters
|
38 |
|
|
|
15 |
|
16 |
# vitforimcls
|
17 |
|
18 |
+
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 [CIFAR10](https://huggingface.co/datasets/Andron00e/CIFAR10-custom) dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.1199
|
21 |
- Accuracy: 0.9678
|
22 |
|
23 |
## Model description
|
24 |
|
25 |
+
[A detailed description of model architecture can be found here](https://github.com/huggingface/transformers/blob/main/src/transformers/models/vit/modeling_vit.py#L756)
|
|
|
|
|
|
|
|
|
26 |
|
27 |
## Training and evaluation data
|
28 |
|
29 |
+
[CIFAR10](https://huggingface.co/datasets/Andron00e/CIFAR10-custom)
|
30 |
|
31 |
## Training procedure
|
32 |
+
Straightforward tuning of all model's parameters.
|
33 |
|
34 |
### Training hyperparameters
|
35 |
|