Update README.md
Browse files
README.md
CHANGED
@@ -19,8 +19,7 @@ pipeline_tag: image-classification
|
|
19 |
|
20 |
# Human-Action-Recognition-VIT-Base-patch16-224
|
21 |
|
22 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on
|
23 |
-
[Bingsu/Human_Action_Recognition](https://huggingface.co/datasets/Bingsu/Human_Action_Recognition) dataset.
|
24 |
It achieves the following results on the evaluation set:
|
25 |
- Loss: 0.4005
|
26 |
- Accuracy: 0.8786
|
@@ -40,7 +39,7 @@ You can use the model for image classification.
|
|
40 |
### How to use
|
41 |
|
42 |
Here is how to use this model to classify an image of the human action into one of the following categories:
|
43 |
-
|
44 |
|
45 |
```python
|
46 |
from transformers import pipeline
|
|
|
19 |
|
20 |
# Human-Action-Recognition-VIT-Base-patch16-224
|
21 |
|
22 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on [Bingsu/Human_Action_Recognition](https://huggingface.co/datasets/Bingsu/Human_Action_Recognition) dataset.
|
|
|
23 |
It achieves the following results on the evaluation set:
|
24 |
- Loss: 0.4005
|
25 |
- Accuracy: 0.8786
|
|
|
39 |
### How to use
|
40 |
|
41 |
Here is how to use this model to classify an image of the human action into one of the following categories:
|
42 |
+
'calling', 'clapping', 'cycling', 'dancing', 'drinking', 'eating', 'fighting', 'hugging', 'laughing', 'listening_to_music', 'running', 'sitting', 'sleeping', 'texting', 'using_laptop'
|
43 |
|
44 |
```python
|
45 |
from transformers import pipeline
|