Instructions to use ogimgio/vit-base-highways-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ogimgio/vit-base-highways-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="ogimgio/vit-base-highways-2") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("ogimgio/vit-base-highways-2") model = AutoModelForImageClassification.from_pretrained("ogimgio/vit-base-highways-2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# vit-base-highways-2
|
| 16 |
|
| 17 |
-
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
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
- Loss: 0.2196
|
| 20 |
- Accuracy: 0.96
|
|
|
|
| 14 |
|
| 15 |
# vit-base-highways-2
|
| 16 |
|
| 17 |
+
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 highways-hacktum dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
- Loss: 0.2196
|
| 20 |
- Accuracy: 0.96
|