Instructions to use aisak-ai/AD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use aisak-ai/AD with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="aisak-ai/AD") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("aisak-ai/AD") model = AutoModelForImageClassification.from_pretrained("aisak-ai/AD") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +2 -12
config.json
CHANGED
|
@@ -38,15 +38,5 @@
|
|
| 38 |
"num_channels": 3,
|
| 39 |
"num_hidden_layers": 12,
|
| 40 |
"patch_size": 16,
|
| 41 |
-
"transformers_version": "4.5.0.dev0"
|
| 42 |
-
|
| 43 |
-
"image_processor_type": "ViTImageProcessor", // Replace with actual type
|
| 44 |
-
"image_size": 224,
|
| 45 |
-
"num_channels": 3,
|
| 46 |
-
"patch_size": 16,
|
| 47 |
-
"normalization": {
|
| 48 |
-
"mean": [0.485, 0.456, 0.406],
|
| 49 |
-
"std": [0.229, 0.224, 0.225]
|
| 50 |
-
}
|
| 51 |
-
}
|
| 52 |
-
}
|
|
|
|
| 38 |
"num_channels": 3,
|
| 39 |
"num_hidden_layers": 12,
|
| 40 |
"patch_size": 16,
|
| 41 |
+
"transformers_version": "4.5.0.dev0"
|
| 42 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|