Instructions to use facebook/dino-vits8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/dino-vits8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="facebook/dino-vits8")# Load model directly from transformers import AutoImageProcessor, AutoModel processor = AutoImageProcessor.from_pretrained("facebook/dino-vits8") model = AutoModel.from_pretrained("facebook/dino-vits8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
change feature_extractor_type to image_processor_type in preprocessor_config.json
#3
by abhaymathur21 - opened
- preprocessor_config.json +1 -1
preprocessor_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"do_normalize": true,
|
| 3 |
"do_resize": true,
|
| 4 |
-
"
|
| 5 |
"image_mean": [
|
| 6 |
0.485,
|
| 7 |
0.456,
|
|
|
|
| 1 |
{
|
| 2 |
"do_normalize": true,
|
| 3 |
"do_resize": true,
|
| 4 |
+
"image_processor_type": "ViTFeatureExtractor",
|
| 5 |
"image_mean": [
|
| 6 |
0.485,
|
| 7 |
0.456,
|