Instructions to use nvidia/mit-b1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/mit-b1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="nvidia/mit-b1") 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("nvidia/mit-b1") model = AutoModelForImageClassification.from_pretrained("nvidia/mit-b1") - Inference
- Notebooks
- Google Colab
- Kaggle
Set do_pad to False
Browse files- preprocessor_config.json +1 -1
preprocessor_config.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
512
|
| 6 |
],
|
| 7 |
"do_normalize": true,
|
| 8 |
-
"do_pad":
|
| 9 |
"do_random_crop": false,
|
| 10 |
"do_resize": true,
|
| 11 |
"feature_extractor_type": "SegformerFeatureExtractor",
|
|
|
|
| 5 |
512
|
| 6 |
],
|
| 7 |
"do_normalize": true,
|
| 8 |
+
"do_pad": false,
|
| 9 |
"do_random_crop": false,
|
| 10 |
"do_resize": true,
|
| 11 |
"feature_extractor_type": "SegformerFeatureExtractor",
|