Instructions to use facebook/vit-mae-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/vit-mae-base with Transformers:
# Load model directly from transformers import AutoImageProcessor, AutoModelForPreTraining processor = AutoImageProcessor.from_pretrained("facebook/vit-mae-base") model = AutoModelForPreTraining.from_pretrained("facebook/vit-mae-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Fix code example
Browse files
README.md
CHANGED
|
@@ -38,7 +38,8 @@ url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
|
|
| 38 |
image = Image.open(requests.get(url, stream=True).raw)
|
| 39 |
|
| 40 |
feature_extractor = AutoFeatureExtractor.from_pretrained('facebook/vit-mae-base')
|
| 41 |
-
model =
|
|
|
|
| 42 |
inputs = feature_extractor(images=image, return_tensors="pt")
|
| 43 |
outputs = model(**inputs)
|
| 44 |
loss = outputs.loss
|
|
|
|
| 38 |
image = Image.open(requests.get(url, stream=True).raw)
|
| 39 |
|
| 40 |
feature_extractor = AutoFeatureExtractor.from_pretrained('facebook/vit-mae-base')
|
| 41 |
+
model = ViTMAEForPreTraining.from_pretrained('facebook/vit-mae-base')
|
| 42 |
+
|
| 43 |
inputs = feature_extractor(images=image, return_tensors="pt")
|
| 44 |
outputs = model(**inputs)
|
| 45 |
loss = outputs.loss
|