Feature Extraction
Transformers
ONNX
dinov2
image-feature-extraction
robotics
edge-deployment
anima
forge
int8
quantized
vision
self-supervised
ros2
jetson
real-time
Eval Results (legacy)
Instructions to use robotflowlabs/dinov2-large-int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use robotflowlabs/dinov2-large-int8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="robotflowlabs/dinov2-large-int8")# Load model directly from transformers import AutoImageProcessor, AutoModel processor = AutoImageProcessor.from_pretrained("robotflowlabs/dinov2-large-int8") model = AutoModel.from_pretrained("robotflowlabs/dinov2-large-int8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from robotflowlabs/dinov2-large-int8: direct link, hf CLI and curl.
- Browser
- Download file 436 Bytes
-
https://huggingface.co/robotflowlabs/dinov2-large-int8/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://robotflowlabs/dinov2-large-int8/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/robotflowlabs/dinov2-large-int8/resolve/main/preprocessor_config.json
436 Bytes
| { | |
| "crop_size": { | |
| "height": 224, | |
| "width": 224 | |
| }, | |
| "do_center_crop": true, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_processor_type": "BitImageProcessor", | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "shortest_edge": 256 | |
| } | |
| } | |