Image Feature Extraction
Transformers
Safetensors
English
keural_vision
vision
vision-encoder
image-text
contrastive-learning
custom-architecture
vlm
Instructions to use mkd-dev/keural-vision-encoder-poc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mkd-dev/keural-vision-encoder-poc with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="mkd-dev/keural-vision-encoder-poc")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("mkd-dev/keural-vision-encoder-poc", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from mkd-dev/keural-vision-encoder-poc: direct link, hf CLI and curl.
- Browser
- Download file 411 Bytes
-
https://huggingface.co/mkd-dev/keural-vision-encoder-poc/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://mkd-dev/keural-vision-encoder-poc/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/mkd-dev/keural-vision-encoder-poc/resolve/main/preprocessor_config.json
411 Bytes
| { | |
| "do_resize": true, | |
| "size": {"height": 256, "width": 256}, | |
| "do_normalize": true, | |
| "image_mean": [0.485, 0.456, 0.406], | |
| "image_std": [0.229, 0.224, 0.225], | |
| "do_rescale": true, | |
| "rescale_factor": 0.00392156862745098, | |
| "image_processor_type": "KeuralImageProcessor", | |
| "supported_sizes": [ | |
| {"height": 224, "width": 224}, | |
| {"height": 256, "width": 256}, | |
| {"height": 320, "width": 320} | |
| ] | |
| } | |