Instructions to use Efferbach/mobilevit-small-10k-steps with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Efferbach/mobilevit-small-10k-steps with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="Efferbach/mobilevit-small-10k-steps")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, MobileViTForSemanticSegmentation processor = AutoImageProcessor.from_pretrained("Efferbach/mobilevit-small-10k-steps") model = MobileViTForSemanticSegmentation.from_pretrained("Efferbach/mobilevit-small-10k-steps", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from Efferbach/mobilevit-small-10k-steps: direct link, hf CLI and curl.
- Browser
- Download file 344 Bytes
-
https://huggingface.co/Efferbach/mobilevit-small-10k-steps/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://Efferbach/mobilevit-small-10k-steps/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/Efferbach/mobilevit-small-10k-steps/resolve/main/preprocessor_config.json
344 Bytes
| { | |
| "crop_size": { | |
| "height": 512, | |
| "width": 512 | |
| }, | |
| "do_center_crop": true, | |
| "do_flip_channel_order": true, | |
| "do_flip_channels": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_processor_type": "MobileViTImageProcessor", | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "shortest_edge": 544 | |
| } | |
| } | |