Instructions to use facebook/regnet-y-320-seer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/regnet-y-320-seer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="facebook/regnet-y-320-seer")# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, AutoModel processor = AutoImageProcessor.from_pretrained("facebook/regnet-y-320-seer") model = AutoModel.from_pretrained("facebook/regnet-y-320-seer", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from facebook/regnet-y-320-seer: direct link, hf CLI and curl.
- Browser
- Download file 401 Bytes
-
https://huggingface.co/facebook/regnet-y-320-seer/resolve/main/config.json
- Command line
-
hf download hf://facebook/regnet-y-320-seer/config.json
-
curl -L -o config.json https://huggingface.co/facebook/regnet-y-320-seer/resolve/main/config.json
401 Bytes
| { | |
| "architectures": [ | |
| "RegNetModel" | |
| ], | |
| "depths": [ | |
| 2, | |
| 5, | |
| 12, | |
| 1 | |
| ], | |
| "downsample_in_first_stage": true, | |
| "embedding_size": 32, | |
| "groups_width": 232, | |
| "hidden_act": "relu", | |
| "hidden_sizes": [ | |
| 232, | |
| 696, | |
| 1392, | |
| 3712 | |
| ], | |
| "layer_type": "y", | |
| "model_type": "regnet", | |
| "num_channels": 3, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.18.0.dev0" | |
| } | |