Instructions to use zllhhhh/SwinUnetr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zllhhhh/SwinUnetr with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("zllhhhh/SwinUnetr", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from zllhhhh/SwinUnetr: direct link, hf CLI and curl.
- Browser
- Download file 751 Bytes
-
https://huggingface.co/zllhhhh/SwinUnetr/resolve/main/config.json
- Command line
-
hf download hf://zllhhhh/SwinUnetr/config.json
-
curl -L -o config.json https://huggingface.co/zllhhhh/SwinUnetr/resolve/main/config.json
751 Bytes
| { | |
| "vision_config": { | |
| "_name_or_path": "", | |
| "architecture": "Swin3DClass", | |
| "image_size": 256, | |
| "image_depth": 128, | |
| "in_channels": 1, | |
| "out_channels": 14, | |
| "depths": [ | |
| 2, | |
| 2, | |
| 2, | |
| 2 | |
| ], | |
| "num_heads": [ | |
| 3, | |
| 6, | |
| 12, | |
| 24 | |
| ], | |
| "hidden_size": 1024, | |
| "feature_size":48, | |
| "intermediate_size": 4096, | |
| "norm_name": "instance", | |
| "drop_rate": 0.0, | |
| "attn_drop_rate": 0.0, | |
| "dropout_path_rate": 0.0, | |
| "normalize": true, | |
| "use_checkpoint": false, | |
| "spatial_dims": 3, | |
| "projection_dim" : 768, | |
| "top_k": 98, | |
| "top_p": 1.0 | |
| }, | |
| "vision_config_dict": { | |
| "hidden_size": 1024, | |
| "intermediate_size": 4096, | |
| "projection_dim": 768 | |
| } | |
| } |