Instructions to use trongg/swinv2_base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use trongg/swinv2_base with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("trongg/swinv2_base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from trongg/swinv2_base: direct link, hf CLI and curl.
- Browser
- Download file 630 Bytes
-
https://huggingface.co/trongg/swinv2_base/resolve/main/config.json
- Command line
-
hf download hf://trongg/swinv2_base/config.json
-
curl -L -o config.json https://huggingface.co/trongg/swinv2_base/resolve/main/config.json
630 Bytes
| { | |
| "architecture": "swinv2_base_window8_256", | |
| "num_classes": 9083, | |
| "num_features": 1024, | |
| "global_pool": "avg", | |
| "model_args": { | |
| "act_layer": "gelu", | |
| "img_size": 448, | |
| "window_size": 14 | |
| }, | |
| "pretrained_cfg": { | |
| "custom_load": false, | |
| "input_size": [ | |
| 3, | |
| 448, | |
| 448 | |
| ], | |
| "fixed_input_size": false, | |
| "interpolation": "bicubic", | |
| "crop_pct": 1.0, | |
| "crop_mode": "center", | |
| "mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "num_classes": 9083, | |
| "pool_size": null, | |
| "first_conv": null, | |
| "classifier": null | |
| } | |
| } |