Image Classification
timm
Safetensors
vision-transformer
adaptive-inference
elastic-inference
imagenet-1k
Instructions to use NCPS/thinkingvit_deit-3h-6h-800epochs-imagenet1k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use NCPS/thinkingvit_deit-3h-6h-800epochs-imagenet1k with timm:
import timm model = timm.create_model("hf_hub:NCPS/thinkingvit_deit-3h-6h-800epochs-imagenet1k", pretrained=True) - Notebooks
- Google Colab
- Kaggle
| { | |
| "architecture": "thinkingvit", | |
| "num_classes": 1000, | |
| "num_features": 384, | |
| "global_pool": "token", | |
| "model_args": { | |
| "thinking_stages": [ | |
| 3, | |
| 6 | |
| ] | |
| }, | |
| "pretrained_cfg": { | |
| "custom_load": false, | |
| "input_size": [ | |
| 3, | |
| 224, | |
| 224 | |
| ], | |
| "fixed_input_size": true, | |
| "interpolation": "bicubic", | |
| "crop_pct": 0.9, | |
| "crop_mode": "center", | |
| "mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "num_classes": 1000, | |
| "pool_size": null, | |
| "first_conv": "patch_embed.proj", | |
| "classifier": "head" | |
| } | |
| } |