Instructions to use timm/vit_large_patch14_clip_336.datacompxl_ft_augreg_inat21 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use timm/vit_large_patch14_clip_336.datacompxl_ft_augreg_inat21 with timm:
import timm model = timm.create_model("hf_hub:timm/vit_large_patch14_clip_336.datacompxl_ft_augreg_inat21", pretrained=True) - Transformers
How to use timm/vit_large_patch14_clip_336.datacompxl_ft_augreg_inat21 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="timm/vit_large_patch14_clip_336.datacompxl_ft_augreg_inat21") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("timm/vit_large_patch14_clip_336.datacompxl_ft_augreg_inat21", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architecture": "vit_large_patch14_clip_336", | |
| "num_classes": 10000, | |
| "num_features": 1024, | |
| "global_pool": "token", | |
| "pretrained_cfg": { | |
| "tag": "datacompxl", | |
| "custom_load": false, | |
| "input_size": [ | |
| 3, | |
| 336, | |
| 336 | |
| ], | |
| "fixed_input_size": true, | |
| "interpolation": "bicubic", | |
| "crop_pct": 1.0, | |
| "crop_mode": "center", | |
| "mean": [ | |
| 0.48145466, | |
| 0.4578275, | |
| 0.40821073 | |
| ], | |
| "std": [ | |
| 0.26862954, | |
| 0.26130258, | |
| 0.27577711 | |
| ], | |
| "num_classes": 10000, | |
| "pool_size": null, | |
| "first_conv": "patch_embed.proj", | |
| "classifier": "head" | |
| } | |
| } |