Instructions to use timm/convnext_atto.d2_in1k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use timm/convnext_atto.d2_in1k with timm:
import timm model = timm.create_model("hf_hub:timm/convnext_atto.d2_in1k", pretrained=True) - Transformers
How to use timm/convnext_atto.d2_in1k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="timm/convnext_atto.d2_in1k") 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/convnext_atto.d2_in1k", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- bf316a3691081814f06077ca9726d20f8a04c0efddaf21c9a955cd2cc8da7b63
- Size of remote file:
- 14.8 MB
- SHA256:
- 1a8e3a6876e3f4a17a59ba3a74fdc48feb16233a21345df7e699fb2b7ad20e79
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.