Model Details
Full Model IDtimm/vit_base_patch16_224.augreg2_in21k_ft_in1k
Pipeline / Taskimage-classification
Librarytimm
Downloads (all-time)617.1K
Likes13
Last Modified1/20/2025
Author / Orgtimm
PrivateNo — public
⚡ Quick Usage (Python)
Using the 🤗 Transformers library. Install with pip install transformers
from transformers import pipeline
# Load the model
pipe = pipeline("image-classification", model="timm/vit_base_patch16_224.augreg2_in21k_ft_in1k")
# Run inference
result = pipe("Your input here")
print(result)🏷️ Tags
timmpytorchsafetensorsimage-classificationtransformersdataset:imagenet-1kdataset:imagenet-21karxiv:2106.10270arxiv:2010.11929license:apache-2.0region:us
More Image Classification Models
See all →🚀 Use This Model
Access model files, inference API, and full documentation on Hugging Face.
Open on Hugging Face →Browse Model Files ↗← Browse All Models🖼️ Task: Image Classification
This model is designed for the Image Classification task. Explore more models for this use case.
All Image Classification Models →📊 Popularity
⬇ Downloads617.1K
❤️ Community Likes13
🛠️ Requirements
- →Install: pip install timm
- →Python 3.8+ recommended for Transformers.
- →GPU (CUDA) speeds up inference significantly.
- →Use model.half() for fp16 on limited VRAM.