Instructions to use timm/eva02_small_patch14_224.mim_in22k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use timm/eva02_small_patch14_224.mim_in22k with timm:
import timm model = timm.create_model("hf_hub:timm/eva02_small_patch14_224.mim_in22k", pretrained=True) - Transformers
How to use timm/eva02_small_patch14_224.mim_in22k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="timm/eva02_small_patch14_224.mim_in22k", device_map="auto")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("timm/eva02_small_patch14_224.mim_in22k", dtype="auto", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Linear Probe Performance?
#3
by georgecazenavette - opened
Hello :)
Do you have any metrics for an ImageNet linear probe for this model? I couldn't find results for this model specifically either in this repo's table or on the timm github.
I'm asking because I'm seeing suspicious results for this Small model compared to the Tiny, Base, and Large versions at 224 resolution.
Thanks, and apologies if I've missed something obvious!