Instructions to use timm/vit_large_patch14_reg4_dinov2.lvd142m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use timm/vit_large_patch14_reg4_dinov2.lvd142m with timm:
import timm model = timm.create_model("hf_hub:timm/vit_large_patch14_reg4_dinov2.lvd142m", pretrained=True) - Transformers
How to use timm/vit_large_patch14_reg4_dinov2.lvd142m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="timm/vit_large_patch14_reg4_dinov2.lvd142m")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("timm/vit_large_patch14_reg4_dinov2.lvd142m", dtype="auto") - Notebooks
- Google Colab
- Kaggle
is this full compatible with dinov2 patch embeddings?
#4
by Ayushnangia - opened
Hi as there is no official release for dinov2 with registers. I was wondering is this an alternative to dinov2 with register on timm?
@Ayushnangia The register models / weights are in the official research repo https://github.com/facebookresearch/dinov2 ... these weights are for the implementation using the timm vit model and should match the original very closely.