Hugging Face's logo
Activity Feed

AI & ML interests

Computer Vision

Recent Activity
rwightmanΒ  new activity about 1 month ago
timm/vit_large_patch16_dinov3.sat493m:Under the hood difference between Feature Map Extraction and Image Embeddings
rwightmanΒ  updated a collection 2 months ago
Searching for Better ViT Baselines
rwightmanΒ  updated a collection 2 months ago
Searching for Better ViT Baselines
View all activity

Organization Card
Community About org cards

timm

image/png

PyTorch Image Models (timm) is a collection of image models, layers, utilities, optimizers, schedulers, data-loaders / augmentations, and reference training / validation scripts that aim to pull together a wide variety of SOTA models with ability to reproduce ImageNet training results.

Collections 20

timm DINOv3
Meta AI's DINOv3 weights in timm. ViTs with `qkvb` have a zero QV bias present, otherwise bias is disabled. QKV bias are all 0 in original weights.
Perception Encoder
OpenCLIP (PE Core image + text) and timm PE Core, Spatial, Lang (ViT only) weights. NOTE: These weights do not work with original modeling code.
timm DINOv3
Meta AI's DINOv3 weights in timm. ViTs with `qkvb` have a zero QV bias present, otherwise bias is disabled. QKV bias are all 0 in original weights.
Perception Encoder
OpenCLIP (PE Core image + text) and timm PE Core, Spatial, Lang (ViT only) weights. NOTE: These weights do not work with original modeling code.
View 20 collections