PyTorch Image Models

https://github.com/rwightman/pytorch-image-models

AI & ML interests

Computer Vision

Recent Activity

rwightman new activity 19 days ago

timm/vit_large_patch16_dinov3.sat493m:Under the hood difference between Feature Map Extraction and Image Embeddings

rwightman updated a collection about 2 months ago

Searching for Better ViT Baselines

rwightman updated a collection about 2 months ago

Searching for Better ViT Baselines

View all activity

timm 's models 1,707

timm/convnext_tiny.in12k_ft_in1k

Image Classification • Updated Jan 21, 2025 • 232k • 5

timm/convnext_tiny.in12k

Image Classification • Updated Jan 21, 2025 • 145k

timm/convnextv2_tiny.fcmae_ft_in22k_in1k_384

Image Classification • Updated Jan 21, 2025 • 21.4k • 4

timm/convnextv2_tiny.fcmae_ft_in22k_in1k

Image Classification • Updated Jan 21, 2025 • 63.7k • 2

timm/convnextv2_tiny.fcmae_ft_in1k

Image Classification • Updated Jan 21, 2025 • 9.62k

timm/convnextv2_tiny.fcmae

Image Feature Extraction • Updated Jan 21, 2025 • 21k • 1

timm/convnextv2_pico.fcmae_ft_in1k

Image Classification • Updated Jan 21, 2025 • 2.2k • 1

timm/convnextv2_pico.fcmae

Image Feature Extraction • Updated Jan 21, 2025 • 119

timm/convnextv2_nano.fcmae_ft_in22k_in1k_384

Image Classification • Updated Jan 21, 2025 • 15.6k

timm/convnextv2_nano.fcmae_ft_in22k_in1k

Image Classification • Updated Jan 21, 2025 • 7.29M • 3

timm/convnextv2_nano.fcmae_ft_in1k

Image Classification • Updated Jan 21, 2025 • 708

timm/convnextv2_nano.fcmae

Image Feature Extraction • Updated Jan 21, 2025 • 171

timm/convnextv2_large.fcmae_ft_in22k_in1k_384

Image Classification • Updated Jan 21, 2025 • 14.1k

timm/convnextv2_large.fcmae_ft_in22k_in1k

Image Classification • Updated Jan 21, 2025 • 9.18k

timm/convnextv2_large.fcmae_ft_in1k

Image Classification • Updated Jan 21, 2025 • 463 • 1

timm/convnextv2_large.fcmae

Image Feature Extraction • Updated Jan 21, 2025 • 608

timm/convnextv2_huge.fcmae_ft_in22k_in1k_512

Image Classification • Updated Jan 21, 2025 • 357 • 3

timm/convnextv2_huge.fcmae_ft_in22k_in1k_384

Image Classification • Updated Jan 21, 2025 • 677 • 2

timm/convnextv2_huge.fcmae_ft_in1k

Image Classification • Updated Jan 21, 2025 • 278

timm/convnextv2_huge.fcmae

Image Feature Extraction • Updated Jan 21, 2025 • 55

timm/convnextv2_femto.fcmae_ft_in1k

Image Classification • Updated Jan 21, 2025 • 9.4k

timm/convnextv2_femto.fcmae

Image Feature Extraction • Updated Jan 21, 2025 • 181

timm/convnextv2_base.fcmae_ft_in22k_in1k_384

Image Classification • Updated Jan 21, 2025 • 19.4k

timm/convnextv2_base.fcmae_ft_in22k_in1k

Image Classification • Updated Jan 21, 2025 • 178k • 2

timm/convnextv2_base.fcmae_ft_in1k

Image Classification • Updated Jan 21, 2025 • 1.57k

timm/convnextv2_base.fcmae

Image Feature Extraction • Updated Jan 21, 2025 • 6.21k • 1

timm/convnextv2_atto.fcmae_ft_in1k

Image Classification • Updated Jan 21, 2025 • 7.41k

timm/convnextv2_atto.fcmae

Image Feature Extraction • Updated Jan 21, 2025 • 908

timm/eva_giant_patch14_560.m30m_ft_in22k_in1k

Image Classification • Updated Jan 21, 2025 • 448 • 3

timm/eva_giant_patch14_336.m30m_ft_in22k_in1k

Image Classification • Updated Jan 21, 2025 • 95