Unclaimed project
Are you a maintainer of pytorch-image-models? Claim this project to take control of your public changelog and roadmap.
Changelog
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
Last updated 6 days ago
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Stable Diffusion web UI
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
A feature-rich command-line audio/video downloader
DiffAttention module + DiffParallelScalingBlock for ViT;...dpwee, dwee, dlittle (differential) ViTs with a small boost over previous runs
Patch release for priority LayerScale initialization regression in 1.0.21
nesterov=True) upd...lvd_1689m -> lvd1689m to match (same for sat_493m -> sat493m)timm model. ViT support done via the EVA base model w/ a new RotaryEmbeddingDinoV3 to match the DINOv3 specific RoPE i...Patch release for Python 3.9 compat break in 1.0.18
set_input_size() method to EVA models, used by OpenCLIP 3.0.0 to allow resizing for timm based encoder models.set_input_size() method to EVA models, used by OpenCLIP 3.0.0 to allow resizing for timm based encoder models.eva.py) including EVA, EVA02, Meta PE ViT, timm SBB ViT w/ ROPE, and Naver ROPE-ViT can be now loa...vit_so150m2_patch16_reg1_gap_448.sbb_e200_in12k_ft_in1k - 88.1% top-1
*...