#pytorch Repositories
1,936 repositories total
Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs (CVPR 2022)
[ICLR 2026] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.
Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]
Modern Computer Vision with PyTorch, published by Packt
[ECCV'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image
Real-time Neural Radiance Talking Portrait Synthesis via Audio-spatial Decomposition
Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".
Build a RAG (Retrieval Augmented Generation) pipeline from scratch and have it all run locally.
๐A pyTorch implementation of the DeepMoji model: state-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc
:zap: Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+.
A minimalist SOTA LaTeX OCR model with only 20M parameters, running in browser. Full training pipeline available for self-reproduction. | Ultralight SOTA LaTeX formula recognition model with only 20M parameters, running in the browser. Full training pipeline code open-sourced for self-study and reproduction.
Repository of Vision Transformer with Deformable Attention (CVPR2022) and DAT++: Spatially Dynamic Vision Transformer with Deformable Attention
[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory
Implementation of [CVPR 2025] "DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation"
This repository is an unoffical PyTorch implementation of Medical segmentation in 2D and 3D.
alfred-py: A deep learning utility library for **human**, more detail about the usage of lib to: https://zhuanlan.zhihu.com/p/341446046
Official Repository for "DrEureka: Language Model Guided Sim-to-Real Transfer" (RSS 2024)
TriplaneGaussian: A new hybrid representation for single-view 3D reconstruction.
MONAI Label is an intelligent open source image labeling and learning tool.
:four_leaf_clover: Another Chinese chatbot implemented in PyTorch, which is the sub-module of intelligent work order processing robot. ๐ฉโ๐ง
BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.
TextGAN is a PyTorch framework for Generative Adversarial Networks (GANs) based text generation models.
Momentum Human Rig is an anatomically-inspired parametric full-body digital human model developed at Meta. It includes: A parametric body skeletal model; A realistic 3D mesh skinned to the skeleton with levels of detail;A body blendshape and pose corrective model; A facial blendshape model.Its design is friendly for both CG and CV communities.
The calflops is designed to calculate FLOPsใMACs and Parameters in all various neural networks, such as Linearใ CNNใ RNNใ GCNใTransformer(BertใLlaMA etc Large Language Model)
Similarities: a toolkit for similarity calculation and semantic search. An toolkit for similarity calculation and matching search, supporting billions of data for text-to-text, text-to-image, and image-to-image search. Developed in Python 3, ready to use out of the box.
A highly optimized LLM inference acceleration engine for Llama and its variants.
A high-performance ML model serving framework, offers dynamic batching and CPU/GPU pipelines to fully exploit your compute machine
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
Omni SenseVoice: High-Speed Speech Recognition with words timestamps ๐ฃ๏ธ๐ฏ