vision
CV toolkit
A collection of utilities for computer vision tasks using PyTorch
Datasets, Transforms and Models specific to Computer Vision
16k stars
442 watching
7k forks
Language: Python
last commit: about 1 month ago
Linked from 4 awesome lists
computer-visionmachine-learning
academic/awesome-datascience
bharathgs/awesome-pytorch-list
weiaicunzai/awesome-image-classification
krzjoa/awesome-python-data-scienceRelated projects:
| Repository | Description | Stars |
|---|---|---|
 donnyyou/torchcv | A comprehensive PyTorch-based framework for computer vision tasks | 2,249 |
 michaelmathieu/thffmpeg | Bindings for using FFmpeg to decode video frames in Torch tensors | 26 |
 torch/cutorch | Provides a CUDA backend for the PyTorch deep learning framework | 337 |
 moodstocks/inception-v3.torch | Reconstructs Inception V3 network from TensorFlow weights and generates Torch model for computer vision tasks | 131 |
 wang-bin/qtav | A multimedia framework that provides an easy-to-use API for building video players across multiple platforms. | 4,001 |
 xamla/torch-pcl | Bindings for integrating Point Cloud Library with the Torch programming framework. | 30 |
| pytorch/audio | A PyTorch module providing tools and functions for audio signal processing | 2,561 |
 kaiyangzhou/deep-person-reid | A PyTorch library for training and retraining deep neural networks for person re-identification in images and videos. | 4,353 |
 nearai/torchfold | A PyTorch module for dynamic batching and optimized computation on deep neural networks | 221 |
 soumith/dcgan.torch | A PyTorch implementation of a deep generative model that can be used to generate images from a dataset. | 1,466 |
 laurentmazare/ocaml-torch | Bindings for PyTorch's tensor library in OCaml for GPU acceleration and automatic differentiation | 416 |
| pytorch/pytorch | A Python library providing tensors and dynamic neural networks with strong GPU acceleration | 84,978 |
| torch/torch7 | A C-based library for high-level numerical computing and tensor operations | 9,001 |
 nvidia/vid2vid | A PyTorch implementation of a video-to-video translation method for generating photorealistic videos from semantic label maps or other input data. | 8,623 |
 ffmpeg/ffmpeg | A collection of libraries and tools to process multimedia content | 46,702 |