tensor-stream
Video decoder library
Decodes real-time video streams into CUDA memory to support GPU-based deep learning processing
A library for real-time video stream decoding to CUDA memory
380 stars
16 watching
44 forks
Language: C++
last commit: over 3 years agoc-plus-pluscudapythonpytorchvideovideo-processing
Related projects:
| Repository | Description | Stars |
|---|---|---|
 uncomplicate/deep-diamond | A fast Clojure library for computing with tensors and neural networks on CPUs and GPUs. | 433 |
 streamio/streamio-ffmpeg | Provides a Ruby interface to FFmpeg for reading movie metadata and transcoding video files. | 1,649 |
 mratsim/arraymancer | A fast and ergonomic tensor library with automatic differentiation support for deep learning on multiple platforms. | 1,342 |
 intel/intel-extension-for-tensorflow | Enables heterogeneous high-performance computing on Intel CPUs and GPUs for deep learning workloads | 323 |
 nvidia/nvpipe | A Cuda-based library for accelerating video compression in interactive applications | 389 |
 liuzhao1225/youdub-webui | A web-based video processing tool that uses AI to facilitate cultural and linguistic tasks such as transcription, translation, and audio synthesis. | 1,980 |
 osciiart/deepaa | Generates ASCII art from images using deep learning-based convolutional neural networks | 1,524 |
 google/tensorstore | A C++ and Python library for storing and manipulating large multi-dimensional arrays in various formats and storage systems. | 1,362 |
 tensorflow/mesh | A library that enables distributed deep learning by partitioning tensors across processors in a mesh topology. | 1,597 |
 preritj/segmentation | Deep learning models for semantic segmentation of images | 101 |
| tensorflow/text | Preprocessing and processing tools for text data in machine learning models | 1,239 |
 frett27/adav4l2 | A lightweight library for interacting with video capture hardware on Linux-based single-board computers like Raspberry Pi. | 0 |
 fengyuli-dev/multimedia-gpt | Enables OpenAI GPT to process multimedia inputs like images and audio with text output | 184 |
 torch/cunn | A CUDA implementation of neural network modules and related GPU operations | 215 |
 apache/tvm-vta | A comprehensive hardware design stack for accelerating deep learning models | 258 |