A flexible framework of neural networks for deep learning

NumPy-like API accelerated with CUDA

A simplified implemention of Faster R-CNN that replicate performance from origin paper

Deep learning operations reinvented (for pytorch, tensorflow, chainer, gluon and others)

ChainerCV: a Library for Deep Learning in Computer Vision

an implementation of 3D Ken Burns Effect from a Single Image using PyTorch

an implementation of Video Frame Interpolation via Adaptive Separable Convolution using PyTorch

Library for faster pinned CPU <-> GPU transfer in Pytorch

a reimplementation of PWC-Net in PyTorch that matches the official Caffe version

CuPy fused PyTorch neural networks ops

a reimplementation of LiteFlowNet in PyTorch that matches the official Caffe version

an implementation of softmax splatting for differentiable forward warping using PyTorch

A Simple & Flexible Cross Framework Operators Toolkit

Deep learning framework realized by Numpy purely, supports for both Dynamic Graph and Static Graph with GPU acceleration

Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset (CVPR'19)

Chainer implementation of waifu2x

A suite of benchmarks to test the sequential CPU and GPU performance of most popular high-performance libraries for Python.

A complete machine vision container that includes Jupyter notebooks with built-in code hinting, Anaconda, CUDA-X, TensorRT inference accelerator for Tensor cores, CuPy (GPU drop in replacement for Numpy), PyTorch, TF2, Tensorboard, and OpenCV for accelerated workloads on NVIDIA Tensor cores and GPUs.

A Python wrapper of NVIDIA Video Loader (NVVL) with CuPy for fast video loading with Python

an example of a CUDA extension for PyTorch using CuPy which computes the Hadamard product of two tensors

a reimplementation of UnFlow in PyTorch that matches the official TensorFlow version

Official source code for our paper "AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation" (CVPR 2020)

This container is no longer supported, and has been deprecated in favor of: https://github.com/joehoeller/NVIDIA-GPU-Tensor-Core-Accelerator-PyTorch-OpenCV

ROIPooling for pytorch

The code for multi-channel speech enhancement and source separation such as MNMF, MNMF_DP, ILRMA, ILRMA_DP, FastMNMF, FastMNMF_DP, FCA, FastFCA

Chainer implementation of PointNet, PointNet++, KD-Network and 3DContextNework

Frame interpolation

Write numeric code that automatically works with any numpy-ish libraries.

Yolo v2 implementation in Chainer, ChainerCV