Stars
Productive, portable, and performant GPU programming in Python.
The Graph-Cut RANSAC algorithm proposed in paper: Daniel Barath and Jiri Matas; Graph-Cut RANSAC, Conference on Computer Vision and Pattern Recognition, 2018. It is available at http://openaccess.t…
Learning embeddings for classification, retrieval and ranking.
Distributed compiler with a central scheduler to share build load
Open deep learning compiler stack for cpu, gpu and specialized accelerators
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Caffe2 is a lightweight, modular, and scalable deep learning framework.
kaldi-asr/kaldi is the official location of the Kaldi project.
Some handy utility libraries and tools for the Caffe deep learning framework.
OptNet - Reducing memory usage in torch neural nets
ImageNet classification using binary Convolutional Neural Networks
Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications
A flexible framework of neural networks for deep learning
Face recognition with deep neural networks.
OpenFace – a state-of-the art tool intended for facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation.
An open source iOS framework for GPU-based image and video processing
This library provides common speech features for ASR including MFCCs and filterbank energies.
Distributed deep learning on Hadoop and Spark clusters.
Real-time audio visualizations (spectrum, spectrogram, etc.)
Torch implementation of ResNet from http://arxiv.org/abs/1512.03385 and training scripts
a fast, scalable, multi-language and extensible build system
computer vision, image processing and machine learning on the web browser or node.
Blade is a powerful build system from Tencent, supports many mainstream programming languages, such as C/C++, java, scala, python, protobuf...