zengjianping Goto Github PK

pytorch-cyclegan-and-pix2pix

Image-to-image translation in PyTorch (e.g. horse2zebra, edges2cats, and more)

quantized-cnn

An efficient framework for convolutional neural networks

r-fcn

R-FCN: Object Detection via Region-based Fully Convolutional Networks

rcn

The code for Recombinator Networks paper.

realtime_multi-person_pose_estimation

Code repo for realtime multi-person pose estimation, without using any person detector.

ron

RON: Reverse Connection with Objectness Prior Networks for Object Detection, CVPR 2017

rrc_detection

Accurate Single Stage Detector Using Recurrent Rolling Convolution

rsa-for-object-detection

Code and some data for 'Recurrent Scale Approximation for Object Detection in CNN' in ICCV 2017

seetafaceengine

sphereface

Implementation for <SphereFace: Deep Hypersphere Embedding for Face Recognition> in CVPR'17.

squeezedet

A tensorflow implementation for SqueezeDet, a convolutional neural network for object detection.

squeezenet

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters

ssh

SSH: Single Stage Headless Face Detector

stackgan

sunxi-tvin

tcdcn-face-alignment

Matlab implementation of facial landmark detection by deep multi-task learning

tensorflow

Computation using data flow graphs for scalable machine learning

tensorpack

Neural Network Toolbox on TensorFlow

tiny

torch-playground

Lightweight training platform for troch

vae_tutorial

Caffe code to accompany my Tutorial on Variational Autoencoders

vs-tools-for-ai

Visual Studio Tools for AI is a free Visual Studio extension to build, test, and deploy deep learning / AI solutions. It seamlessly integrates with Azure Machine Learning for robust experimentation capabilities, including but not limited to submitting data preparation and model training jobs transparently to different compute targets. Additionally, it provides support for custom metrics and run history tracking, enabling data science reproducibility and auditing. Enterprise ready collaboration, allow to securely work on project with other people.

wide-residual-networks

3.8% and 18.3% on CIFAR-10 and CIFAR-100

xnor-net