PL's repositories
Ask_Attend_and_Answer
Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering
awesome-deep-learning-papers
The most cited deep learning papers
BeautifyFaceAndDetection
使用GPUImage实现人脸美白和人脸识别(磨皮,人脸检测)
CAM
Class Activation Mapping
cleverhans
A library for benchmarking vulnerability to adversarial examples
clockwork-fcn
Clockwork Convnets for Video Semantic Segmenation
Computer-Systems-A-Programmer-s-Perspective
Computer Systems: A Programmer's Perspective
DeepLearningBook
MIT Deep Learning Book in PDF format
deeplearningbook-chinese
Deep Learning Book Chinese Translation
ebook
classic books of computer science
FaceAttributeManipulation
An implementation of Learning Residual Images for Face Attribute Manipulation
FC-DenseNet
Fully Convolutional DenseNets for semantic segmentation.
ganhacks
starter from "How to Train a GAN?" at NIPS2016
gitignore
A collection of useful .gitignore templates
meta-learning-lstm
This repo contains the source code accompanying a scientific paper with the same name.
model_compression
Implementation of model compression with knowledge distilling method.
PixelNet
The repository contains source code and models to use PixelNet architecture used for various pixel-level tasks. More details can be accessed at <http://www.cs.cmu.edu/~aayushb/pixelNet/>.
pose-hg-train
Training and experimentation code used for "Stacked Hourglass Networks for Human Pose Estimation"
PSPNet
Repository of paper https://arxiv.org/abs/1612.01105
recurrent-face-alignment
Xi Peng et al. "A Recurrent Encoder-Decoder Network for Sequential Face Alignment", ECCV 2016. (Oral)
research-method
论文写作与资料分享
ResNeXt
Reproduce ResNet-v3(Aggregated Residual Transformations for Deep Neural Network) with Caffe
sca-cnn
image captions generation with spatial and channel-wise attention
sceneparsing
Development kit for MIT Scene Parsing Benchmark
tripletloss
tripletloss in caffe
vae_tutorial
Caffe code to accompany my Tutorial on Variational Autoencoders