leo-zhou's repositories
awesome-rnn
Recurrent Neural Network - A curated list of resources dedicated to RNN
C3D
C3D is a modified version of BVLC caffe to support 3D ConvNets.
caffe
Caffe: a fast framework for deep learning. For the most recent version checkout the dev branch. For the latest stable release checkout the master branch.
caffe-video_triplet
Unsupervised Learning using Videos (ICCV 2015)
caffenet-benchmark
Evaluation of the CNN design choices performance on ImageNet-2012.
CAM
Class Activation Mapping
cleverhans
A library for benchmarking vulnerability to adversarial examples
CNN-visualization
Visualizing Convolutional and Fully-connected layers of deep nets
cnn_treevis
Visualize CNN features in a hierarchy.
convnetjs
Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.
DomainSeparationNetworks
DSN/Tensorflow
DSOD
DSOD: Learning Deeply Supervised Object Detectors from Scratch. In ICCV 2017.
fooling
Code base for "Deep Neural Networks are Easily Fooled" CVPR 2015 paper
IDE-baseline-Market-1501
ID-discriminative Embedding (IDE) for Person Re-identification
lisa-caffe-public
Lisa Anne's public caffe code.
MARS-evaluation
This repository provides the evaluation codes for the MARS dataset
models
Models built with TensorFlow
open-reid
Open source person re-identification library in python
pytorch-CycleGAN-and-pix2pix
Image-to-image translation in PyTorch (e.g. horse2zebra, edges2cats, and more)
resnet-protofiles
Caffe Protofiles for MSRA ResNet: train prototxt
stnbhwd
Modules for spatial transformer networks (BHWD layout)
tensorboard-pytorch
tensorboard for pytorch (and chainer, mxnet, numpy, ...)
the-incredible-pytorch
The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.
torch-toolbox
A collection of snippets and libraries for Torch from e-Lab
tripletloss
tripletloss in caffe
vat
Code for reproducing the results on the MNIST dataset in the paper "Distributional Smoothing with Virtual Adversarial Training"