HuChao's repositories
dynet
DyNet: The Dynamic Neural Network Toolkit
face-alignment-training
Training code for the networks described in "How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)" paper.
SRGAN
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network / Please Star -->
ORN
Oriented Response Networks, in CVPR 2017
FastImageProcessing
Fast Image Processing with Fully-Convolutional Networks
Awesome-Caffe
Awesome Caffe
pytorch2caffe
Convert PyTorch model to Caffemodel
GOTURN-Tensorflow
A tensorflow implementation for GOTURN tracker
super-convergence
Files to create the figures in the paper "Super-Convergence: Very Fast Training of Residual Networks Using Large Learning Rates"
yolo-9000
YOLO9000: Better, Faster, Stronger - Real-Time Object Detection. 9000 classes!
pytorch-fpn
Feature Pyramid Networks in PyTorch
segaware
Segmentation-Aware Convolutional Networks Using Local Attention Masks
blitznet
Deep neural network for object detection and semantic segmentation in real-time. Official code for the paper "BlitzNet: A Real-Time Deep Network for Scene Understanding"
FPN-1
Feature Pyramid Networks for Object Detection on caffe
chainercv
ChainerCV: a Library for Computer Vision in Deep Learning
focal-loss
Focal loss for Dense Object Detection
Focal-Loss-1
loss layer of implementation
Flow-Guided-Feature-Aggregation
Flow-Guided Feature Aggregation for Video Object Detection
Focal-Loss-2
Reproduction of Focal-loss on caffe
placeschallenge
The Toolkit for Places Challenge 2017
Multi-Label-Image-Classification
Multi Label Image Classification
MemNet
Code for our ICCV'17 paper "MemNet: A Persistent Memory Network for Image Restoration" (SPOTLIGHT Presentation)
TensorFlow-Tutorials
Simple tutorials using Google's TensorFlow Framework
NormFace
NormFace: L2 HyperSphere Embedding for Face Verification, 99.21% on LFW
cpp-torch
cpp-torch is a C++ library, implemented as a wrapper around Torch libraries.
DSOD
DSOD: Learning Deeply Supervised Object Detectors from Scratch. In ICCV 2017.
ThiNet
caffe model of ICCV'17 paper - ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression https://arxiv.org/abs/1707.06342
RSA-for-object-detection
Code and some data for 'Recurrent Scale Approximation for Object Detection in CNN' in ICCV 2017