rkshuai

Deep-Learning-Papers-Reading-Roadmap

Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!

.tmux

🇫🇷 Oh my tmux! My self-contained, pretty & versatile tmux configuration made with ❤️

imgaug

Image augmentation for machine learning experiments.

cvat

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

chineseocr

yolo3+ocr

Learning-to-See-in-the-Dark

Learning to See in the Dark. CVPR 2018

EAST

A tensorflow implementation of EAST text detector

mmskeleton

A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.

onnx-tensorrt

ONNX-TensorRT: TensorRT backend for ONNX

crnn.pytorch

Convolutional recurrent network in pytorch

MobileNet-SSD

Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.

HyperLandmark

Deep Learning Based Free Mobile Real-Time Face Landmark Detector. Contact:jack-yu-business@foxmail.com

MTCNN-Tensorflow

Reproduce MTCNN using Tensorflow

PSENet

Official Pytorch implementations of PSENet.

LAB

[CVPR 2018] Look at Boundary: A Boundary-Aware Face Alignment Algorithm

aster

Recognizing cropped text in natural images.

tf_trt_models

TensorFlow models accelerated with NVIDIA TensorRT

Face-Track-Detect-Extract

💎 Detect , track and extract the optimal face in multi-target faces (exclude side face and select the optimal face).

contextualLoss

The Contextual Loss

MobileNetv2-SSDLite

Caffe implementation of SSD and SSDLite detection on MobileNetv2, converted from tensorflow.

seg_every_thing

Code release for Hu et al., Learning to Segment Every Thing. in CVPR, 2018.

var-attn

Latent Alignment and Variational Attention

crnn-mxnet-chinese-text-recognition

An implementation of CRNN (CNN+LSTM+warpCTC) on MxNet for chinese text recognition

MXNet2Caffe

Convert MXNet model to Caffe model

EAST_ICPR

Forked from argman/EAST for the ICPR MTWI 2018 CHALLENGE

ICDAR_2015_data_visualization

Visualize the dataset of ICDAR 2015. Only challenge 4 task 1 is available currently.

chinese-ocr

运用tensorflow实现自然场景文字检测,keras/pytorch实现crnn+ctc实现不定长中文OCR识别

pose-residual-network

Code for 'MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network' paper

st-gcn

Spatial Temporal Graph Convolutional Networks (ST-GCN) for Skeleton-Based Action Recognition in PyTorch

python_tool