liyuming1978's repositories
NativeLibCompression
The native library compression sdk is given to solve the apk size problem. It is easy to integrate and will get max 50% size decreasing. Not only sdk, a Java tool for package is provided to convert normal apk to compressed apk.
openvino_example
this is for intel openvino (https://software.intel.com/en-us/openvino-toolkit)
caffe_example
install script and example for clCaffe which will run caffe by OpenCL (this is for https://github.com/01org/caffe/tree/inference-optimize)
PyTrafficCar
a python demo (DQN) to show why traffic happen (为什么交通拥堵, 慢速变道是原因所在,里面有深度强化学习,但是目前还不收敛)
deep_learning_object_detection
A paper list of object detection using deep learning.
DirectML
DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning. DirectML provides GPU acceleration for common machine learning tasks across a broad range of supported hardware and drivers, including all DirectX 12-capable GPUs from vendors such as AMD, Intel, NVIDIA, and Qualcomm.
generative_inpainting
DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral
GPU-tracking
Final project for 15-618 : implement a GPU version of the KCF algorithm
iai_kinect2
Tools for using the Kinect One (Kinect v2) in ROS
navigation
ROS Navigation stack. Code for finding where the robot is and how it can get somewhere else.
New-C3D-Caffe
This is a reimplementation of 3D CNN (http://vlg.cs.dartmouth.edu/c3d/). It is compatitable with Caffe 2016. The Caffe is forked from Caffe commit c1126aadb6eab5229203bfba9495bc2b06b4ae89.
QASystemOnMedicalKG
A tutorial and implement of disease centered Medical knowledge graph and qa system based on it。知识图谱构建,自动问答,基于kg的自动问答。以疾病为中心的一定规模医药领域知识图谱,并以该知识图谱完成自动问答与分析服务。
ShuffeNet-Tracker
human tracking on an ARM chip(RK3399)
tf-adnet-tracking
Deep Object Tracking Implementation in Tensorflow for 'Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning(CVPR 2017)'
tf-pose-estimation
Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.