There are no reviews yet. Be the first to send feedback to the community and the maintainers!
micronet
micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shapeDesign-and-Implementation-of-Face-Recognition-based-on-PYNQ
Face recognition, computer vision, deep learning, PYNQ, Movidius NCSObject-tracking-system-based-on-deep-learning
Object tracking system based on deep learning. Master-Jetson TX2, ROS-image + control, image (DL) - detection + tracking, control - TurtleBotElectronics-Design-Competition
Remote amplitude frequency characteristic test device—Electronics Design Competition(Instrument class)Object-Tracking
Object TrackingLightweight-facial-expression-recognition
Face detection, expression recognition, model compression, terminal deploymentBody-sense-simulation-against-game-system-based-on-Kinect
基于Kinect体感的仿真对抗游戏系统Person-Follow-Robot
Person Follow RobotComputer-vision
Computer vision combined with deep learningHeart-road
Record sharingPlatform-Robot-Competition
Chinese Robot Competition—Platform Robot CompetitionAlgorithm-and-Data-Structure
Common algorithms and data structuresInternet-of-Things-IOT
IOT system based on smart cloudIntelligent-fire-fighting-robot
To optimize the design of the common fire fighting machines on the market, enhance the use and reliability.Love Open Source and this site? Check out how you can help us