Xianlei Long's Projects
ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks
A list of high-quality (newest) AutoML works and lightweight models including 1.) Neural Architecture Search, 2.) Lightweight Structures, 3.) Model Compression, Quantization and Acceleration, 4.) Hyperparameter Optimization, 5.) Automated Feature Engineering.
Estimate the processing speed of several CNN object detection model.
This is my daily record of reading articles/news from the Batch, one weekly subscription presented by Andrew Ng.
Convolutional Neural Networks
[ICCV 2019] PyTorch implementation of Dynamic Grouping Convolution and Groupable ConvNet with pre-trained G-ResNeXt models
Face detection implementation with different methods and applications
reproduction of the article
re-implement of Group ConvNet, also be called as G-ResNext. It's from the paper, reproduction of the paper "Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks".
All plot function to plot the scan route of samples.
Real-time head pose estimation built with OpenCV and dlib
Just for test. It's no use.
Using wide area object perception and tracking
This is the source code for reviewed TIM paper, Efficient Uncertainty Estimation for Hybrid Wide-Area Human Action Analysis System
Kalman Filter book using Jupyter Notebook. Focuses on building intuition and experience, not formal proofs. Includes Kalman filters,extended Kalman filters, unscented Kalman filters, particle filters, and more. All exercises include solutions.
OpenMMLab Detection Toolbox and Benchmark
A PyTorch implementation of Mnasnet: MnasNet: Platform-Aware Neural Architecture Search for Mobile.
Mobile vision models and code
mobilenetv3 with pytorch,provide pre-train model
Implementing Searching for MobileNetV3 paper using Pytorch
PyTorch*-based Neural Network Compression Framework for enhanced OpenVINO™ inference
Open Source Computer Vision Library
Simple Particle filter implementation in Python
This is the driver code for ptz motor and camera, which uses rs485 and Pelco-D control protocol. Aiming for motor controlling.
PyTorch image models, scripts, pretrained weights -- (SE)ResNet/ResNeXT, DPN, EfficientNet, MixNet, MobileNet-V3/V2/V1, MNASNet, Single-Path NAS, FBNet, and more
RetinaNet in PyTorch
Semantically consistent regularizer for zero-shot learning
Tutorial on SLAM representing a moving scene in Lie algebra and Lie group.