Alexander's repositories
caffe_s3fd
caffe for s3fd face detection
S3FD.PyTorch
A higher performance PyTorch implementation of S3FD
maskrcnn_benchmark_mobilenetv2
maskcnn_benchmark based on mobilenetv2
channel_pruning_lasso
channel pruning for accelerating very deep neural networks
gesture_recognition
hand gesture recognition
mmdetection_lqy
add mobilenet_v2_ssdlite
face_cluster
face cluster based on chinese whispers algorithm
model-compression
model compression based on pytorch (1、quantization: 8/4/2bits(dorefa)、ternary/binary value(twn/bnn/xnor-net)；2、 pruning: normal、regular and group convolutional channel pruning；3、 group convolution structure；4、batch-normalization folding for binary value of feature(A))
awesome-action-recognition
A curated list of action recognition and related area resources
darts_notes
add annotations
Face-alignment-mobilenet-v2
Face Alignment by Mobilenetv2
face_utils
includes face cluster & face detection & face feature extraction
Fast_Human_Pose_Estimation_Pytorch
Pytorch Code for CVPR2019 paper "Fast Human Pose Estimation" https://arxiv.org/abs/1811.05419
github_images
readme_images
knowledge-distillation-pytorch
A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility
ncnn_106landmarks
face detection: retinaface, landmark: zqcnn, recognize: mobilefacenet, Based on ncnn
Online-Realtime-Action-Recognition-based-on-OpenPose
A skeleton-based real-time online action recognition project, classifying and recognizing base on framewise joints, which can be used for safety surveilence.
pytorch-ssd
MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch 1.0 / Pytorch 0.4. Out-of-box support for retraining on Open Images dataset. ONNX and Caffe2 support. Experiment Ideas like CoordConv.
realtime-action-detection
This repository host the code for real-time action detection paper
Realtime-Action-Recognition
Multi-person real-time recognition (classification) of 9 actions based on human skeleton from OpenPose and a 0.5-second window.
thrift_demo
thrift_demo includes face detection & face cluster & face feature extraction
thriftlearn
thrift demo
YOLOv3-complete-pruning
提供对YOLOv3及Tiny的多种剪枝版本，以适应不同的需求。
YOLOv3-model-pruning
对 YOLOv3 做模型剪枝，在 oxford hand 数据集上模型的参数量减少 80% ，FLOPs 降低 70%，Infer 的速度可以达到原来的 200%，mAP 基本保持不变