Kaiden's Projects
An android demo for real-time single person sports counting. It is based on movenet and deployed with ncnn.
Latent Text-to-Image Diffusion
Stable Diffusion web UI
StarGAN v2 - Official PyTorch Implementation (CVPR 2020)
:fire: STEFANN: Scene Text Editor using Font Adaptive Neural Network @ The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020.
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
A simple script to forward all the messages of one chat (private/group/channel) to another. Made using Telethon. Can be used to back up the contents of a chat to another place.
A telegram forwarder that will automatically post message form Another telegram channel / group to Your telegram channel / group
[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding
Debugging, monitoring and visualization for Python Machine Learning and Data Science
This repo for enhacing the performance of yolov3
This is a repository about PCB defect detection.
Joint Detection and Embedding for fast multi-object tracking
Using Tensort to speed up yolov3 with deepsort for MOT
The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."
Background Removal based on U-Net
The official implementation of "Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting"
Demo code for journal "Vehicle Re-identification: exploring feature fusion using multi-stream convolutional networks".
Object detection for video surveillance
Improve some features from original github https://github.com/dbolya/yolact
:zap: Yolo universal target detection model combined with EfficientNet-lite, the calculation amount is only 230Mflops(0.23Bflops), and the model size is 1.3MB
yolov3 yolov4 channel and layer pruning, Knowledge Distillation 层剪枝,通道剪枝,知识蒸馏
提供对YOLOv3及Tiny的多种剪枝版本,以适应不同的需求。
YOLOv3 ModelCompression MultidatasetTraining
Implement Learning Efficient Convolutional Networks Through Network Slimming on YOLOX