Stars
This is a modified version of maskrcnn-benchmark by facebook. The code works on Cuda11.6 and Pytorch 1.13.1
Official implementation of "Segment Any Anomaly without Training via Hybrid Prompt Regularization (SAA+)".
A fast and robust point cloud registration library
https://www.youtube.com/channel/UC34rW-HtPJulxr5wp2Xa04w?sub_confirmation=1
Accurate Subpixel Edge Location Based on Partial Area Effect
linux 编程环境学习笔记，含 linux 基本命令，linux 操作系统，linux 下 C++ 编程等
Unofficial Pytorch-Implementation of "1M parameters are enough? A lightweight CNN-Based model for medical image segmentation".
MedSeg: Medical Image Segmentation GUI Toolbox 可视化医学图像分割工具箱
PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.
Implementation of MobileNet, MobileNetv2, ShuffleNet, ShuffleNetv2, EfficientNet in Pytorch.
All Algorithms implemented in Python
Central Difference Convolutional Networks (CVPR'20)
A general and accurate MACs / FLOPs profiler for PyTorch models
A curated list of neural network pruning resources.
Neural Network Blocks - Collect all kinds of fancy model blocks for you to build more powerful neural network model.
🍅🍅🍅YOLOv5-Lite: Evolved from yolov5 and the size of model is only 900+kb (int8) and 1.7M (fp16). Reach 15 FPS on the Raspberry Pi 4B~
yolov3 yolov4 channel and layer pruning, Knowledge Distillation 层剪枝，通道剪枝，知识蒸馏
We developed a python UI based on labelme and segment-anything for pixel-level annotation. It support multiple masks generation by SAM(box/point prompt), efficient polygon modification and category…