Clasificador de cómo se usa un cubrebocas. Desarrollado con Yolact

YOLACT++ instance segmentation custom training

This project provides an HMI for hand segmentation. It runs the YOLACT Neural Network on Image and Video Files, and on Webcam flows.

This project aims to experiment the trained backbones of different self-supervised methods on Yolact algorithm for object detection and segmetation

Yolact++ training with custom dataset (coco.json format) in Google Colab

Portable YOLACT Edge python package

"Machine learning in applications" project @ Politecnico di Torino, a.y. 2021/2022.

Instance Segmentation Using YOLACT

This is an implementation of an adaptive cruise control system based on a computer vision pipeline. This work is based on YOLACT, a State-Of-The-Art real-time instance segmentation network. You're welcome to test and try our code, we hope you'll enjoy this work!

可以直接用于mmdetection的Mask RCNN、SOLOv2、YOLACT模型输出json文件的可视化

Code and docker files for the yolact framework.

This is a real time instance segmentation task implemented with YOLACT++ and DCNv2 on Google Colab.

A lane detection integrated Real-time Instance Segmentation based on YOLACT (You Only Look At CoefficienTs)

Real time person extraction with utmost accuracy

Yolact running on the ncnn framework on a bare Raspberry Pi 4 with 64 OS, overclocked to 1950 MHz

YOLACT execution with TensorRT

ROS wrapper for yolact instance segmentation with depth image extension for 3D bounding boxes and pointcloud segmentation

Used Yolact++ to implement social distance monitoring.

Provides a conversion flow for YOLACT_Edge to models compatible with ONNX, TensorRT, OpenVINO and Myriad (OAK). My own implementation of post-processing allows for e2e inference. Support for Multi-Class NonMaximumSuppression, CombinedNonMaxSuppression.