gustavovaliati Goto Github PK

bbox-label-tool

A simple tool for labeling object bounding boxes in images

caltech-pedestrian-dataset-to-yolo-format-converter

converts the format of the caltech pedestrian dataset to the format that yolo uses

ccv

C-based/Cached/Core Computer Vision Library, A Modern Computer Vision Library

ci724-finalwork-ppginfufpr-2016

ci724-ppginfufpr-2016

ci822-ppginfufpr-2016

Repositório de arquivos e instruções do relatório final da oficina de processamento de images CI822 do PPGInf UFPR 2016.

curso_intro_ia_jan2019

Códigos do curso de Introdução à IA

darkflow

Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices

darknet

Convolutional Neural Networks

detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

fishbook

Server with a basic functional implementation of the protocol used in the RFIDMonitor project

gmmcp_tracker

This repository contains the implementation of the GMMCP tracker published in CVPR2015

grvfishbook

gustavovaliati.github.io

Gustavo's personal home page.

keras-retinanet

Keras implementation of RetinaNet object detection.

keras-yolo3

A Keras implementation of YOLOv3 (Tensorflow backend)

map

mean Average Precision - This code evaluates the performance of your neural net for object recognition.

models

Models built with TensorFlow

obj-det-experiments

open-reid

Open source person re-identification library in python

pti01eval

Evaluation script for the paper "A Preliminary Evaluation of Pedestrian Detection on Real World Video Surveillance"

rfidmonitor

This project aims to provide a software solution for the researchers of the Itaipu dam. The system is capable of reading data from the Texas Instruments hardware. It currenly works on Linux x86_64 & arm.

rpm-rfidplatform

training_symfony2.8_angular1.5_adminlte

zm-frames-cruiser

Small app that helps navigation through ZoneMinder frames in disk. This enables faster human image analysis than looping through the ZoneMinder web interface in low performance environments.