fatih akyon
fatih akyon
you can use https://github.com/fcakyon/labelme2coco for improved version
Hello, @jegork thanks for the PR! Having some experience in adding tests and fixing repo-consistency/style, I can help you with these aspects if you need any :+1: Feel free to...
@johko have you started implementing it?
@johko I totally understand it. Interested in your implementation since I will be using VATT in my research next year :) Are you working on a TF implementation?
@johko, thanks for the response! I may also help with the pytorch part once you finalize the TF implementation 👍
@yancie-yjr use https://github.com/fcakyon/labelme2coco for improved version
@AliceDinh you can use [labelme2coco](https://pypi.org/project/labelme2coco/) package to convert your annotations to coco format. It is really easy. Installation: ```bash pip install labelme2coco ``` Usage: ```python # import package import labelme2coco...
@loyanie Can you tell me more on your setup? Are you on Linux? Have you installed the package via pip or did you setup from the source? If from pip,...
@kadirnar resize islemi her kutuphaneye ozel oluyor, yolov5/v7de kendi icinde hallediyor mesela, o yuzden resize isleminin frameworke ozel olarak hazirlanmasi gerekiyor.
nms icin ek input almaya gerek yok, yolox kutuphanesindeki default deger (0.3) kullanilabilir, isteyen extra DetectionModel.model.nmsthre =0.4 seklinde de set edebilir (self.model e Predictor instanceini atiyorsun diye kabul ediyorum)