Are you tired by doing Annotation manually ?

Let's Automate it.

We are going to use Reverse Engineering technique. First we will detect objects into images the save their bounding box coordinates as per our requirement in XML format.

Step 1

For Anaconda python Environment

conda create -n env
Activate env 

For Linux

sudo apt install python3-venv
python3 -m venv env
source env/bin/activate

Step 2

Install dependencies pip install -r requirements.txt

Step 3

1. Download pre-trained weights from given link https://drive.google.com/file/d/1FCGAQsBADMPdyfmZrOsSDeneikGWcnlu/view
   
2. Replace yolov4-csp.weights with downloded weights (file size 202MB) in configuration directory
   

Step 4

Open Annotaions.name file present in configuration directory and edit the Labels names as per your dataset.

Step 5

Run python start_annotation.py

Bravooo

Your work is done now check Annotations folder.