Object Detection on Webcam Using YOLOv4

clone darknet repo: !git clone https://github.com/AlexeyAB/darknet

• This repository consists of files required to deploy a Object Detection on Webcam

• Please do ⭐ the repository, if it helped you in anyway.

Authors

• @Akash Kumar Jha

Deployment

1. import dependent libraries.
2. clone darknet repo:!git clone https://github.com/AlexeyAB/darknet
3. change makefile to have GPU, OPENCV and LIBSO enabled.
4. make darknet (builds darknet so that you can then use the darknet.py file and have its dependencies)
5. get the scaled yolov4 weights file that is pre-trained to detect 80 classes (objects) from shared google drive.
6. import darknet functions to perform object detections
7. get image ratios to convert bounding boxes to proper size.
8. run model on darknet style image to get detections
9. run test on person.jpg image that comes with repository.

Installation

To install the libraries used in this project. Follow the below steps:

from IPython.display import display, Javascript, Image
from google.colab.output import eval_js
from google.colab.patches import cv2_imshow
from base64 import b64decode, b64encode
import cv2
import numpy as np
import PIL
import io
import html
import time
import matplotlib.pyplot as plt
%matplotlib inline

Running Flask Api

To run tests, run the following command

  python app.py

🚀 About Me

Data Scientist Enthusiast | Petroleum Engineer Graduate | Solving Problems Using Data

Hi, I'm Akash! 👋

🔗 Links

Tech Stack

Other Me

👩‍💻 I’m interested in Petroleum Engineering

🧠 I’m currently learning Data Scientist | Data Analytics | Business Analytics

👯‍♀️ I’m looking to collaborate on Ideas & Data

🛠 Skills

1. Data Scientist
2. Data Analyst
3. Business Analyst
4. Machine Learning

Future Plans

⚡️ Looking forward to help drive innovations into your company as a Data Scientist

⚡️ Looking forward to offer more than I take and leave the place better than i found