Deploy YOLOv5 Object Detection on Streamlit

[thepbordin]

YOLOv5 Streamlit Deployment

Github : GitHub - thepbordin/YOLOv5-Streamlit-Deployment: A easy-to-use streamlit web application for yolov5 trained model, feel free to use, edit.

Easy way to deploy YOLOv5 to streamlit cloud.

Please feel free to use/edit.

codes modified by GitHub/thepbordin from GitHub/zhoroh

Clone This repo and read install instruction from Installation Guide.

Features

• Support large model file. (Don’t require GitLFS; Download model from URL)

• Support small model file. (<100MB; uploaded to github repository)

• Select images randomly by slider from test set

• Upload image/video

• Select computing device (cuda/cpu)

Installation Guide

configs can be found in app.py

Download model from URL:

1. Upload model to Internet Archive

2. Go to your uploaded file page.

3. From “DOWNLOAD OPTIONS” select “SHOW ALL”.

4. Right click at .pt and Copy link address.

5. Edit config in app.py

• cfg_enable_url_download = True

• url = “”

cfg_enable_url_download = True
url = "your_model_url"

Use local .pt file:

Edit config in app.py

## CFG
cfg_model_path = "models/your_model_name.pt"