In this project, I trained the YOLOv5 model for object detection and created a Streamlit web application to perform object detection on uploaded images. The YOLOv5 model was trained to detect various objects, and the trained model is integrated into a user-friendly web interface using Streamlit.
I initially trained the YOLOv5 model from scratch using Google Colab and Google Drive. The model was trained to detect a variety of objects, including but not limited to persons, cars, chairs, bottles, and animals. For more details on the training process, refer to the YOLOv5 repository.
I have created a Streamlit web application that allows users to upload images and perform object detection using the trained YOLOv5 model. The web app provides a user-friendly interface to visualize the detection results and gain insights into the objects present in the uploaded images.
You can test the web app by clicking here.
-
Clone this repository to your local machine:
git clone https://github.com/mouraffa/RealTime-Object-Detection-YOLOv5.git
-
Install the required packages from the
requirements.txt
file:
pip install -r requirements.txt
-
Run the Streamlit web app locally:
streamlit run Home.py
-
Access the web app in your web browser and follow the instructions to upload an image and perform object detection.
Here are some examples of test results obtained using the Streamlit web app:
Contributions are welcome! If you find any issues or would like to enhance the project, feel free to submit pull requests or open issues.