This project demonstrates object detection using TensorFlow's SSD MobileNet V2 model, a pre-trained model from the TensorFlow Object Detection API. The model is capable of detecting common objects in images with bounding boxes, class labels, and confidence scores(ranges from 0 = [lowest] to 1 = [highest] the closer the score is to 1 the better).
Run locally
git clone https://github.com/iBz-04/Obj-detection
cd https://github.com/iBz-04/Obj-detection
- Python 3.x
- TensorFlow 2.x
- NumPy
- OpenCV (cv2)
- Pillow (PIL)
- Matplotlib
Clone the project
git clone https://github.com/iBz-04/Obj-detection
Go to the project directory
cd https://github.com/iBz-04/Obj-detection
Install dependencies
pip install tensorflow
pip install numpy
pip install opencv-python
pip install pillow
pip install matplotlib
- Download the pre-trained SSD MobileNet V2 model from the TensorFlow Model Zoo and place it in the models/ssd_mobilenet_v2_fpnlite_640x640_coco17_tpu-8/ directory
When you run the script on an image, the output will look similar to this: