Tanwar-12/Traffic-Sign-Detection-
Traffic sign detection involves the use of deep learning yolov5 techniques to identify and locate traffic signs in images or video streams. This is a critical component of many intelligent transportation systems, including autonomous vehicles and traffic management systems.
๐๐๐๐ ๐ ๐๐ ๐๐๐๐ ๐๐๐๐๐๐๐๐๐ ๐๐๐๐๐5
Detect The Traffic Sign Using YoloV5
๐๐๐๐ ๐๐๐๐๐๐๐๐๐๐:
Data Collected from Roboflow website.
๐๐๐๐: ๐๐๐ฃ๐๐๐ญ ๐๐๐ญ๐๐๐ญ๐ข๐จ๐ง
๐๐๐๐ ๐๐๐ ๐๐๐๐๐๐๐๐:
- Total 3708 traffic sign images are present in 43 classes .
- Total 2538 images for training and 701 images for validation present in 2 classes.
- Create bounding boxes with the help of makesense.ai website.
๐๐๐๐ ๐ ๐๐ ๐๐๐๐
๐๐๐๐ ๐๐๐๐๐๐๐๐๐๐:
-
Prepare folder structure that can be accept by YoloV5.
-
Total 3708 images for training and 352 images for validation present in 43 classes.
-
Create a bounding boxes with the help of label-img And makesense.ai website according to YoloV5.
๐๐๐๐๐ ๐๐ ๐๐๐ ๐๐๐๐๐5
-
Cloning the YoloV5 file from official repository.
-
Changing the directory of yolov5
-
Installing the dependencies
-
Download all versions pre-trained weights
๐๐๐๐๐ ๐๐๐ ๐๐๐ ๐๐๐๐๐๐๐๐ ๐๐๐๐๐๐ ๐๐๐๐๐๐๐:
-
Go to yolov5/data/
-
Open coco128.yaml
-
Edit the following inside it:
A. Training and Validation file path
B. Number of classes and Class names.
๐๐๐๐๐๐๐๐ ๐๐๐๐๐5 ๐๐๐๐๐:
- Set images size 408 with batch of 8
- Train model on 1000 epochs
- Gives the data file path as well as give pre-trained weights path.
VISUALISE THE TRAINING METRICS WITH THE HELP OF TENSORBOARD
๐๐๐๐๐๐๐๐๐ ๐๐๐๐๐๐:
