mdhamani/traffic-sign-recognition-using-yolo

Identifying traffic signs in real time using YOLO for autonomous self driving car

Traffic-Sign-Recognition-Using-YOLO

This repository contains model and training notebook for traffic sign recognition

Dataset

The dataset used for training is German Traffic Sign Recognition Benchmark (GTSRB) containing 43 classes of traffic signs. The training set contains 39209 labeled images and the test set contains 12630 unlabelled images.

Model

Using and YOLOv5 for training and achieved >93% mAP on the dataset.

Report

Used WandB to log hyperparameters and output metrics from runs.

Download the model

traffic-sign-recognition-using-yolo's Issues

no module named 'utils.datasets'

When I try to run the detect.py script I got error like that: from utils.datasets import LoadStreams, LoadImages
ModuleNotFoundError: No module named 'utils.datasets'

I have no idea what to do. I need help at that point.
Thanks

Can u share detect.py code and instructions how to run .pt model in windows please

Can u share detect.py code and instructions how to run .pt model in windows please

question

Hello , from where do i get the annotated data in yolo format ?
Thank you

Following files are missing

I was going through the python notebook, in the training command i.e.
'!./darknet/darknet detector train labelled_data.data yolov3-tiny_custom.cfg backup/yolov3-tiny_custom_best.weights -dont_show -map'
we would be requiring the following files:-
yolov3-tiny_custom_best.weights,yolov3-tiny_custom.cfg
Please provide these files or let me know where to get them from.