Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/devdezzies/gtsrb-traffic-vision
Replicating LeNet-5 convolutional neural network architecture with PyTorch to predict traffic signs using German Traffic Sign Recognition Benchmark (GTSRB) dataset.
https://github.com/devdezzies/gtsrb-traffic-vision
computer-vision convolutional-neural-networks deep-learning image-classifier lenet-5 machine-learning pytorch self-driving-car
Last synced: about 2 months ago
JSON representation
Replicating LeNet-5 convolutional neural network architecture with PyTorch to predict traffic signs using German Traffic Sign Recognition Benchmark (GTSRB) dataset.
- Host: GitHub
- URL: https://github.com/devdezzies/gtsrb-traffic-vision
- Owner: devdezzies
- Created: 2024-08-07T02:21:34.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2024-08-08T06:00:41.000Z (5 months ago)
- Last Synced: 2024-08-08T11:14:27.057Z (5 months ago)
- Topics: computer-vision, convolutional-neural-networks, deep-learning, image-classifier, lenet-5, machine-learning, pytorch, self-driving-car
- Language: Jupyter Notebook
- Homepage:
- Size: 3.36 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# GTSRB Traffic Vision with LeNet-5 (modified)
An image classifier using Convolutional Neural Network (CNN) to predict German traffic signs.
[_source_](https://www.kaggle.com/datasets/meowmeowmeowmeowmeow/gtsrb-german-traffic-sign?select=Train.csv)
# Overview dataset
German Traffic Sign Recognition Benchmark (GTSRB) is a large multi-category classification benchmark. The first was used in a competition at IJCNN 2011. The images are classified into 43 classes, consisting of 26640 training labeled images and 12630 testing set.
# Models
There are few trained models with different configuration and CNN architecture
* GTSRBModelV0
* GTSRBModelV1 (work in progress)
# Sample Predictions
**model:** GTSRBModelV0