GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → NikolasEnt → Traffic Sign Classifier

NikolasEnt / Traffic Sign Classifier

Udacity Self-Driving Car Engineer Nanodegree. Project: Build a Traffic Sign Recognition Classifier

Labels

jupyter-notebookdeep-learningconvolutional-neural-networksneural-networksself-driving-car

Projects that are alternatives of or similar to Traffic Sign Classifier

Teacher Student Training
This repository stores the files used for my summer internship's work on "teacher-student learning", an experimental method for training deep neural networks using a trained teacher model.
Stars: ✭ 34 (+183.33%)
Mutual labels:  jupyter-notebook, convolutional-neural-networks, neural-networks
Coursera Deep Learning Specialization
Notes, programming assignments and quizzes from all courses within the Coursera Deep Learning specialization offered by deeplearning.ai: (i) Neural Networks and Deep Learning; (ii) Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization; (iii) Structuring Machine Learning Projects; (iv) Convolutional Neural Networks; (v) Sequence Models
Stars: ✭ 188 (+1466.67%)
Mutual labels:  jupyter-notebook, convolutional-neural-networks, neural-networks
Yann
This toolbox is support material for the book on CNN (http://www.convolution.network).
Stars: ✭ 41 (+241.67%)
Mutual labels:  jupyter-notebook, convolutional-neural-networks, neural-networks
Deep learning projects
Stars: ✭ 28 (+133.33%)
Mutual labels:  jupyter-notebook, convolutional-neural-networks, neural-networks
Deeplearning.ai Assignments
Stars: ✭ 268 (+2133.33%)
Mutual labels:  jupyter-notebook, convolutional-neural-networks, neural-networks
Convisualize nb
Visualisations for Convolutional Neural Networks in Pytorch
Stars: ✭ 57 (+375%)
Mutual labels:  jupyter-notebook, convolutional-neural-networks, neural-networks
Sigmoidal ai
Tutoriais de Python, Data Science, Machine Learning e Deep Learning - Sigmoidal
Stars: ✭ 103 (+758.33%)
Mutual labels:  jupyter-notebook, convolutional-neural-networks, neural-networks
Deep Learning With Python
Deep learning codes and projects using Python
Stars: ✭ 195 (+1525%)
Mutual labels:  jupyter-notebook, convolutional-neural-networks, neural-networks
Image To 3d Bbox
Build a CNN network to predict 3D bounding box of car from 2D image.
Stars: ✭ 200 (+1566.67%)
Mutual labels:  self-driving-car, jupyter-notebook, convolutional-neural-networks
Gtsrb
Convolutional Neural Network for German Traffic Sign Recognition Benchmark
Stars: ✭ 65 (+441.67%)
Mutual labels:  self-driving-car, jupyter-notebook, convolutional-neural-networks
Easy Deep Learning With Keras
Keras tutorial for beginners (using TF backend)
Stars: ✭ 367 (+2958.33%)
Mutual labels:  jupyter-notebook, convolutional-neural-networks, neural-networks
Cs231
Complete Assignments for CS231n: Convolutional Neural Networks for Visual Recognition
Stars: ✭ 317 (+2541.67%)
Mutual labels:  jupyter-notebook, convolutional-neural-networks, neural-networks
Tensorflow 101
TensorFlow 101: Introduction to Deep Learning for Python Within TensorFlow
Stars: ✭ 642 (+5250%)
Mutual labels:  jupyter-notebook, convolutional-neural-networks, neural-networks
Xnnpack
High-efficiency floating-point neural network inference operators for mobile, server, and Web
Stars: ✭ 808 (+6633.33%)
Mutual labels:  convolutional-neural-networks, neural-networks
Deepmedic
Efficient Multi-Scale 3D Convolutional Neural Network for Segmentation of 3D Medical Scans
Stars: ✭ 809 (+6641.67%)
Mutual labels:  convolutional-neural-networks, neural-networks
Basic reinforcement learning
An introductory series to Reinforcement Learning (RL) with comprehensive step-by-step tutorials.
Stars: ✭ 826 (+6783.33%)
Mutual labels:  jupyter-notebook, neural-networks
Skin Cancer Image Classification
Skin cancer classification using Inceptionv3
Stars: ✭ 16 (+33.33%)
Mutual labels:  jupyter-notebook, convolutional-neural-networks
Sincnet
SincNet is a neural architecture for efficiently processing raw audio samples.
Stars: ✭ 764 (+6266.67%)
Mutual labels:  convolutional-neural-networks, neural-networks
Awesome Ai Ml Dl
Awesome Artificial Intelligence, Machine Learning and Deep Learning as we learn it. Study notes and a curated list of awesome resources of such topics.
Stars: ✭ 831 (+6825%)
Mutual labels:  jupyter-notebook, neural-networks
Tensorrider self driving car
基于BP神经网络的自动驾驶模型车。包含收集数据、控制模型生成与在线/离线自动运行所需的程序。
Stars: ✭ 17 (+41.67%)
Mutual labels:  self-driving-car, jupyter-notebook
View All Similar Projects ➔

Traffic Sign Classifier

image 1 image 2 image 3 image 8 image 10 image 11

This repo contains code for images of traffic sign classification from German Traffic Sign Database GTSRB. Originally, it was the task of the second project from Udacity Self-Driving Car Engineer Nanodegree, but now there are some my independent experiments added. The train dataset consists of 39209 images with 32x32 px resolution, test dataset - 12630. The datasets were provided by Udacity.

Notebooks:

Traffic_Sign_Classifier.ipynb Udacity Self-Driving Car Engineer Nanodegree. Project: Build a Traffic Sign Recognition Classifier. Finally, 95.0% accuracy on the test dataset achieved with one Convolutional neural network, based on GoogLeNet inception modules. The code uses TensorFlow only. Look through this file to make yourself familiar with data and the implementation. train_log_f.csv is a log file of the CNN training process.

Traffic_Sign_Classifier-2Net.ipynb Experiments with two Convolutional neural network, also based on inception modules. Basic idea: train two CNN: one - for traffic sign classification in general, and second - for numbers on speed limit sign classification. It should work better then only one CNN, which was used originally for the project as it was observed, that it usually wrong classify speed limits, but is correct about sign type. This implementation uses Keras with TensorFlow as backend. Under development

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].