UdacitySignClassifier
所属分类：人工智能/神经网络/深度学习
开发工具：Jupyter Notebook
文件大小：35847KB
下载次数：0
上传日期：2017-02-22 10:38:13
上 传 者：
sh-1993
说明： 使用深度神经网络和卷积神经网络对交通标志进行分类。准确度约为97.5%。
(Classify Traffic Signs with deep neural networks & convolutional neural networks. Accuracy roughly 97.5%.)
文件列表:
Traffic_Sign_Classifier.ipynb (906488, 2017-02-22)
checkpoint (95, 2017-02-22)
new_signs (0, 2017-02-22)
new_signs\0.jpg (1856, 2017-02-22)
new_signs\1.jpg (1714, 2017-02-22)
new_signs\12.jpg (1518, 2017-02-22)
new_signs\13.jpg (1517, 2017-02-22)
new_signs\14.jpg (1135, 2017-02-22)
new_signs\17.jpg (1568, 2017-02-22)
new_signs\18.jpg (1685, 2017-02-22)
new_signs\19.jpg (1617, 2017-02-22)
new_signs\2.jpg (1707, 2017-02-22)
new_signs\25.jpg (1712, 2017-02-22)
new_signs\3.jpg (1686, 2017-02-22)
new_signs\32.jpg (1458, 2017-02-22)
new_signs\36.jpg (1617, 2017-02-22)
new_signs\37.jpg (1623, 2017-02-22)
new_signs\38.jpg (1554, 2017-02-22)
new_signs\40.jpg (1682, 2017-02-22)
new_signs\7.jpg (1689, 2017-02-22)
new_signs\9.jpg (1623, 2017-02-22)
prediction.txt (0, 2017-02-22)
signnames.csv (999, 2017-02-22)
train_tf_model.ckpt.data-00000-of-00001 (65690468, 2017-02-22)
train_tf_model.ckpt.index (2166, 2017-02-22)
train_tf_model.ckpt.meta (283506, 2017-02-22)
## Project: Build a Traffic Sign Recognition Program
[](http://www.udacity.com/drive)
### Overview
In this project, you will use what you've learned about deep neural networks and convolutional neural networks to classify traffic signs. You will train a model so it can decode traffic signs from natural images by using the [German Traffic Sign Dataset](http://benchmark.ini.rub.de/?section=gtsrb&subsection=dataset). After the model is trained, you will then test your model program on new images of traffic signs you find on the web, or, if you're feeling adventurous pictures of traffic signs you find locally!
### Dependencies
This lab requires:
* [CarND Term1 Starter Kit](https://github.com/udacity/CarND-Term1-Starter-Kit)
The lab enviroment can be created with CarND Term1 Starter Kit. Click [here](https://github.com/udacity/CarND-Term1-Starter-Kit/blob/master/README.md) for the details.
### Dataset
1. [Download the dataset](https://d17h27t6h515a5.cloudfront.net/topher/2016/November/581faac4_traffic-signs-data/traffic-signs-data.zip). This is a pickled dataset in which we've already resized the images to 32x32.
2. Clone the project and start the notebook.
```sh
git clone https://github.com/udacity/CarND-Traffic-Sign-Classifier-Project
cd CarND-Traffic-Sign-Classifier-Project
jupyter notebook Traffic_Sign_Classifier.ipynb
```
3. Follow the instructions in the `Traffic_Sign_Recognition.ipynb` notebook.
近期下载者：
相关文件：
收藏者：