Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/taunusflieger/carnd-traffic-sign-classifier-project


https://github.com/taunusflieger/carnd-traffic-sign-classifier-project

Last synced: about 2 months ago
JSON representation

Awesome Lists containing this project

README 

        
# **Traffic Sign Recognition** 



## Writeup



### You can use this file as a template for your writeup if you want to submit it as a markdown file, but feel free to use some other method and submit a pdf if you prefer.



---



**Build a Traffic Sign Recognition Project**



The goals / steps of this project are the following:

* Load the data set (see below for links to the project data set)

* Explore, summarize and visualize the data set

* Design, train and test a model architecture

* Use the model to make predictions on new images

* Analyze the softmax probabilities of the new images

* Summarize the results with a written report



[//]: # (Image References)



[image1]: ./writeup-img/output_11_0.png "Visualization"

[image2]: ./writeup-img/output_13_0.png "Visualization"

[image3]: ./writeup-img/output_18_1.png "Visualization"

[image4]: ./writeup-img/output_27_0.png "Visualization"

[image5]: ./writeup-img/output_34_0.png "Visualization"

[image6]: ./writeup-img/output_37_1.png "Visualization"

[image7]: ./writeup-img/output_42_0.png "Visualization"



## Rubric Points

### Here I will consider the [rubric points](https://review.udacity.com/#!/rubrics/481/view) individually and describe how I addressed each point in my implementation.  



## Submission Files



This project includes



* The notebook Traffic_Sign_Classifier.ipynb (and signames.csv for completeness)

* report.html, the exported HTML version of the python notebook

* A directory test-data containing images found on the web

* writeup.md, which you're reading



---

### Writeup / README



#### 1. Provide a Writeup / README that includes all the rubric points and how you addressed each one. You can submit your writeup as markdown or pdf. You can use this template as a guide for writing the report. The submission includes the project code.



You're reading it! 



### Data Set Summary & Exploration



#### 1. Provide a basic summary of the data set. In the code, the analysis should be done using python, numpy and/or pandas methods rather than hardcoding results manually.



I used the pandas library to calculate summary statistics of the traffic

signs data set:



* The size of training set is ?



Number of training examples = 34799

* The size of the validation set is ?



Number of validation examples =  4410

* The size of test set is ?



Number of testing examples = 12630

* The shape of a traffic sign image is ?



Image data shape = (32, 32)

* The number of unique classes/labels in the data set is ?



Number of classes = 43



#### 2. Include an exploratory visualization of the dataset.



Here is an exploratory visualization of the data set. It is a bar chart showing how the data is distributed. From the chart it is clear that the examples in the training set are not evenly distributed across the different classes.



![alt text][image1]



The following image shows randomly selected sample images from the test dataset



![alt text][image2]



### Design and Test a Model Architecture



#### 1. Describe how you preprocessed the image data. What techniques were chosen and why did you choose these techniques? Consider including images showing the output of each preprocessing technique. Pre-processing refers to techniques such as converting to grayscale, normalization, etc. (OPTIONAL: As described in the "Stand Out Suggestions" part of the rubric, if you generated additional data for training, describe why you decided to generate additional data, how you generated the data, and provide example images of the additional data. Then describe the characteristics of the augmented training set like number of images in the set, number of images for each class, etc.)



The code processing images is in cell 8.



As a first step, I decided to convert the images to gray scale because colors in the traffic sign are important in real world for people to recognize different signs, traffic signs are also different in their shapes and contents. We can ignore colors because signs in our training set are differentiable from their contents and shapes, and the network seems having no problem to learn just from shapes.



Therefore, my preprocessing phase normalizes images and transforms it to gray scale.



The following image shows an example of the gray scale conversion

![alt text][image3]



#### 2. Describe what your final model architecture looks like including model type, layers, layer sizes, connectivity, etc.) Consider including a diagram and/or table describing the final model.



I adapted LeNet architecture: Two convolutional layers followed by one flatten layer, drop out layer, and three fully connected linear layers. My final model consisted of the following layers:



| Layer         		|     Description	        					| 

|:---------------------:|:---------------------------------------------:| 

| Input         		| 32x32x1							            | 

| Convolution 3x3     	| 1x1 stride, same padding, outputs 28x28x12 	|

| Max Pooling 	      	| 2x2 stride,  outputs 14x14x12 			    |

| Convolution 3x3	    | 1x1 stride, same padding, outputs  14x14x12  	|

| Max Pooling 	      	| 2x2 stride,  outputs 5x5x25				    |

| Dropout				| 625 input, output 625							|

| Fully Connected		| 625 input, output 300       					|

| Fully Connected		| 300 input, output 100      					|

| Fully Connected		| 100 input, output 43 (number of classes)		|

|						|												|

 



#### 3. Describe how you trained your model. The discussion can include the type of optimizer, the batch size, number of epochs and any hyperparameters such as learning rate.



To train the model, I used the following parameters:



* learning rate = 0.001

* optimizer = AdamOptimizer with a learning rate of 0.001

* batch size = 256

* max epochs = 30



#### 4. Describe the approach taken for finding a solution and getting the validation set accuracy to be at least 0.93. Include in the discussion the results on the training, validation and test sets and where in the code these were calculated. Your approach may have been an iterative process, in which case, outline the steps you took to get to the final solution and why you chose those steps. Perhaps your solution involved an already well known implementation or architecture. In this case, discuss why you think the architecture is suitable for the current problem.



My final model results were:

* training set accuracy of 1.000

* validation set accuracy of 0.951

* test set accuracy of 0.934



If a well known architecture was chosen:

* What architecture was chosen? LeNet architecture

* Why did you believe it would be relevant to the traffic sign application? Because it was introduced within the training as a suitable architecture

* How does the final model's accuracy on the training, validation and test set provide evidence that the model is working well? The achieved accuracy for the test and validation data set indicates that the model is suitable for the task.

 



### Test a Model on New Images



#### 1. Choose five German traffic signs found on the web and provide them in the report. For each image, discuss what quality or qualities might be difficult to classify.



Here are five German traffic signs that I found on the web:



![alt text][image5] 



The quality of the images is good and I'm not expecting any difficulties to classify them



#### 2. Discuss the model's predictions on these new traffic signs and compare the results to predicting on the test set. At a minimum, discuss what the predictions were, the accuracy on these new predictions, and compare the accuracy to the accuracy on the test set (OPTIONAL: Discuss the results in more detail as described in the "Stand Out Suggestions" part of the rubric).



Here are the results of the prediction:



![alt text][image6] 



The model was able to correctly guess 6 of the 6 traffic signs, which gives an accuracy of 100%. This is an excellent result. It might be different in case the images are less clear, but for these images it was expected.



#### 3. Describe how certain the model is when predicting on each of the five new images by looking at the softmax probabilities for each prediction. Provide the top 5 softmax probabilities for each image along with the sign type of each probability. (OPTIONAL: as described in the "Stand Out Suggestions" part of the rubric, visualizations can also be provided such as bar charts)



The code for making predictions on my final model is located in the 11th cell of the Ipython notebook.



The fourth image is least well detected image - might be due to the perspective, but still it has been detected with a probability of 98% - a very good result



![alt text][image6]