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
Here I will consider the rubric points individually and describe how I addressed each point in my implementation.
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 34799
- The size of the validation set is 4410
- The size of test set is 12630
- The shape of a traffic sign image is (32, 32, 3)
- The number of unique classes/labels in the data set is 43
For exploratory visualization please see Traffic_Sign_Classifier.ipynb
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.)
Generally the idea for preprocessing the image was inspired by the published baseline model.
1.Images were transformed in the YUV space and adjusted by histogram sketching and by increasing sharpness
2.Before augmentation, I combined the original train set and valid set together, and augmented by generating 10 additional images. After that I shuffled and splited it into new train and valid set(by 20%).
3.All images were processed by transform_img function, and were augmented by augment_img function.
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.
My final model consisted of the following layers:
| Layer | Description |
|---|---|
| Input | 32x32x1 (Y channel image) |
| Convolution 5x5 | 1x1 stride, same padding, outputs 28x28x6 |
| RELU | |
| Max pooling | 2x2 stride, outputs 14x14x6 |
| Convolution 5x5 | 1x1 stride, valid padding, outputs 10x10x16 |
| RELU | |
| Max pooling | 2x2 stride, outputs 5x5x16 |
| Flatten | outputs 400 |
| Fully connected | Input 400 output 120 |
| RELU | |
| Dropout | |
| Fully connected | Input 120 output 84 |
| RELU | |
| Dropout | |
| Fully connected | Input 84 output 43 |
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.
I am using a well known architecture (LeNet) for training the model because of simplicity of implementation and because it performs well on recognition task with tens of classes. There is only one enhancement: adding dropout to mitigate overfitting.
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:
- validation set accuracy: around 95%
- test set accuracy: around 93%
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.
Please see Traffic_Sign_Classifier.ipynb
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).
Please see Traffic_Sign_Classifier.ipynb
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)
Please see Traffic_Sign_Classifier.ipynb