Description
Note:
• In Homework #2 mini-project assignment, you will build and train a convolutional neural
networks (classifier) for traffic sign recognition based on German Traffic Sign Dataset, with an accuracy on the validation set of 95% or greater.
Submission files (to Canvas):
- Jupyter notebook with code or python file with code
- PDF of the code
- A writeup PDF report:
o The report would describe the main steps that you used to § explore the dataset
§ design and test your classifier
§ use your classifier to make predictions on the new images o Please include the necessary code or figures
- Import your data:
a. We’ve provided the dataset through canvas which includes the training, validation and test set.
b. Please use the following code to import your data:
- (10 points) Data Exploration:
a.Dataset Summary
- Number of samples in each set
- Shape of the traffic image ie. (x, x, x)
- Number of classes/labels
Page 1 of 2
b. Exploratory Visualization
i. For each class/label, plot a sample image
- Â Design and Test a Classifier (or model architecture)
- Preprocess the dataset using techniques such as normalization, colors
converting, and explain why you choose those techniques in report
- Â Design your model architecture with at least 5 layers, and show the
architecture in your report
- Â Compile your model: choose the loss function, optimizer, and metrics,
batch size, number of epochs, and other relevant values of hyperparameters
- Â Train your model, and plot your training history
- ) Tune your model or change your model if your validation accuracy is
less than 95%, and save your final model which has a validation accuracy higher
than 95%
-  Evaluate your final model’s performance, and make predictions on 10
randomly selected test image
- Preprocess the dataset using techniques such as normalization, colors
- Â Test Your Classifier on New Images
- (Download 10 pictures of the traffic signs from the internet and use your model to predict the traffic sign type. You might need to preprocess the pictures.
- Â Output the top 5 softmax probabilities for each above picture
- (optional bonus: 5 points) Visualize selected layers of convolutional neural networks of the test images to help you understand what features your model extracted from the
images.