We've prepared a Jupyter notebook that will guide you through the process of creating a convolutional neural network in TensorFlow.
Make sure you have followed the instructions in the classroom to setup your environment. You can also utilize the AWS GPU instances for this lab, although you can manage quite well with just a CPU. The instructions for AWS can be found [here].
Run the following commands from the same directory as the commands above.
$ git clone https://github.com/udacity/RoboND-CNN-Lab.git
$ activate RoboND
$ jupyter notebook
The above will open the jupyter interface in your browser from where you can access the Lab folder and the jupyter notebook CNN_lab.ipynb
This is a self-assessed lab. Feel free to compare your results and discuss on improvements with your fellow students in the Slack!