Preprocess notMNIST data and train a neural net on it
We've prepared a Jupyter notebook that will guide you through the process of creating a single layer neural network in TensorFlow.
If you don't have Docker already, download and install Docker from here.
Run the command below to clone the Lab Repository:
$ git clone https://github.com/udacity/CarND-TensorFlow-Lab.git
After running the command above, follow the “Run the Notebook” instructions to start the lab.
This lab requires Anaconda and Python 3.4 or higher. If you don't meet all of these requirements, install the appropriate package(s).
Run these commands in your terminal to install all requirements:
$ git clone https://github.com/udacity/CarND-TensorFlow-Lab.git
$ conda env create -f environment.yml
$ conda install --name CarND-TensorFlow-Lab -c conda-forge tensorflow
Make sure to run the server from the same directory that you ran in the Setup steps above.
$ docker run -it -p 8888:8888 -v `pwd`:/notebooks udacity/carnd-tensorflow-lab
$ source activate CarND-TensorFlow-Lab
$ jupyter notebook
You setup your environment in the Setup steps and started a Jupyter server in the Start a Jupyter Server instructions above. Open a browser window and go here. This is the notebook you'll be working on. The notebook has 3 problems for you to solve:
- Problem 1: Normalize the features
- Problem 2: Use TensorFlow operations to create features, labels, weight, and biases tensors
- Problem 3: Tune the learning rate, number of steps, and batch size for the best accuracy
This is a self-assessed lab. Compare your answers to the solutions here. If you have any difficulty completing the lab, Udacity provides a few services to answer any questions you might have.
Remember that you can get assistance from your mentor, the Forums, or the Slack channel. You can also review the concepts from the previous lessons.