Notebook: De-noising Autoencoder

Try defining and training an autoencoder for denoising images!

To open this notebook, you have two options:

• Go to the next page in the classroom (recommended).
• Clone the repo from Github and open the notebook Denoising_Autoencoder_Exercise.ipynb in the autoencoder > denoising-autoencoder folder. You can either download the repository with git clone https://github.com/udacity/deep-learning-v2-pytorch.git , or download it as an archive file from this link .

Instructions

• Define and train a convolutional autoencoder
• Add more/deeper layers to create a successful de-noiser

This is a self-assessed lab. If you need any help or want to check your answers, feel free to check out one kind of solution in the following notebook, or by clicking here .

Exercise: GPU Workspaces

You do not need to enable GPU to complete this exercise. This is left as an optional exercise; you will be responsible for moving your models and data to GPU, should you choose to enable it.

The next workspace is GPU-enabled , which means you can select to train on a GPU instance. The recommendation is this:

• Load in and test models while in CPU (non-enabled) mode
• When you're ready to extensively train and test your model, you'll have to add GPU functionality (in this case, the code is not provided for you)
• Once you've moved your model and data to GPU, you can enable GPU to quickly train the model!

All models and data they see as input will have to be moved to the GPU device, so take note of the relevant movement code in the model creation and training process.