Image Generation - Google DeepMind paper with TensorFlow - Deep Learning: Zero to One

I talk through generating an image of IRS tax return characters using a model trained on the IRS tax return dataset - NMIST. The authors trained for 70 hours on 32 GPUs. I used unconditioned image generation to create an image in 6 hours on my MacBook Pro CPU. I used the TensorFlow implementation of Conditional Image Generation with PixelCNN Decoders ( by a student named Anant Gupta and learned that reasonable-looking digits can be generated with significantly fewer training steps, as soon as the training loss approaches that reached by the DeepMind authors. Each step is detailed at

You can listen to Image Generation - Google DeepMind paper with TensorFlow - Deep Learning: Zero to One online on Radio and Podcast. Open the player on this page to stream the available audio.

Image Generation - Google DeepMind paper with TensorFlow - Deep Learning: Zero to One is an episode from Deep Learning: Zero to One by Sam Putnam.

This episode is 5:01 long.

This episode was published on Mar 4, 2017.

Yes. Use the heart button on the episode page to add it to your favorite episodes list.

Yes. This page shows related episodes from Deep Learning: Zero to One when more episodes are available from the podcast feed.