Episode #2: DALL-E and friends in image generation

https://is1-ssl.mzstatic.com/image/thumb/Podcasts125/v4/ce/1f/54/ce1f5445-5b3b-7779-23c1-7afc0c08d0ae/mza_981984752925761863.jpg/600x600bb.jpg

Deep Learning Deep Dive

2 episodes

6 days ago

Long-form technical deep dives with Andrej Karpathy and Justin Johnson

All content for Deep Learning Deep Dive is the property of Deep Learning Deep Dive and is served directly from their servers with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.

Long-form technical deep dives with Andrej Karpathy and Justin Johnson

Technology

https://d3t3ozftmdmh3i.cloudfront.net/production/podcast_uploaded_nologo/13043328/13043328-1614147569939-b393781f22101.jpg

Episode #2: DALL-E and friends in image generation

Deep Learning Deep Dive

1 hour 51 minutes 27 seconds

4 years ago

Episode #2: DALL-E and friends in image generation

Andrej Karpathy and Justin Johnson deep dive into OpenAI's DALL-E and use it as an anchor point to recurse into some of the recent work in AI on image generation. Approximate agenda:

DALL-E Blog Post:
https://openai.com/blog/dall-e/

ImageGPT
https://openai.com/blog/image-gpt/

VQ-VAE
https://arxiv.org/abs/1711.00937

VQ-VAE-2
https://arxiv.org/abs/1906.00446

Gumbel-Softmax / Concrete Distribution
https://arxiv.org/abs/1611.01144
https://arxiv.org/abs/1611.00712

VQGAN
https://arxiv.org/abs/2012.09841

Andrej's attempted re-implementation of VQVAE and GumbelSoftmax:
https://github.com/karpathy/deep-vector-quantization/blob/main/model.py

You can see a video version of this episode on YouTube:
https://www.youtube.com/watch?v=gMc90bqHMSM

We reached out to all speakers and obtained their written consent to appear in this recording.