Find me on Github/Twitter/Kaggle @SamDeepLearning.
Find me on LinkedIn @SamPutnam.
This Podcast is supported by Enterprise Deep Learning | Cambridge/Boston | New York City | Hanover, NH | http://www.EnterpriseDeepLearning.com. Contact: Sam@EDeepLearning.com, 802-299-1240, P.O. Box 863, Hanover, NH, USA, 03755. We move deep learning to production.
I teach the worldwide Deploying Deep Learning Masterclass at http://www.DeepLearningConf.com in NYC regularly and am a Deep Learning Consultant serving Boston and New York City.
If you like Talking Machines, harvardnlp, CS231n, the Media Lab, CSAIL, karpathy.github.io, FAIR, Google Brain, Deeplearning4j, TensorFlow, Amazon Web Services, or Google Cloud Platform, you will like the podcast. Try it.
Tweet at @SamDeepLearning if you have questions & to correct me!
All content for Deep Learning: Zero to One is the property of Sam Putnam 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.
Find me on Github/Twitter/Kaggle @SamDeepLearning.
Find me on LinkedIn @SamPutnam.
This Podcast is supported by Enterprise Deep Learning | Cambridge/Boston | New York City | Hanover, NH | http://www.EnterpriseDeepLearning.com. Contact: Sam@EDeepLearning.com, 802-299-1240, P.O. Box 863, Hanover, NH, USA, 03755. We move deep learning to production.
I teach the worldwide Deploying Deep Learning Masterclass at http://www.DeepLearningConf.com in NYC regularly and am a Deep Learning Consultant serving Boston and New York City.
If you like Talking Machines, harvardnlp, CS231n, the Media Lab, CSAIL, karpathy.github.io, FAIR, Google Brain, Deeplearning4j, TensorFlow, Amazon Web Services, or Google Cloud Platform, you will like the podcast. Try it.
Tweet at @SamDeepLearning if you have questions & to correct me!
Image Generation - Google DeepMind paper with TensorFlow - Deep Learning: Zero to One
Deep Learning: Zero to One
5 minutes
8 years ago
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 (https://arxiv.org/abs/1606.05328) 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 https://medium.com/@SamPutnam/this-is-the-1st-deep-learning-zero-to-one-newsletter-this-one-is-called-image-generation-935bcaf0f37c
Deep Learning: Zero to One
Find me on Github/Twitter/Kaggle @SamDeepLearning.
Find me on LinkedIn @SamPutnam.
This Podcast is supported by Enterprise Deep Learning | Cambridge/Boston | New York City | Hanover, NH | http://www.EnterpriseDeepLearning.com. Contact: Sam@EDeepLearning.com, 802-299-1240, P.O. Box 863, Hanover, NH, USA, 03755. We move deep learning to production.
I teach the worldwide Deploying Deep Learning Masterclass at http://www.DeepLearningConf.com in NYC regularly and am a Deep Learning Consultant serving Boston and New York City.
If you like Talking Machines, harvardnlp, CS231n, the Media Lab, CSAIL, karpathy.github.io, FAIR, Google Brain, Deeplearning4j, TensorFlow, Amazon Web Services, or Google Cloud Platform, you will like the podcast. Try it.
Tweet at @SamDeepLearning if you have questions & to correct me!
