Deep Learning Zero to One: 5 Awe-Inspiring Demos with Code for Beginners, part 2
Deep Learning Zero to One: 5 Awe-Inspiring Demos with Code for Beginners, part 2Here are deep learning examples and demos you can just download and run, including Spotify Artist Search using Speech APIs, Symbolic AI Speech Recognition, and Algorithmia API Photo Colorizer.
By Sam Putnam, Enterprise Deep Learning.
(Editor: this is the second installment of the demos - here is the first part)
Someone in a meetup said they wanted deep learning examples that they can just download and run. No Math. No Theory. No Books.
It's difficult to find deep learning examples that are open source and that also run first try without stepping through dependency hell, so try this:
Below are 5 more models I have downloaded and started running on my MacBook Pro or AWS in under 10 minutes. All ran several days to several months ago - just download and go. They finish in between 5s (pre-trained neural networks) and several hours (GPU-intensive neural network training) time. But you've got 5 seconds, right?
Please email me Sam@EnterpriseDeepLearning.com if the following doesn't work for you!
Model:
Demo:
Model:
Demo:
Model:
Demo:
Setting up on an EC2 GPU Step-by-step (start at p.17):
Model:
Demo:
Model:
Demo:
Source: YouTube
In the theme of learning by doing - I highly recommend Josh Gordon's Google Developers Deep Learning videos too:
Thank you to the model creators: Algorithmia, Clarifai, Anant Gupta, Abhishek Kumar, Yen-Chen Lin, Sash Zats, Marc Brown, Stephen Anthony, Manuel Ruder, and Shantanu Johri.
Github List:
Tutorials for demos available here: https://ai-month.teachable.com/p/the-terrible-deep-learning-list-part-1-tutorials
Bio: Sam Putnam is CEO/Founder, and a Deep Learning Consultant, at Enterprise Deep Learning, LLC. He directs machine learning projects, solves clients' business problems, and trains deep neural networks on large datasets. Sam is also a contributor to the TensorFlow machine learning project and a member of the Machine Learning Society.
Original. Reposted with permission.
(Editor: this is the second installment of the demos - here is the first part)
Someone in a meetup said they wanted deep learning examples that they can just download and run. No Math. No Theory. No Books.
It's difficult to find deep learning examples that are open source and that also run first try without stepping through dependency hell, so try this:
Below are 5 more models I have downloaded and started running on my MacBook Pro or AWS in under 10 minutes. All ran several days to several months ago - just download and go. They finish in between 5s (pre-trained neural networks) and several hours (GPU-intensive neural network training) time. But you've got 5 seconds, right?
Please email me Sam@EnterpriseDeepLearning.com if the following doesn't work for you!
1. Spotify Artist Search using Speech APIs on iOS
Model:
Demo:
2. Symbolic AI Speech Recognition with iOS 10 Speech APIs
Model:
Demo:
3. Video Style Transfer using Torch 7
Model:
Demo:
Van Gogh image+Butterfly video=Stylized butterfly video, ~1 min/frame to compute optical flow w/ DeepFlow+DeepMatching, Torch7 to train net. pic.twitter.com/sDic1NMi0K— Sam Putnam (@samdeeplearning) April 18, 2017
Setting up on an EC2 GPU Step-by-step (start at p.17):
Deep Learning and Artistic Style Transfer for Videos - Enterprise Deep Learning from Sam Putnam [Deep Learning]
4. Algorithmia API Photo Colorizer
Model:
Demo:
top rated colorful image colorization https://t.co/CIt4864jCB deep learning algo's 1.8millionth API call brightens my auto-gen'd NMIST digs pic.twitter.com/Jx3qpC7n1D— Sam Putnam (@samdeeplearning) February 21, 2017
5. Clarifai Information Retrieval for Videos on Android
Model:
Demo:
Source: YouTube
In the theme of learning by doing - I highly recommend Josh Gordon's Google Developers Deep Learning videos too:
Thank you to the model creators: Algorithmia, Clarifai, Anant Gupta, Abhishek Kumar, Yen-Chen Lin, Sash Zats, Marc Brown, Stephen Anthony, Manuel Ruder, and Shantanu Johri.
Github List:
Tutorials for demos available here: https://ai-month.teachable.com/p/the-terrible-deep-learning-list-part-1-tutorials
Bio: Sam Putnam is CEO/Founder, and a Deep Learning Consultant, at Enterprise Deep Learning, LLC. He directs machine learning projects, solves clients' business problems, and trains deep neural networks on large datasets. Sam is also a contributor to the TensorFlow machine learning project and a member of the Machine Learning Society.
Original. Reposted with permission.