Francesco Cardinale

I'm happy to announce that we just open-sourced a major update for our image super-resolution project: using an adversarial network and convolutional feature maps for the loss, we got some interesting results in terms realism and noise cancellation.
Pre-trained weights and GANs training code are available on GitHub!
If you want to read up about the process, check out the blog post.
Also, we released a pip package, 'ISR' (admittedly not the most creative name:D), with a nice documentation and colab notebooks to play around and experiment yourself on FREE GPU(#mindblown). Thanks to Dat Tran for the big help.

💻Blog: https://lnkd.in/dUnvXQZ
📝Documentation: https://lnkd.in/dAuu2Dk
🔤Github: https://lnkd.in/dmtV2ht
📕Colab (prediction): https://lnkd.in/dThVb_p
📘Colab (training): https://lnkd.in/diPTgWj

https://lnkd.in/dVBaKv4

#opensource #deeplearning #gans #machinelearning #keras

✴️ @AI_Python_EN

TensorFlow is dead, long live TensorFlow!

#TensorFlow just went full #Keras! (!!!!!) Here's why that's an earthquake for #AI and #DataScience...

🌎 TensorFlow

✴️ @AI_Python_EN

The best way to learn #DeepLearning is by practicing it. But which framework to use? Here are 5 articles to get you started!

A Comprehensive Introduction to #PyTorch - https://bit.ly/2L8Rj7n

Learn How to Build Quick & Accurate Neural Networks using PyTorch (& 4 Case Studies) - https://bit.ly/2Vts9nY

Get Started with Deep Learning using #Keras and #TensorFlow in #R - https://bit.ly/2Iro2BY

TensorFlow 101: Understanding Tensors and Graphs - https://bit.ly/2GNg195

An Introduction to Implementing #NeuralNetworks using TensorFlow - https://bit.ly/2V17cBs

✴️ @AI_Python_EN

A #Keras usage pattern that allows for maximum flexibility when defining arbitrary losses and metrics (that don't match the usual signature) is the "endpoint layer" pattern. It works like this: https://colab.research.google.com/drive/1zzLcJ2A2qofIvv94YJ3axRknlA6cBSIw
In short, you use add_loss/add_metric inside an "endpoint layer" that also has access to model targets. The layer then returns the inference-time predictions. You compile without an external "loss" argument, and you fit with a dictionary of data that contains the targets.
Of course logistic regression is a basic case that doesn't actually need this advanced pattern. But endpoint layers will work every time, even when you have losses & metrics that don't match the usual fn(y_true, y_pred, sampl_weight) signature that is required in compile.

✴️ @AI_Python_EN

A Convolutional Neural Network Tutorial in Keras and Tensorflow 2

https://medium.com/@isakbosman/a-convolutional-neural-network-tutorial-in-keras-and-tensorflow-2-2bff79f477c0

#Keras #neuralnetwork #TensorFlow #ConvolutionalNeuralNetwork

✴️ @AI_Python_EN

This is a neat project for reusable text generation with #Keras:

https://github.com/minimaxir/textgenrnn

✴️ @AI_Python_EN

François Chollet

This is how you implement a network in Chainer. Chainer, the original eager-first #deeplearning framework, has had this API since launch, in mid-2015. When PyTorch got started, it followed the Chainer template (in fact, the prototype of PyTorch was literally a fork of Chainer).

Nearly every day, I am getting ignorant messages saying, "PyTorch is an original innovation that TensorFlow/Keras copied". This is incorrect. Subclassing is a fairly obvious way to do things in Python, and Chainer had this API first. Many others followed.

I had been looking at adding a Model subclassing API to Keras as soon as late 2015 (before the Functional API even existed, and over a year before being aware of PyTorch), inspired by Chainer. Our first discussions about adding an eager execution mode also predate PyTorch.

By the time #PyTorch came out, I had been looking at its API (which is exactly the Chainer API) for 1.5 year (since the release of Chainer). It wasn't exactly a shock. There was nothing we didn't already know.



To be clear, it's a good thing that API patterns and technical innovations are cross-pollinating among deep learning framework. The #Keras API itself has a had a pretty big influence over libraries that came after. It's completely fine, and it all benefits end users.

✴️ @AI_Python_EN

Keras notebooks


Material used for Deep Learning related workshops for Machine Learning Tokyo (MLT)

ConvNets: colab notebook with functions for constructing #keras models. Models:

AlexNet
VGG
Inception
MobileNet
ShuffleNet
ResNet
DenseNet
Xception
Unet
SqueezeNet
YOLO
RefineNet

https://github.com/Machine-Learning-Tokyo/DL-workshop-series

✴️ @AI_Python_EN

than standard Adam? - I ran 24 experiments to find out. - The answer? Meh, not really. Full tutorial w/ #Python code here:
http://pyimg.co/asash

#DeepLearning #Keras #MachineLearning #ArtificialIntelligence #AI #DataScience

❇️ @AI_Python_en

.

just published my (free) 81-page guide on learning #ComputerVision, #DeepLearning, and #OpenCV!
Includes step-by-step instructions on:
- Getting Started
- Face Applications
- Object Detection
- OCR
- Embedded/IOT
- and more!
Check it out here:
http://pyimg.co/getstarted
And if you liked it, please do give it a share to spread the word. Thank you!
#Python #Keras #MachineLearning #ArtificialIntelligence #AI

❇️ @AI_Python_EN

New tutorial! Traffic Sign Classification with #Keras and #TensorFlow 2.0

- 95% accurate
- Includes pre-trained model
- Full tutorial w/ #Python code

http://pyimg.co/5wzc5

#DeepLearning #MachineLearning #ArtificialIntelligence #DataScience #AI #computervision

❇️ @AI_Python_EN

Functional #RL with #Keras and #Tensorflow Eager

https://bit.ly/2IIyzIj

❇️ @AI_Python_EN