Remember Style transfer with Convolutional Nerual Network, lllyasviel has developed a software for automatically coloring the sketches base on an exampler image. The software is based on convolution neural network.

Mitchell Orsucci has proposed method to control an FPGA from the Linux OS, where you are dynamically reconfigure the FPGA from Linux user-space. You can read more here

In this post, I will introduce several deep learning package which can be delpoyed to mobile platforms.

Franchise is a lightweight but powerful SQL tool with a notebook interface. You can use it online at franchise.cloud. You can query SQL as easy as Jupyter notebook, which is very popular for Python.

Java 9 has been release. Let’s check the most important updates:

wordcloud

XDA has made a comparison of speed, thermal and performance for a list of fast charge standards. You can access the full content here

I have created a list of phone which I am interested to buy.

Amulya Aankul has written a nice tutorial on how to run a jupyer notebook on Google Cloud Plaform and connect it locally.

A new open-source tool named GUINNESS makes it easy for you to develop binarized (2-valued) neural networks (BNNs) for Zynq SoCs and Zynq UltraScale+ MPSoCs using the SDSoC Development Environment. GUINNESS is a GUI-based tool that uses the Chainer deep-learning framework to train a binarized CNN. In a paper titled On-Chip Memory Based Binarized Convolutional Deep Neural Network Applying Batch Normalization Free Technique on an FPGA presented at the recent 2017 IEEE International Parallel and Distributed Processing Symposium Workshops, authors Haruyoshi Yonekawa and Hiroki Nakahara describe a system they developed to implement a binarized CNN for the VGG-16 benchmark on the Xilinx ZCU102 Eval Kit, which is based on a Zynq UltraScale+ ZU9EG MPSoC. Nakahara presented the GUINNESS tool again this week at FPL2017 in Ghent, Belgium.</p>