Movies, and engineering.

Menu Close

Another intro to numpy

Informative error messages are great.

Looks like beloved Gabriel José de la Concordia García Márquez would NOT be able to change his address on the

https://moversguide.usps.com/

Thank you USPS for the error message that doesn’t make any sense to people with Last names that are several distinct words.

{field: "lastName", message: "The Last Name field allows only letters and the following characters ( - )."}

SIMS – Semi-parametric Image Synthesis – really cool

Interesting work on image synthesis. Generated picture quality improved a lot compared to both pxi2pix and pix2pixHD.

I recommend taking a look at the youtube video:
https://www.youtube.com/watch?v=U4Q98lenGLQ&feature=youtu.be

Also, you can run Tensorflow implementation of the network:
https://github.com/xjqicuhk/SIMS

Example of how to visualize Gluon based network in MXNet using mx.viz API

Apache MXNet 1.1 on Windows 10 64 bit

Attempted to run MXNet 1.1 GPU version on Windows 10. It works well, but the process of installation has a few details that is helpful to know.
1. You can create Anaconda environment based on Python 3.6 and use environment’s pip to install GPU version of Apache MXNet on Windows – pip install mxnet-cu90 at the moment. I believe cu91 is in the works and soon will be available.
2. You still need to download and install CUDA 9.0 as well as CuDNN 7.1 (FOR WINDOWS 10, NOT WINDOWS 7 – very easy to mistake them!) from the nVidia website. If CUDA itself is available for the download without an account – to get CuDNN library you need to have a free account on the nVidia page.
3. You still need to install latest graphics card drivers on the system, even after you installed all the CUDA stuff. For me MXNet was breaking on initialization of GPU context until I’ve rolled GPU drivers.

A few helpful links:
Cuda 9.0 download – https://developer.nvidia.com/cuda-90-download-archive
CuDNN download – https://developer.nvidia.com/cudnn ( I’ve tested 7.1 version and it works well)
nVidia GPU drivers – http://www.nvidia.com/Download/index.aspx

Nvidia’s work on pix2pix network

Amazing work on the introduction of high-definition to pix2pix architecture. Hypnotizing results, take a look for yourself – https://github.com/NVIDIA/pix2pixHD

Pix2pixHD is quite video memory hungry and runs best on cards with 24gig of VRAM :/

coin-git-stats

Hello, hello.

With the current boom in the concurrency and block-chain world, I’ve decided I want to learn more about the open source crypto projects, how popular they are and how often these projects are updated. After going to github and bitbucket and manually searching for projects I’ve came to a decision that I need to build a portal that would track all of the interest points for me automatically. And as it is a portal, it might be useful for you as well.
So in a few weekends and united work of 3 coders – https://www.coingitstats.com came to life.

The project is still in very early phase – but it does provide hourly updates and a very sleek UI – thanks to my wife:-)
We have a few items on the road-map, such as adding market capitalization, introducing machine learning based on the git and market data and a bit friendlier mobile experience.

Hopefully you enjoy the portal!

MXNet and Tensorboard

The notebook shows how to visualize accuracy and gradient of a MXNet network (gluon) via stand-alone Tensorboard.

MXNet is a machine learning framework.
https://mxnet.incubator.apache.org/

Tensorboard stand-alone that could run independently of Tensorflow.
https://github.com/dmlc/tensorboard

Read more

Image and video colorization using pre-trained pix2pix

This IPython notebook shows how to use pre-trained pix2pix generator to colorize black and white images. The network was trained as part of the experiments in https://github.com/skirdey/mxnet-pix2pix

Read more

Example of using mx.io.ImageRecordIter

© 2018 Movies, and engineering. . All rights reserved.

Theme by Anders Norén.