Movies, and engineering.

Menu Close

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

Python, MXNet and pix2pix image translation.

I’ve been doing some self-study around machine learning and deep learning, and once upon a time stumbled on a unsupervised image to image translation network called pix2pix .

Very interesting network architecture. I’ve looked at it from the perspective of image colorization. It seems like a great option and it trains quite quickly. Although I haven’t had a large enough training set to gather any specific metrics, it feels like it would generalize well on range of images.

There are several implementations of pix2pix available in the frameworks like Tensorflow, Caffe, and Scala/MXNet.

My version of pix2pix here is in Python and MXNet, aiming to colorize 256×256 images using GPU and CUDA.

https://github.com/skirdey/mxnet-pix2pix

Installing or upgrading to MXNet version 0.12.1 on Windows 10

This post is a continuation and somewhat a revision of  “Installing MXNet on Windows 10”

MXNet is evolving and recently there was a release of version 0.12

I want to share the upgrade process that worked for me on my Windows 10 machine. You can use this tutorial as installation tutorial of MXNet 0.12

First, we will need to create a folder somewhere called mxnet-0.12, I’ve placed mine on the D drive, so I have

After we have a folder for the installation, lets go to https://github.com/yajiedesign/mxnet/releases and download two packages:

  1. VC14 – vc14 v2 base package
  2. GPU ( or CPU) pre-built package – at the moment of writing it was 20171127_mxnet_x64_vc14_gpu_cu80.7z

Unpack VC14 v2 first in the mxnet-0.12 folder and after that do the same with the GPU archive.

If you are using GPU version of MXNet, you will need to add CUDAlibraries to the folder called 3rd party.

You can register at NVIDIA web-site and get required cuDNN  library for free. You will need to use

CUDA 8 / cuDNN v5.1 Library for Windows 10

The file should be placed into:

Drive:\mxnet-0.12\3rdparty\cudnn\bin\

Now in the root of the mxnet-0.12 folder look for a file called setupenv.cmd and run it as Administrator.

This execution of the .cmd file should adjust the PATH, and add MXNET_HOME environment variable.

MXNET_HOME should just point to the location of the mxnet-0.12 folder.

When all above is done, activate either Python 3.6 or Python 2.7 64-bit environment of your choice – Anaconda, virtualenv or Python binary native to the operating system.

Usually you do that by issuing command source activate [environment name] In my case, it is just source activate mxnet which I’ve created earlier using Anaconda Python 3.6 64bit installation.

Once the environment is active, go to the MXNET_HOME\python and run

python setup.py install

It should upgrade or install your MXNet package. Enjoy!

One of the greatest comedies of all

Tucker and Dale vs Evil

I can see that a movie is promising just by spotting in the plot a group of students going out for an outdoors vacation. It is just the best type of plot. There are infinite amount of possibilities what could happen to a group of young, mostly intoxicated and extremely self confident people that hanging out in a forest.

For instance, our students could – hallucinate, get kidnapped, be tortured, ride ponies, try to find a way to Mordor, fight giant spiders, fight giant giants, get more intoxicated, lose confidence, and it just goes on and on.  No spoilers.

The cast is on spot.

Alan Tudyk and Tyler Labine are perfect as the main characters. Their work is organic, and they bring the whole concept of empathy on a different level. You will understand them, and you will feel their struggle and, the bias they experience will be the bias you experience. Especially if you ever lived in a village or a farm. 

The group of students were Great. Loud. Judgmental. They just make you side with them from the first scenes 🙂

The setting of the piece is quite a forest!

Actually, everything about this comedy is remarkable, especially an old house! The old house is one of the funniest old houses that I’ve seen. It has its own character, and its own jokes. It gets grumpy sometimes.

The story is quite self-destructive, in a good way though.

Well, please, rent it and watch it. Highly recommended.

 

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

Theme by Anders Norén.