The order of the byte appears is called the endianness in computer technology. This term stem from processor architecture design, for example, x86 and the classic 6502 is little endian, while S/360 and SPARC are big endian. ARM processors like the one powering the Beagleboard SBC I am happy with from Yubikey to the R statistics package can be configured to run either.
At the end of the day, programs are compiled and linked to instruction sets for the hardware processor to execute. But that is not the end of the story for software developers. Apart from the hardware instruction sets there are also endianness in file. Any developers having involved in any form of low level file processing, in classic or modern programming languages alike, should be very familiar with this.
Take the bitcoin file as en example, the hex dump below is the genesis bitcoin with the timestamp field highlighted in yellow.
On file it reads 29AB5F49, but for the sake of endianness, this value should be interpreted as 495FAB29 in hexadecimal, and the corresponding decimal value is 1231006505. Converting this decimal value timestamp into human readable date:
It is quite trivial to convert from one to another through programming languages and a classic C example as simple as the below macro will do the job.
Theano needs no introduction in the field of deep learning. It is based on Python and supports CUDA. Keras is a libray that wraps the complexity of Theano to provide a high level abstraction for developing deep learning solutions.
Installing Theano and Keras are easy and there are tons of resources available online. However, my primary CUDA platform is on Windows so most standard guides that are based on Linux required some adaptations. Most notably are the proper setting of the PATH variable and the use of the Visual Studio command prompt.
The basic installation steps include setting up of CUDA, a scientific python environment, and then Theano and Keras. CuDNN is optional and required Compute Capability of greater than 3.0 which unfortunately my GPU is a bit old and does not meet this requirement.
Some programs on Windows platform encountered errors and found to be library related issues. Like this one that failed to compile on Spyder can be resolved using the Visual Studio Cross Tool Command Prompt.
The Nvidia profiler checking for the performance of the GPU, running the Keras example of the MNIST digits with MLP.