Skip to main content

Introduction to TensorFlow

Here you will get TensorFlow introduction.

TensorFlow is a framework which is used for machine learning and deep learning applications like neural network. It is used for data flow programming as an open source software library over various range of tasks. It is symbolic  math library used in research and production both.

Tensorflow is used for general purpose computing on graphics processing units that are able to run on multiple CPUs and GPUs unlike the reference implementation that runs on single devices. It is available on Linux, macOS, windows with 64-bit configuration and also on mobile computing platforms like Android and IOS. As the neural network performs operations on multidimensional data arrays that derives from tensorflow and these arrays are called tensors.

Introduction to TensorFlow

Image Source

Also Read: Introduction to Deep Learning

Also Read: Introduction to Neural Networks

Tensorflow has multiple application programmable interfaces. The lowest level application programmable interface is tensorflow core that provides complete programming control. Generally tensorflow core is used by machine learning researchers and those who require control of fine levels over their models. The higher level application programmable interface unit makes task in repetition with easy task and maintain consistent between different users.

The higher level APIs are easier to use than tensorflow core and built on top of tensor flow core.

Tensors

Tensor is the central unit of data in tensorflow and it comprises of primitive values set shaped as an array of multi-dimension. Tensorflow is a framework with generalized tensor of vectors and matrices of higher dimensions. Tensors are represented as an n-dimensional array with n as rank of tensor of base data types. In tensor flow programming, tf.tensor is the main object that can be manipulated and passed around. The tf.tensor is an object that will produce value by partial computation. Firstly tf.tensor graph is built that describes detailed description about each tensor.

Tf.tensor has a data type and a shape as its properties. The element of tensor has same known data type and partially known shape i.e. the dimension.

Interaction of GPUs on TensorFlow System

Tensorflow by default maps almost all the GPU memory visible to the process. This process is efficiently used by reducing memory fragmentation of precious GPU memory resources on the devices. Tensorflow gives two configurations on the session to control the growth of memory usage, it only allocate a subset of memory as is needed by the process.

The first configuration option is “allow_growth” which allows to allocate only GPU memory based on runtime allocations. In starting it allocates very less amount of memory and thereafter as per the requirement they extent the GPU memory needed by tensorflow process. However it does not release memory automatically and this scenario leads to memory fragmentation. To release memory automatically we have to turn on this option by setting the option in configProto by:-

config=tf.ConfigProto()
config.gpu_options.allow_growth=true
session=tf.Session(config=config,...)

The second configuration method is “per process GPU memory fraction option”, it determines the amount of memory that the particular GPU should allocate.

config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 0.4
session = tf.Session(config=config, ...)

Comment below if you have any queries related to above introduction to tensorflow.

The post Introduction to TensorFlow appeared first on The Crazy Programmer.



from The Crazy Programmer https://www.thecrazyprogrammer.com/2017/12/introduction-to-tensorflow.html
Labels:

Comments

Post a Comment

Popular posts from this blog

Rail Fence Cipher Program in C and C++[Encryption & Decryption]

Here you will get rail fence cipher program in C and C++ for encryption and decryption. It is a kind of transposition cipher which is also known as zigzag cipher. Below is an example. Here Key = 3. For encryption we write the message diagonally in zigzag form in a matrix having total rows = key and total columns = message length. Then read the matrix row wise horizontally to get encrypted message. Rail Fence Cipher Program in C #include<stdio.h> #include<string.h> void encryptMsg(char msg[], int key){ int msgLen = strlen(msg), i, j, k = -1, row = 0, col = 0; char railMatrix[key][msgLen]; for(i = 0; i < key; ++i) for(j = 0; j < msgLen; ++j) railMatrix[i][j] = '\n'; for(i = 0; i < msgLen; ++i){ railMatrix[row][col++] = msg[i]; if(row == 0 || row == key-1) k= k * (-1); row = row + k; } printf("\nEncrypted Message: "); for(i = 0; i < key; ++i) f...
3 comments
Read more

Data Encryption Standard (DES) Algorithm

Data Encryption Standard is a symmetric-key algorithm for the encrypting the data. It comes under block cipher algorithm which follows Feistel structure. Here is the block diagram of Data Encryption Standard. Fig1: DES Algorithm Block Diagram [Image Source: Cryptography and Network Security Principles and Practices 4 th Ed by William Stallings] Explanation for above diagram: Each character of plain text converted into binary format. Every time we take 64 bits from that and give as input to DES algorithm, then it processed through 16 rounds and then converted to cipher text. Initial Permutation: 64 bit plain text goes under initial permutation and then given to round 1. Since initial permutation step receiving 64 bits, it contains an 1×64 matrix which contains numbers from 1 to 64 but in shuffled order. After that, we arrange our original 64 bit text in the order mentioned in that matrix. [You can see the matrix in below code] After initial permutation, 64 bit text passed throug...
Post a Comment
Read more

Experimental: Reducing the size of .NET Core applications with Mono's Linker

The .NET team has built a linker to reduce the size of .NET Core applications. It is built on top of the excellent and battle-tested mono linker . The Xamarin tools also use this linker so it makes sense to try it out and perhaps use it everywhere! "In trivial cases, the linker can reduce the size of applications by 50%. The size wins may be more favorable or more moderate for larger applications. The linker removes code in your application and dependent libraries that are not reached by any code paths. It is effectively an application-specific dead code analysis ." - Using the .NET IL Linker I recently updated a 15 year old .NET 1.1 application to cross-platform .NET Core 2.0 so I thought I'd try this experimental linker on it and see the results. The linker is a tool one can use to only ship the minimal possible IL code and metadata that a set of programs might require to run as opposed to the full libraries. It is used by the various Xamarin products to extract...
Post a Comment
Read more