Quick Contact

    Python Tutorial
    Python Panda Tutorial
    Python Selenium
    Python Flask Tutorial
    Python Django
    Interview Questions & Answers


    • Give light to the structure and capabilities of tensorflow library. Tensorflow is open source library developed by Google brain team. It is versatile library, which is created to perform tasks which require complex numerical computations. For this reason Tensorflow was geared towards the problem of machine learning and deep neural network.

    • Due to C, C++ backend, tensorflow is able to run faster than pure python code.
    • Tensorflow application uses structure known as data flow graph.
    • Tensorflow offers several advantages for an application. It provides both python and C++ API. But the python is more complete and easy to use.

    • It also has great compilation times in comparison to alternative deep learning libraries.
    • It supports CPU, GPU and even distributed processing in a cluster.
    • Tensorflow structure is based on execution of data flow graph.


      • Data flow graph has two basic units.
        • Node represents mathematical operation, and an edge represents a multi-dimensional array, known as tensors. So this high level abstraction reveals how the data flows between operations.

      • Standard usage is to build a graph and then execute after the session is created, by using ‘run’ and ‘eval’ operations.
      • Since this would be difficult for interactive environments like IPython etc. notebooks, So there is an option to create interactive sessions that run on demand.

        • Once the graph is built, an inner loop is written to drive computation-:
    • Inputs are fed into nodes through variables or placeholders. You can take example of working of graph in above diagram.
    • In tensorflow graph run the computations only after the session is created.


    In tensorflow, graph will only run computations after the creation of session. Tensorflow flexible architecture allows deploying computation on one or more CPUs, GPUs, in desktop, server or any mobile device as-:

    • All of this can be done while only using single API.
    • It comes with convenient interaction with python interface to build and execute your computational graphs.
    • It is easy to learn and use machine learning using Data Scientist workbench, or DSWB. You don’t need any special hardware.
    • You can scale up and develop models faster with different implementations.


    • Tensorflow built-in support for deep learning and neural networks, so it’s easy to assemble assign parameters and run the training process.
    • It has also a collection of simple, trainable mathematical functions that are useful for neural networks and any gradient-based machine learning algorithm will benefit from Tensor Flow’s auto-differentiation and suite of first-rate optimizers.
    • Due to large collection of flexible tools, tensorflow is compatible with many variants of machine learning.


      • Neural network is machine learning model. Data comes to an input layer and flows across to an output layer.
      • Hidden layers in between are responsible for running calculations.
      • Simple neural network you see in above diagram below is known as Multi-layer perceptron.
      • By increasing the number of hidden layers, you move from shallow neural network to a deep neural network.
    • Deep neural networks are capable of significantly more complex behavior than their shallow counterparts.


    Each node or neuron processes input using an activation function. There are many different functions like the binary step, the hyperbolic tangent and the logistic function.

    The choice of activation function has a big impact on the network’s behavior. Tensorflow provides a lot of flexibility because it gives control over the network’s structure and function used for processing.

      • But tensorflow can be used for more than just neural networks. It can also be used to take set of points and apply a linear regression.
    • In its most basic form, this is essential a ‘line of best fit’ and if a line isn’t suitable for your data, you can use Tensorflow to build non-linear models as well.
    • If you need to build a model to perform classification with tensorflow, you can easily implement logistic regression.


    Apply now for Advanced Python Training Course

    Copyright 1999- Ducat Creative, All rights reserved.

    Anda bisa mendapatkan server slot online resmi dan terpercaya tentu saja di sini. Sebagai salah satu provider yang menyediakan banyak pilihan permainan.