TensorFlow Interview Questions and Answers

TensorFlow Interview Questions and Answers

Last updated on 04th Jul 2020BlogInterview Questions

Ratings 8

These Tensorflow Interview Questions have been designed specially to get you acquainted with the nature of questions you may encounter during your interview for the subject of Tensorflow . As per my experience good interviewers hardly plan to ask any particular question during your interview, normally questions start with some basic concept of the subject and later they continue based on further discussion and what you answer.we are going to cover top 100 Tensorflow  Interview questions along with their detailed answers. We will be covering Tensorflow  scenario based interview questions, Tensorflow  interview questions for freshers as well as Tensorflow  interview questions and answers for experienced. 

1. What is Tensorflow?

Ans:

TensorFlow is a machine learning library created by the Brain Team of Google and made open source in 2015. Basically, Tensorflow is a low-level toolkit for doing complicated math and it offers the users customizability to build experimental learning architectures, to work with them and to turn them into running software.

2. What does the latest release of TensorFlow have to offer?

Ans:

The latest release of TensorFlow is 1.7.0 and is available on www.tensorflow.org. It has been designed with deep learning in mind but applicable to a much wider range of problems.

3. What are Tensors?

Ans:

Tensors are higher dimensional arrays which are used in computer programming to represent a multitude of data in the form of numbers. There are other n-d array libraries available on the internet like Numpy but TensorFlow stands apart from them as it offers methods to create tensor functions and automatically compute derivatives.

4. What is a TensorBoard?

Ans:

TensorBoard, a suit of visualizing tools, is an easy solution to Tensorflow offered by the creators that lets you visualize the graphs, plot quantitative metrics about the graph with additional data like images to pass through it.

5. What are the features of TensorFlow?

Ans:

Tensorflow has APIs for Matlab, and C++ and has a wide language support. With each day passing by, researchers working on making it more better and recently in the latest Tensorflow Summit, tensorflow.js, a javascript library for training and deploying machine learning models has been introduced.

6. List a few advantages of TensorFlow?

Ans:

  • It has platform flexibility
  • It is easily trainable on CPU as well as GPU for distributed computing.
  • TensorFlow has auto differentiation capabilities
  • It has advanced support for threads, asynchronous computation, and queue es.
  • It is a customizable and open source.

7. List a few limitations of Tensorflow.

Ans:

  • Has GPU memory conflicts with Theano if imported in the same scope.
  • No support for OpenCL
  • quires prior knowledge of advanced calculus and linear algebra along with a pretty good understanding of machine learning.

8. What are TensorFlow servables?

Ans:

  • These are the central rudimentary units in TensorFlow Serving.  Objects that clients use to perform the computation are called Servables.
  • The size of a servable is flexible. A single servable might include anything from a lookup table to a single model to a tuple of inference models. 

9. What do the TensorFlow managers do?

Ans:

Tensorflow Managers handle the full lifecycle of Servables, including:

  • Loading Servables
  • Serving Servables
  • Unloading Servables

10. What are TensorFlow loaders?

Ans:

Tensorflow Loaders are used for adding algorithms and data backends one of which is tensorflow itself. For example, a loader can be implemented to load, access and unload a new type of servable machine learning model.

11. What is deep speech?

Ans:

Deep Speech developed by Mozilla is a TesnsorFlow implementation motivated by Baidu’s Deep Speech architecture.

12.What do you mean by sources in TensorFlow?

Ans:

Sources are in simple terms, modules that find and provide servables. Each Source provides zero or more servable streams. One Loader is supplied for each servable version it makes available to be loaded.

13. How does TensorFlow make use of the python API?

Ans:

Python is the most recognisable and “the main” language when it comes to TensorFlow and its development. The first language supported by TensorFlow and still supports most of the features. It seems as TensorFlow’s functionality first define in Python and then moved to C++.

14. How many types of Tensors are there?

Ans:

There are three types of Tensors used to create neural network models:

  • Constant Tensor
    Constant Tensors are used as constants, as the name suggests. They create a node that takes a value and does not change it. A constant can be created using tf.constant.
    tf.constant(value, dtype=None, shape=None, name=’Const’, verify_shape=False)
    It accepts the five arguments.
  • Variable Tensor
    Variable Tensors are the nodes which provide their current value as output. It means that they can retain their value over multiple executions of a graph.
  • Place Holder Tensor
    Placeholders Tensors are essential than variables. These are used to assign data in a later time. Placeholders are the nodes whose value is fed at the time of execution. Assume, we have inputs to our network which are dependent on some external data. Also, we do not want our graph to depend on any real value while developing the graph, then Placeholders are useful datatype. We can even build a graph without any data.
    Therefore, placeholders do not require any initial value. They only need a datatype (such as float32) and a tensor shape, so the graph still knows what to compute with even though it does not have any stored values.

15. Which client languages are supported in TensorFlow?

Ans:

TensorFlow provides support for multiple client languages, one of the best among them is Python. There are some experimental interfaces which are available for C++, Java, and Go. A language bindings for many other languages such as C#, Julia, Ruby, and Scala are created and supported by the open-source community.

16. What are the three working components of TensorFlow Architecture?

Ans:

TensorFlow architecture works in three parts:

  • Preprocessing the data
  • Building the model
  • Training and estimating the model

17. Explain few options to load data into TensorFlow.

Ans:

  • Loading the data into TensorFlow is the first step before training a machine learning algorithm. There are two ways to load the data:
  • Load data in memory
    It is the easiest method. All the data is loaded into memory as a single array. One can write a Python code which is unrelated to TensorFlow.
  • Tensorflow data pipelineTensorFlow has built-in APIs which help to load the data, perform the operations, and feed the machine learning algorithm easily. This method is mostly used when there is a large dataset.

18. Describe the common steps to most TensorFlow algorithms?

Ans:

  • Import data, generate data, or setting a data-pipeline through placeholders.
  • Feed the data through the computational graph.
  • Evaluate output on the loss function.
  • Use backpropagation to modify the variables.
  • Repeat until stopping condition.

19. Mention the name of some methods to deal with the overfitting in TensorFlow.

Ans:

  • Dropout Technique
  • Regularization
  • Batch Normalization

20.What is the difference between CNN and RNN?

Ans:

  • The following table shows the differences between CNN and RNN:
Convolutional Neural Networks (CNN)Recurrent Neural Networks (RNN)
Best suited for spatial data like images.Best suited for sequential data.
CNN is powerful when compared to RNN.RNN supports less featureset than CNN.
This network takes fixed type of  inputs and outputs.
These are ideal for video and image processing.These are ideal for text and speech analysis.

21. Where can you run a TensorFlow?

Ans:

TensorFlow can run on different platforms:

  • Operating System such as Windows, OS, and Linux
  • Cloud Web Service
  • Mobile OS like IOS and Android

22. When will you find overfit condition of a model in TensorFlow?

Ans:

There are variations in the training data, and this data needs to be verified through TensorFlow. Overfitting can be probably seen if the variations are huge in the data. The best possible solution is to remove the noise from the available data upto the possible extent.

23.What is pruning in a decision tree?

Ans:

Pruning refers to minimizing the overall complexity of the model to increase the accuracy. This process is strictly managed as the model may completely become useless.

24. List some products that are built using TensorFlow.

Ans:

There are a few products built using TensorFlow:

  • Nsynth
  • Giorgio Cam
  • Hand Writing Recognition
  • Teachable Machine

25.What is a Recurrent Neural Network(RNN)?

Ans:

RNN is a category of Artificial Neural Network where the connections among the nodes form a directed graph throughout the temporal sequence.

26. What are the benefits of TensorFlow over other libraries? Explain.

Ans:

There are many benefits of TensorFlow over other libraries which are given below:

  • Scalability
    TensorFlow provides easily scaled machine learning applications and infrastructure.
  • Visualization of Data
    Visualizing the graph is very straight-forward in TensorFlow. TensorBoard(a suite of visualization tools) is used to visualize TensorFlow graphs.
  • Debugging Facility
    is a specialized debugger for TensorFlow. It lets us view the internal structure and states of running TensorFlow graphs during training and inference.
  • Pipelining
    TensorFlow’s Dataset module tf.data is used to build efficient pipelines for images and text.

27. What do you understand by Deep Speech?

Ans:

  • DeepSpeech is an open-source engine used to convert Speech into Text. It uses a model which is trained by machine learning techniques. It is based on Baidu’s Deep Speech research paper. It uses Google’s TensorFlow to make the implementation easier.
  • We can list the command line options through deep Speech, and the syntax for that is given below:
  • ./deepspeech.py  

28. What do you know about TensorFlow abstractions?

Ans:

  • TensorFlow contains abstraction libraries such as TF-Slim and kereas, which provides simplified high-level access to TensorFlow. Such abstractions help to streamline the construction of data flow graphs.
  • TensorFlow abstractions not only help to make the code cleaner but also reduce the length of codes drastically. As a result, it significantly reduces development time.

29. What are the APIs used outside the TensorFlow project?

Ans:

There are a few APIs used outside the TensorFlow project, which are:

  • TFLearn
    TFLearn provides a high-level API which makes neural network building and training fast and easy. This API is fully compatible with Tensorflow. Its API can be indicated as tf.contrib.learn.
  • TensorLayer
    TensorLayer is a TensorFlow-based deep learning and reinforcement learning library. It is designed for researchers and engineers. It provides an extensive collection of customizable neural layers/functions which are crucial for building real-world AI applications.
  • PrettyTensor
    Pretty Tensor delivers high-level builder API for TensorFlow. It offers thin wrappers on Tensors so that you can easily build multi-layer neural networks.
    Pretty Tensor provides a set of objects that behave likes Tensors. It also supports a chainable object syntax to define neural networks and other layered architectures in TensorFlow quickly.
  • Sonnet
    Sonnet is a library which is built on top of TensorFlow for creating complex neural networks. It is a part of Google’s DeepMind project, which features a modular approach.

30. How do we create tensors from Python objects?

Ans:

We can create tensors such as numpy arrays and lists with the help of Python objects. We can easily perform it using tf.convert_to_tensor() operation.

31.How you place operations on a particular device?

Ans:

You should create the operations within a with tf.device(name): context to place them on a particular device.

32.What is the simplest way to send data to TensorBoard?

Ans:

First of all, you should add summary operations to your graph, and then log them in a log directory. Then, TensorBoard  should be started using:

  • python tensorflow/tensorboard/tensorboard.py –logdir=path/to/log-directory

33.What exactly do you know about Bias-Variance decomposition?

Ans:

It generally uses to decompose problems such as errors that occur during learning in different algorithms. Bias keeps reducing if the data is to be made complex. Trading off the Variance and Bias are very essential to get results that are totally free from errors.

34.How is k-means clustering different from KNN?

Ans:

It is an unsupervised learning algorithm used for clustering. On the other hand, the KNN is a structured clustering algorithm. They both share some similarities but users need to label the data in the KNN which is not required in k-means clustering.

35.What exactly Neural Networks are? What are the types of same you are familiar with?

Ans:

  • Basically a connection of processing elements which can very large or very small depending on the application, it deployed for. These elements called neurons and generally, two types of networks can be seen in this category. They are Artificial Neural Networks and Biological Neural Networks.
  • The use of artificial neural networks is more common and generally, they are considered for creating machines which are equally powerful to human brains.

36.What are placeholders in TensorFlow?

Ans:

It is an assurity to the tensorflow that an external value will be provided later.

37.What is tf.contrib.learn?

Ans:

tf.contrib.learn is a TensorFlow library for simplifying the working of machine learning, and it includes:

  • managing data sets
  • managing feeding

38.What is input pipeline optimization?

Ans:

The process flow of your model includes the loading of the image from the disk, converting it to a tensor followed by manipulating the tensor by cropping, padding and then making a batch. The process flow described above is called input pipeline.

39.What is the MNIST dataset?

Ans:

It is a dataset containing information of handwritten digits.

40.What are the different dashboards in TensorFlow?

Ans:

Below mentioned are different types of dashboards in TensorFlow:

  • Histogram
  • Text
  • Distribution
  • Image
  • Audio
  • Graph
  • Embedding.

41.How do you import Tensorflow?

Ans:

import TensorFlow as tf

42.What are word embeddings used for and can they be used in TensorFlow?

Ans:

Word embeddings usually use in Natural Language Processing as a representation of words and they can use in TensorFlow where it also call as word2vec.

43.Do Sessions have a lifetime? What about intermediate tensors?

Ans:

Resources like as tf.Variable, tf.QueueBase, and tf.ReaderBase; own by a session and may use a significant amount of memory which are released when the session is terminated with tf.Session.close.

44.What’s the deal with feeding and placeholders?

Ans:

Feeding is a phenomenon that allows you to substitute different values for one or more Tensors at the runtime. The feed_dict argument is used to map tf.Tensorobjects to numpy arrays for further executions.

45.Why does Session.run() hang when using a reader or a queue?

Ans:

The tf.ReaderBase and tf.QueueBase classes provide special operations that become blocked since the input isn’t available. They allow building clear input pipelines, by making the computation a little more complicated.

46.What is the lifetime of a variable?

Ans:

A variable is created when you first run the tf.Variable.initializer operation for that variable in a session. It gets destroyed when that tf.Session.close.

47.How do variables behave when they are concurrently accessed?

Ans:

Variables allow concurrency in read/write ops. The variable value may change when the concurrently updates. By default, there is no mutex (mutual exclusion).

48.Name the two models used in word embeddings?

Ans:

The Continuous Bag of Words (CBOW) model and the skip-gram model

49.Write a code to start a simple session for the training?

Ans:

  • with tf.Session() as sess:

Explain the following example.

  • for the epoch in      range(training_epochs):
  •        for (x, y) in zip(train_X, train_Y):
  •            sess.run(optimizer, feed_dict={X: x, Y: y})
  • Here, the initializer is run and all the training data fit by running a loop for all the epochs

Here, the initializer is run and all the training data fit by running a loop for all the epochs

50.List the two configurations needed to optimize CPU performance?

Ans:

  • Intra_op_parallelism and iner_op_parallelism

51.How do you define a cluster in TensorFlow?

Ans:

  •  cluster = tf.train.ClusterSpec({“local”: [“localhost:2222”, “localhost:2223”]})

52.How do you see the charts and graphs for your model and what is the URL?

Ans:

You can view the charts and graphs using TensorBoard by browsing to https://localhost:6006 in your browser.

53.What is the confusion matrix?

Ans:

A confusing matrix comprising of discrete values where each column contains a set of samples that estimated to be a keyword in your training model.

54.Describe the steps to configure a wide and deep model in TensorFlow?

Ans:

  • Wide model features: Choosing the base columns and crossed columns.
  • Deep model features: Choosing the continuous columns, the dimension for each categorical column, and hidden layer sizes.
  • Combining these into a single model with DNNLinearCombinedClassifier

55.Write a code to display the evaluated values while training your model in TensorFlow.

Ans:

             print(‘Results at epoch’, (n + 1) * FLAGS.epochs_per_eval)

  • print(‘Results at epoch’, (n + 1) * FLAGS.epochs_per_eval)
  •   print(‘-‘ * 30)
  •  for key in sorted(results):

56.What are the imports needed for visualizing the Mandelbrot set in TensorFlow?

Ans:

  • import PIL.Image
  • from io import BytesIO
  • from IPython.display import Image, display

57.How do you report a vulnerability in TensorFlow?

Ans:

The reports about any security issues can send directly to security@tensorflow.org. The report to this email delivered to the security team at TensorFlow. The emails then acknowledged within 24 hours and detailed response is provided within a week along with the next steps.

58.What do you use for deploying a lite model file in TensorFlow?

Ans:

Java API: A wrapper around C++ API on Android.

C++ API: It loads the TensorFlow Lite model and calls the interpreter.

Interpreter: It can use to execute the model. It uses selective kernel loading which is a unique feature of TensorFlow Lite.

59. In TensorFlow, what exactly Bias and Variance are? Do you find any similarity of difference between them?

Ans:

  • In the learning algorithms, Bias are generally considered as errors that declare their presence due to overly assumptions. These can sometimes result in failure of entire model and can largely affect the accuracy also in several cases. Some experts believe these errors are essential to enable leaner’s gain knowledge from a training point of view.
  • On the other side, Variance is another problem that comes when the learning algorithm is quite complex. Therefore a limit is to be imposed on this.

60. What exactly do you know about a ROC curve and its working?

Ans:

  • IT is basically used to reflect something very important regarding the rates which are classified as true positive rates and false positive rates.
  • It represents all the information in the form of graphs. Basically, it can be used as a proxy for the trade-off operations related to different algorithms. 

61. What are the general advantages of using the Artifical Neural Networks?

Ans:

  • They provide complete information on how to find solutions to complex problems in a  stepwise manner. All the information that a network receive can easily be represented in any format.
  • Artificial neural networks also make sure of real-time operations. In addition to this, they have excellent fault tolerance capability. 
  • Get ahead in your career by learning Tensorflow through Mindmajix TensorFlow Tutorial.

62. Compare general computers with artificial neural networks?

Ans:

  • The artificial neural network’s information source is examples that are common in general computers. It is very necessary to choose the examples carefully as they need to be given as input to the artificial neural network.
  • Predicting the artificial neural network outcome is not an easy job but it can be trusted for its accuracy. However, the outcomes of general computers are already well-defined and can easily be predicted.

63. What exactly do you know about Recall and Precision

Ans:

  • The other name of Recall is true positive rate. Actually, it is the overall figure of positiveness a model generally claim. Precision is generally regarded as the predictive value which is positive in nature.
  • The difference between the true positive rate an claimed positive rate can be defined with the help of both these options. 

64. In the machine learning context, how useful and reliable Bayes’ theorem is according to you?

Ans:

  • This theorem defines the probability of any event in machine learning. It represents a fixed value which is actually a mathematical calculation. This value is generally obtained by dividing the true positive rate divided by the false positive rate.
  • In machine learning, some of the very complex problems and challenges can easily be solved and eliminated with the help of this theorem. Most of the time results provided by it are highly accurate and can easily be trusted. 

65. What difference do you find in Type I and Type II errors?

Ans:

  • Type I error is a false positive value. On the other side, Type II error is a false negative value.
  • Type I error generally represent that something has happened when actually it doesn’t while Type II error is to representing the machine that nothing is wrong when actually something is not good. 

66. In TensorFlow, what exactly the discriminative and generative method?

Ans:

  • All the distinction among the different types of data can simply be learned with the help of discriminative method. On the other side, generative model is used for understanding a specific format of same.
  • The tasks that can also be handled with both these approaches need to be classified in a well-defined order first. 

67. What would be your strategy to handle a situation indicating an imbalanced dataset?

Ans:

  • This situation occurs when a majority of data that is under a specific use is kept in one class only. Resampling the dataset is the best possible solution for the users.
  • Migration of data to the parallel classes can also overcome the problem to a great extent. Users also need to make sure that a dataset is not damaged. 

68. What is the application of Naïve Bayes Naïve in machine learning?

Ans:

  • It is basically a sub-algorithm of a sub-module that defines the conditional probabilities of different components. The final results can be integrated with other possible outcomes to predict the final outcomes.
  • It can also overcome a lot of problems which are related to the unstructured data. 

69. How is it possible to evaluate a logistic regression model for a user?

Ans:

It is necessary for the users to fully understand the typical goals related to the concepts are. Some use cases are also to be considered for this approach. 

70. What do you know about supervised and unsupervised machine learning?

Ans:

  • One of the prime needs in the supervised learning is the labeled data which is not always necessary to be present in unsupervised learning.
  • Data labeling is important to enable the groups handle all the things in the right manner. On the other side, it is possible for the users to use data in unsupervised learning but labeling the same is not always necessary. 

71. Name the two common regularizations in a machine learning approach and explain the significance of them?

Ans:

These are L1 and L2 regularization. Both these have their own well-defined functions. L1 contains multiple variables that are in binary values. L2 regularization are meant for error handling and both of them largely depends on the Gaussian concept. 

72. In machine learning based on TensorFlow, what is more important you among the performance or the accuracy of a model?

Ans:

  • The answer to this question depends on your overall experience. Although both are important accuracy is more important in the majority of tasks.
  • It would be good for you to boost your knowledge on nuances of machine learning to have a better reply to this question if it is asked to you in an interview. 

73. What exactly F1 score is in machine learning? 

Ans:

  • It is basically a score that gives clear information regarding the overall performance of a model that is utilized for any task. The score generally varies between the two fixed values that are generally 0 and 1.
  • The latter is regarded as the best score while 0 represents the worst performance. 

74. Name the algorithm you are properly familiar with and explain everything you know about it in one minute?

Ans:

  • Such a question basically text your information representing skills for the tasks that are technical and complex.
  • Make sure you summarize the text properly and give the answer in a  defined format. You can go with any algorithm that you have studied or practiced properly.

75. What exactly do you know about Deep learning?

Ans:

  • It is basically related to neural networks and is generally considered as a subset of machine learning. When it comes to implementing some important principles that are related to the back propagation, this concept is applied.
  • It is an unsupervised learning algorithm that is used for data understanding and to use neural nets properly. 

76. On a time series dataset, what type of validation technique would you prefer?

Ans:

  • This dataset is not a randomly distributed data and thus the standard techniques such as k-folds cannot be applied. Therefore a pattern based technique would be useful here and this is because it makes sure that all the sub-tasks flow in a well-defined sequence.
  • There are no chances of any errors that can be considered as a chronological order that creates issues related to the functionality of the model.

77. In which situation the ensemble approach is useful?

Ans:

  • In a model, there is a need to use multiple learning algorithms. This situation needs ensemble approach. In addition to this, there can also be a need to combine an applied part of learning algorithms for the optimization or the predictive performance.
  • One of the primary aim to use this approach is to impose a limit on the overfitting. 

78. How can you make sure that overfitting situation is not arriving with a model you are using?

Ans:

  • Users need to make sure that their model is simple and is not having any complex statement. All the variance should be taken into the account and the noise should be eliminated from the model data.
  • Cross-validation technique like k-fold is another useful method that is helpful in this matter. LASSO technique is another possible solution to this issue. 

79. What exactly do you know about Kernel Trick?

Ans:

  • All the kernel functions are involved in this trick basically. These tricks are useful to perform some advanced calculations. It is possible for the users to express these functions in terms of products.
  • Also, different algorithms can be made run effectively. the good thing is this can be done even if the dimensional data is low. 

80. What if a file is corrupted or missing in a dataset?

Ans:

It is possible to replace them with other values that run parallel to them. Dropna and isnull are the two methods that are useful in this matter. In some special cases, it is even possible to replace them with desired values and have an error-free outcome. 

81. What differences will you find in an array and a linked list?

Ans:

Collection of objects in a well-defined order is generally considered as an array. On the other side, a linked list is also a set of objects but they are not always necessary to be well-defined or remain in a sequence. Also, they have a pointer which is missing in case of an array. 

82.Explain the Architecture of TensorFlow?

Ans:

TensorFlow Architecture works on three primary principles:

  • Pre-Process the data.
  • Build the model according to the data sets.
  • Trained and evaluate the model.

83. What are the pros and cons of TensorFlow?

Ans:

Pros of TensorFlow

  • We can easily use Keras as an interface for TensorFlow.
  • It is an Open Source.
  • It can be used as a general library.
  • We can easily find resources of TesnorFlow and nicely coded and documented with the help of TensorFlow.
  • When we compare to other libraries like Torch And Theano, the TensorFlow has excellent computational Graph Visualizations.
  • The TensorFlow has high performance, quick updates, and new release with new features.
  • It is scalable
  • TensorFlow supports various types of debugging methods.
  • You are visualizing the data and pipeline.

Cons of TensorFlow

  • There is a workaround by using finite unfolding(bucketing), TensorFlow does not support this feature, so we can say that it’s a disadvantage of TensorFlow. If it comes to variable length sequences are the symbolic loops, that’s why we can say that the TensoFlow has missing symbolic loops.
  • Not supported for windows, if you want to use TensorFlow, so you have to install anaconda first on windows after that you can use TensorFlow on that.
  • It lacks both speed and usage as compared to other libraries.
  • The Computation speed is also a disadvantage of TensorFlow.

84. What is the  possibility of evaluating a logistic regression model for a user?

Ans:

 Necessarily, the users need to completely understand typical goals connected to the concepts. Some use cases should be considered for this approach.

85.  Which unit gives non-linearity to a neural network?

Ans:

 Rectified Linear unit provides non-linearity to a neural network.

86. What is an important feature of model capacity?

Ans:

 Model capacity increases as number of hidden layers increase.

87. What are the APIs inside the TensorFlow project?

Ans:

The API’s inside TensorFlow are still Python-based and they have low-level options for its users such as tf.manual or tf.nnrelu which use to build neural network architecture. These APIs also use to aid designing deep neural network having higher levels of abstraction.

88. How does TensorFlow use the C++ API?.

Ans:

The runtime of TensorFlow is written in C++ and mostly C++ is connected to TensorFlow through header files in tensorflow/cc. C++ API still is in experimental stages of development but Google is committed to working with C++.

89. Can TensorFlow be deployed in container software?

Ans:

Tensorflow can also use with containerization tools such as docker, for instance, it could use to deploy a sentiment analysis model which uses character level ConvNet networks for text classification. 

90.What is the difference between Pytorch and Tensorflow?

Ans:

PytorchTensorFlow
1. The Pytorch is based on Torch.1.  The TensorFlow is based on Theano.
2. It is developed by Facebook.2. Google produces it.
3. Pytorch is more easy to understand.3.TensorFlow is not so easy to understand.
4. Pytorch includes computational graph at the runtime.4.TensorFlow does not have any option at run time.
5. Pytorch doesn’t have any feature like visualization.5.TensorFlow has  Tensor board for visualizing machine learning model.

91.Have you any idea about deep learning and machine learning?

Ans:

Deep learning

  • Deep learning is the subpart of machine learning. There are various types of deep learning architectures, such as deep neural networks, deep belief networks, recurrent neural network, and convolutional neural network.
  • Machine learning
  • The application of artificial intelligence is known as machine learning, and it is the scientific study of algorithms and statistical models. Machine learning is a subset of artificial intelligence.

92.Explain the role of Neural Network in TensorFlow?

Ans:

  • The neural networks are designed to recognize the patterns, and these are the set of algorithms. We can interpret the sensory data through a kind of machine learning perception, labeling, or raw clustering input with the help of the neural network.
  • When we develop those type of applications in which image recognition, speech recognition, and natural language processing are used, then we can use a neural network for this purpose in the TensorFlow.

93.What is Bias in TensorFlow?

Ans:

The Bias is a type of Variables in Neural Networks, and It is the core concept of an artificial neural network. The Artificial Neural Network is the use of Bias variables to improve functions with a y-intercept other than zero.

94.What is the difference between Bias and Variance?

Ans:

  • The main difference between Bias and Variance is that the Bias estimator’s expected value and actual value of the parameter being estimated, on the other hand, the variance estimator value does not depend on the parameter being determined.
  • Through variance estimator, we can measure how far amount can the estimate take, away from its expected value while the Bias estimator can alter accuracy.

95.Describe TensorFlow API in short?

Ans:

There are lot of features which are similar to python, and the TensorFlow is same as a python package. The central core functionality of TensorFlow is circulation at runtime and implemented in various languages, and the python is one of them. There is TensorFlow’s Circulated execution Engine, or the runtime engine exists in TensorFlow. It is a type of virtual machine, and there are various types of API’s which are given  below in the diagram:

  • C API for TensorFlow: When we want to create the TensorFlow then, we should use the C API for TensorFlow.
  • C++ API for TensorFlow: The C++ API supports mechanism for building and executing the data flow graph, it is simple to understand. This API is created to work with TensorFlow bazel build, and If you require a stand-alone option, you can use C API for that.
  • Python API for TensorFlow: Python API is famous for the TensorFlow, and it was one of the first language supported for TensorFlow. The python API is so diverse; that’s why you need to decide before the use of python API according to your work.
  • R API for TensorFlow: It is a different approach form other traditional approaches.
  • API’s Inside TensorFlow project: These types of API’s are python based, API’s inside TensorFlow always use to aid in designing a deep neural network, with a higher level of abstraction.
  • API’s Outside TensorFlow project: There is an API tf.contrib.learn which is a separate package of python. The TensorFlowLayer is also an external TensorFlow project API, and the pretty Tensor is a Google’s project which provides an interface with chaining. The sonnet is also a project of Google, which is known as DeepMind. It has the feature of the modular approach.

96.What are the use cases of tensorflow?

Ans:

Tensorflow is an important tool for deep learning, it has mainly 5 use cases, they are:

  • Text Based Applications
  • Voice/Sound Recognition
  • Time Series
  • Image Recognition
  • Video Detection

97. What is keras?

Ans:

  • Keras is an Application Programming Interface (API) designed for humans and not machines. It follows best ways to minimize cognitive load.
  • It is efficient in offering consistent and simple API’s, also reduces amount of user actions required for common use cases providing clear feedback.

98. What is a pooling layer?

Ans:

pooling layer is generally used in reducing the spatial dimensions and not depth, on a convolutional neural network model.

99.What is the difference between tf.variable and tf.placeholder?

Ans:

The tf.variable and tf.placeholder are almost similar to each other but, there are some differences:

tf.variabletf.placeholder
tf.variable defines variable values that are modified with period of time.tf.placeholder defines certain input data that does not change with period of time.
tf.variable requires an initial value at the time of definition.tf.placeholder does not require initial value at the time of definition.

100.What is necessary to evaluate any formulas in Tensorflow?

Ans:

  •  with tf.Session() as sess:

101.How do you sum the whole array into one number in tensorflow?

Ans:

  • tf.reduce_sum(array) or tf.reduce_sum(x, [0, 1])

102.What programming language is it for?

Ans:

The API is nominally for the Python programming language, although there is access to the underlying C++ API.

103.What do you understand by Tensor and Flow in case of Tensorflow?

Ans:

Tensor:

  • Multi dimensional array – e.g., scalar, vector, matrix, cube

Flow:

  • A graph that defines operations like + to do with data (tensors). 
  • A lot like numpy
  • Fast Math with tensors

104.What is nodes?

Ans:

Nodes perform computation and have zero or more inputs and outputs. Data that moves between nodes are known as tensors, which are multi-dimensional arrays of real values.

105.What is edges?

Ans:

The graph defines the flow of data, branching, looping and updates to state. Special edges can be used to synchronize behavior within the graph, for example waiting for computation on a number of inputs to complete.

106.What is the purpose of tf.Session?

Ans:

It provides a class for running Tensorflow objects. It encapsulates the environment in which Operation objects are executed and Tensor objects are evaluated.

usage:

  • with tf.Session as sess:
  • (context manager)
  • or
  • sess = tf.Session()
  • which then requires
  • sess.run(…)
  • sess.close()

107.What happens when you create a variable?

Ans:

You pass a tensor into the Variable() constructor. You must specify the shape of the tensor which becomes the shape of the variable. Variables generally have fixed shape.

108.When you will use tf.get_variable()?

Ans:

Sometimes you have large sets of variables in complex models that you want to all initialize in the same place.

ssass

Are you looking training with Right Jobs?

Contact Us
Get Training Quote for Free