1. What is TensorFlow?
TensorFlow is an open-source machine learning framework developed by Google. It allows developers to build and train machine learning models using data flow graphs, which represent computations as directed graphs.
2. What is a data flow graph in TensorFlow?
A data flow graph in TensorFlow is a graphical representation of a machine learning model. It consists of a set of nodes, which represent mathematical operations, and edges, which represent the data that flows between the nodes.
3. What is a tensor in TensorFlow?
A tensor in TensorFlow is a multi-dimensional array that represents a mathematical object. It can be a scalar, vector, matrix, or higher-dimensional array. Tensors are the basic building blocks of machine learning models in TensorFlow.
4. What is a session in TensorFlow?
A session in TensorFlow is an environment for executing computational graphs. It allows developers to run a graph, evaluate nodes, and update variables in the graph.
5. What is a variable in TensorFlow?
A variable in TensorFlow is a tensor that holds a value that can be updated during training. It is typically used to store the weights and biases of a machine learning model.
6. What is a placeholder in TensorFlow?
A placeholder in TensorFlow is a way to pass data to a computational graph. It allows developers to define the input and output shapes of a graph without specifying the actual data.
7. What is a feed_dict in TensorFlow?
A feed_dict in TensorFlow is a dictionary that maps placeholders to actual data. It is used to feed data into a computational graph during runtime.
8. What is a loss function in TensorFlow?
A loss function in TensorFlow is a mathematical function that measures how well a machine learning model is performing. It is typically used to optimize the weights and biases of the model during training.
9. What is backpropagation in TensorFlow?
Backpropagation is a method for calculating the gradients of a loss function with respect to the weights and biases of a machine learning model. It is used to update the weights and biases during training.
10. What is a checkpoint in TensorFlow?
A checkpoint in TensorFlow is a saved version of a machine learning model. It allows developers to resume training from a specific point, or to use the model for inference without retraining it. Checkpoints are typically saved to disk during training.
11. What are placeholder tensors?
Placeholder tensors are entities that provide an advantage over a regular variable. It is used to assign data at a later point in time.
Placeholders can be used to build graphs without any prior data being present. This means that they do not require any sort of initialization for usage.
12. What are managers in TensorFlow?
TensorFlow managers are entities that are responsible for handling the following activities for servable objects:
- Lifetime management
13. Where is TensorFlow mostly used?
TensorFlow is used in all of the domains that cover Machine Learning and Deep Learning. Being the most essential tool, the following are some of the main use cases of TensorFlow:
- Time series analysis
- Image recognition
- Voice recognition
- Video upscaling
- Test-based applications
14. What are TensorFlow services?
Servables in TensorFlow are simply the objects that client machines use to perform computations. The size of these objects is flexible. Servables can include a variety of information like any entity from a lookup table to a tuple needed for inference models.
15. How does the Python API work with TensorFlow?
Python is the primary language when it comes to working with TensorFlow. TensorFlow provides an ample number of functionalities when used with the API, such as:
- Automatic checkpoints
- Automatic logging
- Simple training distribution
- Queue-runner design methods
16. What are some of the APIs outside of the TensorFlow project?
Following are some of the APIs developed by Machine Learning enthusiasts across the globe:
- TFLearn: A popular Python package
- TensorLayer: For layering architecture support
- Pretty Tensor: Google’s project providing a chaining interface
- Sonnet: Provides a modular approach to programming
17. What are TensorFlow loaders?
Loaders are used in TensorFlow to load, unload, and work with servable objects. The loaders are primarily used to add algorithms and data into TensorFlow for working.
The load() function is used to pre-load a model from a saved entity easily.
18. What makes TensorFlow advantageous over other libraries?
Following are some of the benefits of TensorFlow over other libraries:
- Pipelines: data is used to build efficient pipelines for text and image processing.
- Debugging: tfdbg is used to track the state and structure of objects for easy debugging.
- Visualization: TensorBoard provides an elegant user interface for users to visualize graphs.
- Scalability: It can scale Deep Learning applications and their associated infrastructure easily.
19. What are TensorFlow abstractions?
TensorFlow contains certain libraries used for abstraction such as Keras and TF-Slim. They are used to provide high-level access to data and model life cycles for programmers using TensorFlow. This can help them easily maintain clean code and also reduce the length of the code exponentially.
20. What is a graph explorer in TensorFlow?
A graph explorer is used to visualize a graph on TensorBoard. It is also used for the inspection operations of a model in TensorFlow. To easily understand the flow of a graph, it is recommended to use a graph visualizer in TensorBoard.
21. What exactly do you know about Recall and Precision?
The other name for Recall is the true positive rate. It is the overall figure of positiveness a model can generally claim. The predictive value which is generally positive in nature is Precision.
The difference between the true positive rate and claimed positive rate can be defined with the help of both these options.
22. Name some products built using TensorFlow?
TensorFlow built the following products:
- Teachable Machine
- Giorgio Camthat
23. What are some advantages of TensorFlow over other libraries?
Debugging facility, scalability, visualization of data, pipelining, and many more.
24. How can you make sure that an overfitting situation is not arriving with a model you are using?
Users need to make sure that their model is simple and does not have any complex statements. Variance takes into account and the noise eliminates from the model data. Techniques like K-fold and LASSO can also help.
25. What exactly do you know about a ROC curve and its working?
ROC or region of convergence is used to reflect data rates that classify as true positive and false positive. Represented in the form of graphs, it can use as proximity to swap operations related to different algorithms.