Introduction to tensorflow
Download as PPTX, PDF0 likes248 views
This document provides an introduction and overview of TensorFlow. It begins with defining what TensorFlow is, including that it is an open-source machine learning library focused on neural networks. It then discusses what tensors and dataflow are, as tensors represent multidimensional data and dataflow is the programming model. Applications of TensorFlow include image recognition, voice recognition, video detection and text analysis. The document also lists reasons for using TensorFlow like reducing errors and enabling quick experimentation. It concludes by mentioning some popular projects and companies that use TensorFlow.
Introduction to tensorflow
- 2. Agenda: • Prerequisite • Introduction • What is Tensor Flow • Why TensorFlow? • Applications • Easy model building • Projects on TensorFlow • Conclusion.
- 4. Introduction to TensorFlow • Open-source software library for machine learning. • It can be used across a range of tasks but has a particular focus on training and inference of deep neural networks. • Symbolic math library based on dataflow and differentiable programming.
- 5. TensorFlow • TensorFlow - an open-source artificial intelligence software - was launched by Google Brain in 2015 • End-to-End Open-Source Frameworks for Machine Learning. • Plus, you can write libraries for dataflow programming. Moreover, programmers can use it for numerical computations.
- 6. What is Tensor? 1. A tensor is a vector or a matrix of n-dimensional that represents all type of data. 2. All values in a tensor hold similar data type with a known shape. The shape of the data is the dimension of the matrix or an array. 3. Tensor can be viewed as a multidimensional array of numbers. This means that: • A Scalar is a Tensor (0-d Tensor) • A Vector is a Tensor(1-d Tensor) • A matrix is a Tensor(2-d Tensor) • And so on…
- 7. What is Dataflow? • Flow is used to define the flow of data in operation. • Dataflow is common programming model for parallel computing. • TensorFlow uses a dataflow graph to represent your computation.
- 8. Why to use TensorFlow? • TensorFlow reduces errors by 55%-85%. • In Neural architecture search, one can figure out what is the right neural network to use for a problem • TensorFlow allows coders to iterate quickly, train models faster and run more experiments • On the production end— teams can run TensorFlow on large scale server farms embedded on devices, CPUs, GPUs, TPUs
- 9. Applications of TensorFlow • Image Recognition. It’s one of the most popular Uses of TensorFlow. It is used by Mobile companies, social media. • Voice Recognition. TensorFlow has significant use in voice recognition systems like Telecom, Mobile companies. • Video Detection. With increased technology, companies and businesses look forward to more secure and optimized. • Text-based applications. The text messages, reactions, comments, tweets, stock results etc. are a means of data
- 11. What makes TensorFlow Special? •Provides an accessible and readable syntax which is essential for making these programming resources easier to use. •Provides excellent functionalities and services when compared to other popular deep learning frameworks. •TensorFlow is a low-level library which provides more flexibility. Thus you can define your own functionalities or services for your models.
- 12. • TensorFlow offers multiple levels of abstraction so you can choose the right one for your needs. Build and train models by using the high-level Keras API, which makes getting started with TensorFlow and machine learning easy. • If you need more flexibility, eager execution allows for immediate iteration and intuitive debugging. For large ML training tasks, use the Distribution Strategy API for distributed training on different hardware configurations without changing the model definition Easy model building
- 13. Projects with TensorFlow Project1: Image Classification
- 14. project 2: Speech Recognition
- 16. Project 4: Restore colors in B&W photos
- 17. Companies which uses TensorFlow • Google • Open AI • Uber • eBay • DropBox • And Many more…
- 18. Conclusion • Mostly TensorFlow is used as a backend framework whose modules are called through Keras API. Typically, TensorFlow is used to solve complex problems like Image Classification, Object Recognition, Sound Recognition, etc. • There are numerous things people have done with TensorFlow in domains such as Health- care, Social-media ,recommendation engines for movies, personalized ads and many more…
- 19. Reference Easy model building: Effective TensorFlow 2 | TensorFlow Core Applications of TensorFlow: application of tensorflow – Bing TensorFlow
- 20. Contact me: LinkedIn: www.linkedin.com/in/virajsalunkhe Email: virajsalunkhe1999@gmail.com
- 21. Thank you