Getting started with TensorFlow
0 likes152 views
This document introduces TensorFlow, an open-source library for machine learning. It outlines the basic workflow of training a model using labeled data, including epochs and model adjustment. Additionally, it provides practical steps for applying TensorFlow to real-world problems.
1 of 22
Download to read offline
More Related Content
Similar to Getting started with TensorFlow (20)
Ad
Recently uploaded (20)
Ad
Getting started with TensorFlow
- 1. Getting started with TensorFlow Gustavo García @anarchyco
- 2. Machine Learning is everywhere
- 4. TensorFlow is an open source library for numerical computation, specializing in machine learning applications
- 6. Machine Learning Pseudocode labeled_data = ... // f.e. X: square_meters -> y: house_prices model = ... // f.e. y = B * x + A // Training do N times: // epochs for d in labeled_data: // usually in batches y_predicted = model.predict(d) model.adjust(y_predicted - y, learning_rate) // Inference model.predict(unseen_data)
- 8. Deep Neural Network with TensorFlow
- 9. Deep Neural Network with TensorFlow
- 10. Deep Neural Network with TensorFlow
- 11. Deep Neural Network with TensorFlow
- 12. Deep Neural Network with TensorFlow
- 13. Deep Neural Network with TensorFlow
- 19. Real world TensorFlow 1. Find a model to the type of problem you want to solve 2. Obtain as much good data as possible 3. Train the model (or retrain) 4. Save the model and deploy it
- 21. Demo
- 22. The End