Effective ML
PyTorch
1. PyTorch basics
2. Encapsulate your model with Modules
3. Broadcasting the good and the ugly
4. Take advantage of the overloaded operators
5. Optimizing runtime with TorchScript
6. Building efficient custom data loaders
7. Numerical stability in PyTorch
8. Faster training with mixed precision
TensorFlow 1.0
01. TensorFlow basics
02. Understanding static and dynamic shapes
03. Scopes and when to use them
04. Broadcasting the good and the ugly
05. Feeding data to TensorFlow
06. Take advantage of the overloaded operators
07. Understanding order of execution and control dependencies
08. Control flow operations: conditionals and loops
09. Prototyping kernels and advanced visualization with Python ops
10. Multi-GPU processing with data parallelism
11. Debugging TensorFlow models
12. Numerical stability in TensorFlow
13. Building a neural network training framework with learn API
14. TensorFlow Cookbook
TensorFlow 2.0
01. TensorFlow basics
02. Broadcasting the good and the ugly
03. Take advantage of the overloaded operators
04. Control flow operations: conditionals and loops
05. Prototyping kernels and advanced visualization with Python ops
06. Numerical stability in TensorFlow
TensorFlow.js
01. TensorFlow.js basics
02. Using pretrained models
03. Tiling and broadcasting
About
Effective Machine Learning
Learn to use machine learning tools in practice efficiently.
Keep me updated
Subscribed
Table of Contents
1. PyTorch basics
2. Encapsulate your model with Modules
3. Broadcasting the good and the ugly
4. Take advantage of the overloaded operators
5. Optimizing runtime with TorchScript
6. Building efficient custom data loaders
7. Numerical stability in PyTorch
8. Faster training with mixed precision
Table of Contents
01. TensorFlow basics
02. Understanding static and dynamic shapes
03. Scopes and when to use them
04. Broadcasting the good and the ugly
05. Feeding data to TensorFlow
06. Take advantage of the overloaded operators
07. Understanding order of execution and control dependencies
08. Control flow operations: conditionals and loops
09. Prototyping kernels and advanced visualization with Python ops
10. Multi-GPU processing with data parallelism
11. Debugging TensorFlow models
12. Numerical stability in TensorFlow
13. Building a neural network training framework with learn API
14. TensorFlow Cookbook
Table of Contents
01. TensorFlow basics
02. Broadcasting the good and the ugly
03. Take advantage of the overloaded operators
04. Control flow operations: conditionals and loops
05. Prototyping kernels and advanced visualization with Python ops
06. Numerical stability in TensorFlow
Table of Contents
01. TensorFlow.js basics
02. Using pretrained models
03. Tiling and broadcasting