Download
This is the corresponding code for the book "The Deep Learning Framework PyTorch: Getting Started and Practical", but it can also be used as a standalone PyTorch Getting Started Guide and Tutorial. The current version of the code is based on pytorch 1.0.1, if you want to use an older version please git checkout v0.4or git checkout v0.3. Legacy code has better python2/python3 compatibility, CPU/GPU compatibility test. The new version of the code has not been fully tested, it has been tested under GPU and python3. But in theory there shouldn't be too many problems on python2 and CPU. The basic part (the first five chapters) explains the content of PyTorch. This part introduces the main modules in PyTorch and some tools commonly used in deep learning. For this part of the content, Jupyter Notebook is used as a teaching tool here, and readers can modify and run with notebooks and repeat experiments.
Features
- Install PyTorch and configure the learning environment
- Multi-dimensional array Tensor and dynamic graph autograd/Variable in PyTorch
- Basic usage of the neural network module nn in PyTorch
- Implement several cool and interesting applications
- The text description in the Notebook belongs to the first draft of this book
- The code is mainly tested under python3 to get the final result
Project Samples
