Gluon¶
Getting started¶
Six 10-minute tutorials covering the core concepts of MXNet using the Gluon API.
An introduction to defining and training neural networks with Gluon.
An end to end tutorial on working with the MXNet Gluon API.
A guide to implementing custom layers for beginners.
Implementing logistic regression using the Gluon API.
Saving and loading trained models.
Using pre-trained models with Apache MXNet.
Data¶
A guide to data augmentation.
Boost your training dataset with image augmentation.
A guide to loading data using the Gluon API.
A guide to the NDArray data structure.
Training¶
How to use Layers and Blocks.
Understand usage of normalization layers (such as BatchNorm).
Understand usage of activation layers (such as ReLU).
How to use loss functions for predicting outputs.
How to use the init function.
How to manage parameters.
How to use the fit API
How to use the Learning Rate Finder to find a good learning rate.
How to schedule Learning Rate change over time.
How to update neural network parameters using an optimization method.
How to use Automatic Differentiation with the Autograd API.
Advanced Topics¶
Best practices for the naming of things.
A guide to implementing custom layers.
Building custom operators with numpy.
A guide to implementing custom losses.
Common misconceptions when using NumPy in Apache MXNet.
Speed up training with hybrid networks.
How to schedule Learning Rate change over time (advanced)
Applications Topics¶
How to create deep learning models for images.
How to create deep learning models for text.