Table Of Contents
Table Of Contents

Gluon

Getting started

A 60-minute Gluon crash course../../crash-course/index.html

Six 10-minute tutorials covering the core concepts of MXNet using the Gluon API.

Gluon - Neural network building blockshttps://mxnet.incubator.apache.org/versions/master/tutorials/gluon/gluon.html

An introduction to defining and training neural networks with Gluon.

Gluon: from experiment to deploymenthttps://mxnet.incubator.apache.org/versions/master/tutorials/gluon/gluon_from_experiment_to_deployment.html

An end to end tutorial on working with the MXNet Gluon API.

Custom Layers for Beginnershttps://mxnet.incubator.apache.org/versions/master/tutorials/gluon/custom_layer.html

A guide to implementing custom layers for beginners.

Logistic regression using Gluon API explainedhttps://mxnet.incubator.apache.org/versions/master/tutorials/gluon/logistic_regression_explained.html

Implementing logistic regression using the Gluon API.

Saving and Loading Gluon Modelshttps://mxnet.incubator.apache.org/versions/master/tutorials/gluon/save_load_params.html

Saving and loading trained models.

Using pre-trained models in MXNethttps://mxnet.incubator.apache.org/versions/master/tutorials/gluon/pretrained_models.html

Using pre-trained models with Apache MXNet.

Data

Data Loadingdata.html

How to load data for training.

Image Augmentationimage-augmentation.html

Boost your training dataset with image augmentation.

Data Augmentationhttps://mxnet.incubator.apache.org/versions/master/tutorials/gluon/data_augmentation.html

A guide to data augmentation.

Gluon Datasets and DataLoaderhttps://mxnet.incubator.apache.org/versions/master/tutorials/gluon/datasets.html

A guide to loading data using the Gluon API.

NDArray - Scientific computing on CPU and GPUhttps://mxnet.incubator.apache.org/versions/master/tutorials/gluon/ndarray.html

A guide to the NDArray data structure.

Training

Neural Networksnn.html

How to use Layers and Blocks.

Normalization Blocksnormalization/normalization.html

Understand usage of normalization layers (such as BatchNorm).

Activation Blocksactivations/activations.html

Understand usage of activation layers (such as ReLU).

Loss Functionsloss.html

How to use loss functions for predicting outputs.

Initializing Parametersinit.html

How to use the init function.

Parameter Managementparameters.html

How to manage parameters.

Learning Rate Finderhttps://mxnet.incubator.apache.org/versions/master/tutorials/gluon/learning_rate_finder.html

How to use the Learning Rate Finder to find a good learning rate.

Learning Rate Scheduleshttps://mxnet.incubator.apache.org/versions/master/tutorials/gluon/learning_rate_schedules.html

How to schedule Learning Rate change over time.

Trainertrainer.html

How to update neural network parameters using an optimization method.

Autograd API../autograd/autograd.html

How to use Automatic Differentiation with the Autograd API.

Advanced Topics

Namingnaming.html

Best practices for the naming of things.

Custom Layerscustom-layer.html

A guide to implementing custom layers.

Custom Operatorshttps://mxnet.incubator.apache.org/versions/master/tutorials/gluon/customop.html

Building custom operators with numpy.

Custom Losscustom-loss/custom-loss.html

A guide to implementing custom losses.

Gotchas using NumPy in Apache MXNethttps://mxnet.incubator.apache.org/versions/master/tutorials/gluon/gotchas_numpy_in_mxnet.html

Common misconceptions when using NumPy in Apache MXNet.

Hybrid- Faster training and easy deploymenthttps://mxnet.incubator.apache.org/versions/master/tutorials/gluon/hybrid.html

Combines declarative and imperative programming using HybridBlock.

Hybridizehybridize.html

Speed up training with hybrid networks.

Advanced Learning Rate Scheduleshttps://mxnet.incubator.apache.org/versions/master/tutorials/gluon/learning_rate_schedules_advanced.html

Advanced exploration of Learning Rate shapes.

Applications Topics

Image Tutorialsimage/index.html

How to create deep learning models for images.

Text Tutorialstext/index.html

How to create deep learning models for text.