MXNet tutorials can be found in this section. A variety of language bindings are available for MXNet (including Python, Scala, C++ and R) and we have a different tutorial section for each language.
Are you new to MXNet, and don’t have a preference on language? We currently recommend starting with Python, and specifically the Gluon APIs (versus Module APIs) as they’re more flexible and easier to debug.
Another great resource for learning MXNet is our examples section which includes a wide variety of models (from basic to state-of-the-art) for a wide variety of tasks including: object detection, style transfer, reinforcement learning, and many others.
We have two types of API available for Python: Gluon APIs and Module APIs. See here for a comparison.
A comprehensive introduction to Gluon can be found at The Straight Dope. Structured like a book, it build up from first principles of deep learning and take a theoretical walkthrough of progressively more complex models using the Gluon API. Also check out the 60-Minute Gluon Crash Course if you’re short on time or have used other deep learning frameworks before.
Use the tutorial selector below to filter to the relevant tutorials. You might see a download link in the top right corner of some tutorials. Use this to download a Jupyter Notebook version of the tutorial, and re-run and adjust the code as you wish.Select API:
- Gotchas using NumPy
- Multi-GPU training
- Checkpointing and Model Serialization (a.k.a. saving and loading) (Alternative)
- Distributed Training
- Inference using an ONNX model
- Fine-tuning an ONNX model on Gluon
- Visualizing Decisions of Convolutional Neural Networks
- Learning Rate Finder
- Learning Rate Schedules
- Advanced Learning Rate Schedules
- Profiling MXNet Models
- Hybridize Gluon models with control flows
- Gluon end to end from training to inference
- Linear Regression
- Linear Regression with Sparse Symbols
- MNIST Handwritten Digit Classification
- Movie Review Classification using Convolutional Networks
- Generative Adversarial Networks (GANs)
- Recommender Systems using Matrix Factorization
- Speech Recognition with Connectionist Temporal Classification Loss