NNabla's tutorials are provided as Jupyter Notebooks where you can run the code step-by-step.
On many Linux (probably on Windows), Jupyter can be easily installed using pip by:
pip install ipython<=5 # IPython>=6 is not supported in Python<=3.3.
pip install jupyter
You can run Jupyter server on your terminal on this folder.
jupyter notebook
Then, follow the instruction printed on your terminal to connect the server on your browser.
Open the .ipynb
files to start tutorials.
You can also run it directly on Colab from the links in the table below.
Name | Notebook | Doc |
---|---|---|
NNabla By Examples | read | |
NNabla Python API | read | |
Cifar-10 Training | Coming Soon | |
Model Finetuning | read | |
Debugging | read | |
Static vs. Dynamic Neural Network in NNabla | read | |
Image Generation with DCGAN | Coming Soon | |
Semi-Supervised Learning with VAT | Coming Soon | |
Unsupervised Learning with VAE | Coming Soon | |
Feature Embedding with SiameseNet | Coming Soon | |
Mixed Precision Training | read | |
Data Parallel Distributed Training | read | |
Graph Converter for Inference | read |