cuTAGI is an open-source library that implements TAGI on CUDA platform. It supports various neural network architectures such as full-connected, convolutional, and transpose convolutional layers, as well as skip connections, pooling and normalization layers. cuTAGI is capable of performing different tasks such as supervised learning, unsupervised learning, and reinforcement learning. This library has a python API called pyTAGI that allows users to easily use the library.
- Fast: cuTAGI is written in C++ and uses CUDA to accelerate the training process.
- Easy to use: cuTAGI has a python API that allows users to easily use the library.
- Modules: pyTAGI has a set of moduels that allows users to easily make their own models.
- Examples: pyTAGI has a bunch of examples that users can use as a starting point.
To get started with using our library, check out our:
- installation guide for linux and macos.
- quick tutorial for a 1D toy problem to get a starting point.
Check out our API reference for a complete list of all the functions and classes in our library.
pyTAGI already includes a set of modules that allow users to easily make their own models. Check out our modules reference for a list of classes and functions.
In this section, you will find a series of examples for each available architecture that you can use as a starting point. Check out our examples for a list of examples.
We welcome contributions from the community. Please read our contributing guide for more information.
If you run into any issues or have any questions, please open an issue or contact us at luongha.nguyen@gmail.com or james.goulet@polymtl.ca.
cuTAGI is licensed under the MIT License.