A curated list of awesome Torch tutorials, projects, libraries, and communities for deep learning.
Awesome Torch is a curated GitHub repository listing high-quality resources for the Torch deep learning framework. It aggregates tutorials, implemented research models (a "model zoo"), essential libraries, and community links to help developers and researchers quickly find tools and knowledge for building neural networks with Torch.
Machine learning researchers, deep learning practitioners, and students who use or are evaluating the Torch framework for projects in computer vision, NLP, reinforcement learning, or other AI domains.
It saves significant time by providing a single, organized, and community-vetted directory of Torch resources, eliminating the need to search scattered forums, papers, and repositories for reliable implementations and learning materials.
A curated list of awesome Torch tutorials, projects and communities
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
Collects high-quality tutorials from authoritative sources like CVPR and Oxford, covering topics from basic Torch usage to advanced techniques like reinforcement learning and neural style transfer.
Includes a wide range of implemented research models such as LSTMs, ResNets, and DCGANs, each with direct links to code and associated papers for easy reference and reproducibility.
Structures essential Torch libraries for model building (e.g., nn, dpnn), GPU acceleration (e.g., cutorch), and development tools (e.g., iTorch), streamlining setup and dependency management.
Provides direct links to official support channels like Google Groups and Gitter chat, facilitating quick access to discussions and assistance within the Torch ecosystem.
Most resources and models date from 2015-2016, making it less relevant for current deep learning practices as Torch has been largely superseded by PyTorch.
The README shows no recent updates, so it misses newer tools and frameworks, and may contain broken links or deprecated code.
Since Torch usage has declined, the resources are specific to an older ecosystem, limiting applicability for projects using more popular frameworks like PyTorch.