# Training Infrastructure -> Deep Learning Frameworks

Full-stack model-building and training frameworks that provide layers, optimizers, autograd, and high-level training APIs as integrated systems.

Choose a repository below only when its description, package/repository identity, task surface, and runtime intent match the request. If several candidates overlap, prefer the one whose root skill directly covers the requested workflow; then inspect its internal navigation rather than loading all candidates.

| Repo skill | Repository | Skill description |
| --- | --- | --- |
| [`axlearn`](../../../../repo-skills/axlearn/SKILL.md) | `apple/axlearn` | Routes AXLearn training, language-model, vision, audio/ASR, and GCP CLI workflows. |
| [`chainer`](../../../../repo-skills/chainer/SKILL.md) | `chainer/chainer` | Routes Chainer workflows for training, export, distributed learning, ChainerX, and checkout maintenance. |
| [`jittor`](../../../../repo-skills/jittor/SKILL.md) | `Jittor/jittor` | Guide Jittor package workflows for tensor programming, training, data/model I/O, custom ops, runtime validation, and troubleshooting. |
| [`ludwig`](../../../../repo-skills/ludwig/SKILL.md) | `ludwig-ai/ludwig` | Guides agents using Ludwig declarative machine learning configs, CLI commands, Python APIs, AutoML, HPO, serving, export, and deployment workflows. |
| [`deepxde`](../../../../repo-skills/deepxde/SKILL.md) | `lululxvi/deepxde` | Use DeepXDE for scientific machine learning, PINNs, DeepONet/operator learning, backend selection, training, and troubleshooting. |
| [`tensorlayer`](../../../../repo-skills/tensorlayer/SKILL.md) | `tensorlayer/TensorLayer` | Routes TensorLayer model-building, data utilities, vision, text, reinforcement learning, and training workflows. |
| [`tflearn`](../../../../repo-skills/tflearn/SKILL.md) | `tflearn/tflearn` | Use and troubleshoot TFLearn, a TensorFlow-v1-style high-level deep learning API for layers, data feeds, DNN training, checkpoints, and model recipes. |