Training: Implement Training APIs¶
The training APIs is the interface between Determined and the user’s application framework (e.g., Keras, TensorFlow), in terms of loading training data, describing a model architecture, and specifying the underlying iterative optimization training algorithms.
The interface is called the Trial API. With the Trial API, developers expose the components of their model and training to Determined’s training loop implementation.
To read more about the Trial API, see:
See the full list of documents.
- Python API determined
- Python API determined.estimator
- Python API determined.keras
- Python API determined.pytorch
- Python API determined.pytorch.lightning
- Python API determined.pytorch.samplers
- Python API determined.TrialContext
- Best Practices for Model Definitions
- Experiment Configuration
- Save Checkpoints
- Training Units
- Trial API