tlt.models.model.BaseModel

class tlt.models.model.BaseModel(model_name: str, framework: FrameworkType, use_case: UseCaseType)

Abstract base class for a pretrained model that can be used for transfer learning

__init__(model_name: str, framework: FrameworkType, use_case: UseCaseType)

Class constructor

Methods

__init__(model_name, framework, use_case)	Class constructor
benchmark(dataset[, saved_model_dir, ...])	Use Intel Neural Compressor to benchmark the model with the dataset argument.
evaluate(dataset)	Evaluate the model using the specified dataset.
export(output_dir)	Export the serialized model to an output directory
load_from_directory(model_dir)	Load a model from a directory
optimize_graph(output_dir[, overwrite_model])	Performs FP32 graph optimization using the Intel Neural Compressor on the model and writes the inference-optimized model to the output_dir.
quantize(output_dir, dataset[, config, ...])	Performs post training quantization using the Intel Neural Compressor on the model using the dataset.
train(dataset, output_dir[, epochs, ...])	Train the model using the specified dataset

Attributes

framework	Framework with which the model is compatible
learning_rate	Learning rate for the model
model_name	Name of the model
preprocessor	Preprocessor for the model
use_case	Use case (or category) to which the model belongs