GraphEmbedder

class flash.graph.embedding.model.GraphEmbedder(backbone, pooling_fn='mean')

The GraphEmbedder is a Task for obtaining feature vectors (embeddings) from graphs. For more details, see Graph Embedder.

Parameters

• backbone (Module) – A model to use to extract image features.

• pooling_fn (Union[str, Callable, None]) – The global pooling operation to use (one of: “max”, “max”, “add” or a callable).

classmethod available_finetuning_strategies(cls)

Returns a list containing the keys of the available Finetuning Strategies.

Return type

List[str]

classmethod available_lr_schedulers(cls)

Returns a list containing the keys of the available LR schedulers.

Return type

List[str]

classmethod available_optimizers(cls)

Returns a list containing the keys of the available Optimizers.

Return type

List[str]

classmethod available_outputs(cls)

Returns the list of available outputs (that can be used during prediction or serving) for this Task.

Examples

..testsetup:

>>> from flash import Task

>>> print(Task.available_outputs())
['preds', 'raw']

Return type

List[str]