xfer.Repurposer¶

class xfer.Repurposer(source_model: mxnet.module.module.Module, context_function=<function cpu>, num_devices=1)¶

Base Class for repurposers that train models using Transfer Learning (source_model -> target_model).

Parameters:	source_model (`mxnet.mod.Module`) – Source neural network to do transfer learning from. context_function (function(int)->:class:mx.context.Context) – MXNet context function that provides device type context. num_devices (int) – Number of devices to use with context_function.

Methods

`__init__`	Initialize self.
`deserialize`	Abstract method.
`get_params`	Get parameters of repurposer that are in the constructor’s argument list.
`predict_label`	Abstract method.
`predict_probability`	Abstract method.
`repurpose`	Abstract method.
`save_repurposer`	Serialize the repurposed model (source_model, target_model and supporting info) and save it to given file_path.
`serialize`	Abstract method.

predict_probability(test_iterator: mxnet.io.io.DataIter)¶: Abstract method.

get_params()¶

Get parameters of repurposer that are in the constructor’s argument list.

Return type:	dict

save_repurposer(model_name, model_directory='', save_source_model=None)¶

Serialize the repurposed model (source_model, target_model and supporting info) and save it to given file_path.

Parameters:	model_name (str) – Name to save repurposer to. model_directory (str) – File directory to save repurposer in. save_source_model (boolean) – Flag to choose whether to save repurposer source model. Will use default if set to None. (MetaModelRepurposer default: True, NeuralNetworkRepurposer default: False)