xfer.SvmRepurposer¶

class xfer.SvmRepurposer(source_model: mxnet.module.module.Module, feature_layer_names, context_function=<function cpu>, num_devices=1, c=1.0, kernel='linear', gamma='auto', enable_probability_estimates=False)¶

Bases: xfer.meta_model_repurposer.MetaModelRepurposer

Perform Transfer Learning through a Support Vector Machine (SVM) meta-model which repurposes the source neural network.

Parameters:

source_model (mxnet.mod.Module) – Source neural network to do transfer learning from.
feature_layer_names (list[str]) – Name of layer(s) in source_model from which features should be transferred.
context_function (function(int)->:class:mx.context.Context) – MXNet context function that provides device type context.
num_devices (int) – Number of devices to use to extract features from source_model.
c (float) – Penalty parameter C of the error term.
kernel (string) – Specifies the kernel type to be used in the SVM algorithm in sklearn library. It must be one of ‘linear’, ‘poly’, ‘rbf’, ‘sigmoid’, ‘precomputed’ or a callable.
gamma (float) – Kernel coefficient for ‘rbf’, ‘poly’ and ‘sigmoid’. If gamma is ‘auto’ then 1/n_features will be used instead.
enable_probability_estimates (bool) – Whether to enable probability estimates. This must be enabled for predict_probability to work and will slow down training.

Methods

`__init__`	Initialize self.
`deserialize`	Uses dictionary to set attributes of repurposer.
`get_features_from_source_model`	Extract feature outputs from feature_layer_names in source_model, merge and return all features and labels.
`get_params`	Get parameters of repurposer that are in the constructor.
`predict_label`	Predict class labels on test data using the target_model (repurposed meta-model).
`predict_probability`	Predict class probabilities on test data using the target_model (repurposed meta-model).
`repurpose`	Train a meta-model using features extracted from training data through the source neural network.
`save_repurposer`	Serialize the repurposed model (source_model, target_model and supporting info) and save it to given file_path.
`serialize`	Saves repurposer (excluding source model) to file_prefix.json.

Attributes

`feature_layer_names`	Names of the layers to extract features from.
`source_model`	Model to extract features from.

get_params()¶

Get parameters of repurposer that are in the constructor.

Return type:	dict

serialize(file_prefix)¶

Saves repurposer (excluding source model) to file_prefix.json.

Parameters:	file_prefix (str) – Prefix to save file with.

deserialize(input_dict)¶

Uses dictionary to set attributes of repurposer.

Parameters:	input_dict (dict) – Dictionary containing values for attributes to be set to.

feature_layer_names¶: Names of the layers to extract features from.

get_features_from_source_model(data_iterator: mxnet.io.io.DataIter)¶

Extract feature outputs from feature_layer_names in source_model, merge and return all features and labels.

In addition, return mapping of feature_layer_name to indices in feature array.

Parameters:	data_iterator (`mxnet.io.DataIter`) – Iterator for data to be passed through the source network and extract features.
Returns:	features, feature_indices_per_layer and labels.
Return type:	`MetaModelData`

predict_label(test_iterator: mxnet.io.io.DataIter)¶

Predict class labels on test data using the target_model (repurposed meta-model).

Parameters:	test_iterator (mxnet.io.DataIter) – Test data iterator to return predictions for.
Returns:	Predicted labels.
Return type:	`numpy.ndarray`

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

Predict class probabilities on test data using the target_model (repurposed meta-model).

Parameters:	test_iterator (mxnet.io.DataIter) – Test data iterator to return predictions for.
Returns:	Predicted probabilities.
Return type:	`numpy.ndarray`

repurpose(train_iterator: mxnet.io.io.DataIter)¶

Train a meta-model using features extracted from training data through the source neural network.

Set self.target_model to the trained meta-model.

Parameters:	train_iterator – Training data iterator to use to extract features from source_model.

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)

source_model¶: Model to extract features from.