accelbrainbase.observabledata._mxnet.neuralnetworks package¶
Submodules¶
accelbrainbase.observabledata._mxnet.neuralnetworks.auto_encoder module¶
-
class
accelbrainbase.observabledata._mxnet.neuralnetworks.auto_encoder.
AutoEncoder
(encoder, decoder, computable_loss, initializer=None, learning_rate=1e-05, learning_attenuate_rate=1.0, attenuate_epoch=50, units_list=[100, 1], dropout_rate_list=[0.0, 0.5], optimizer_name='SGD', activation_list=['tanh', 'sigmoid'], ctx=gpu(0), hybridize_flag=True, regularizatable_data_list=[], scale=1.0, tied_weights_flag=False, **kwargs)¶ Bases:
accelbrainbase.observabledata._mxnet.neural_networks.NeuralNetworks
Auto-Encoder.
References
- Kamyshanska, H., & Memisevic, R. (2014). The potential energy of an autoencoder. IEEE transactions on pattern analysis and machine intelligence, 37(6), 1261-1273.
-
collect_params
(select=None)¶ Overrided collect_params in mxnet.gluon.HybridBlok.
-
compute_loss
(pred_arr, labeled_arr)¶ Compute loss.
Parameters: - pred_arr – mxnet.ndarray or mxnet.symbol.
- labeled_arr – mxnet.ndarray or mxnet.symbol.
Returns: loss.
-
extract_feature_points
()¶ Extract the activities in hidden layer and reset it, considering this method will be called per one cycle in instances of time-series.
Returns: The mxnet.ndarray of array like or sparse matrix of feature points or virtual visible observed data points.
-
extract_learned_dict
()¶ Extract (pre-) learned parameters.
Returns: dict of the parameters.
-
forward_propagation
(F, x)¶ Hybrid forward with Gluon API.
Parameters: - F – mxnet.ndarray or mxnet.symbol.
- x – mxnet.ndarray of observed data points.
Returns: mxnet.ndarray or mxnet.symbol of inferenced feature points.
-
get_init_deferred_flag
()¶ getter for bool that means initialization in this class will be deferred or not.
-
hybrid_forward
(F, x)¶ Hybrid forward with Gluon API.
Parameters: - F – mxnet.ndarray or mxnet.symbol.
- x – mxnet.ndarray of observed data points.
Returns: mxnet.ndarray or mxnet.symbol of inferenced feature points.
-
inference
(observed_arr)¶ Inference the feature points.
Parameters: observed_arr – rank-2 Array like or sparse matrix as the observed data points. The shape is: (batch size, feature points) Returns: mxnet.ndarray of inferenced feature points.
-
init_deferred_flag
¶ getter for bool that means initialization in this class will be deferred or not.
-
load_parameters
(filename, ctx=None, allow_missing=False, ignore_extra=False)¶ Load parameters to files.
Parameters: - filename – File name.
- ctx – mx.cpu() or mx.gpu().
- allow_missing – bool of whether to silently skip loading parameters not represents in the file.
- ignore_extra – bool of whether to silently ignre parameters from the file that are not present in this Block.
-
regularize
()¶ Regularization.
-
save_parameters
(filename)¶ Save parameters to files.
Parameters: filename – File name.
-
set_init_deferred_flag
(value)¶ setter for bool that means initialization in this class will be deferred or not.
-
set_readonly
(value)¶ setter
accelbrainbase.observabledata._mxnet.neuralnetworks.neural_networks_3d module¶
-
class
accelbrainbase.observabledata._mxnet.neuralnetworks.neural_networks_3d.
NN3DHybrid
(computable_loss, initializer=None, learning_rate=1e-05, learning_attenuate_rate=1.0, attenuate_epoch=50, units_list=[100, 1], dropout_rate_list=[0.0, 0.5], optimizer_name='SGD', activation_list=['tanh', 'sigmoid'], hidden_batch_norm_list=[None, None], ctx=gpu(0), hybridize_flag=True, regularizatable_data_list=[], scale=1.0, output_no_bias_flag=False, all_no_bias_flag=False, not_init_flag=False, **kwargs)¶ Bases:
accelbrainbase.observabledata._mxnet.neural_networks.NeuralNetworks
3D Neural networks.
References
- Kamyshanska, H., & Memisevic, R. (2014). The potential energy of an autoencoder. IEEE transactions on pattern analysis and machine intelligence, 37(6), 1261-1273.
-
batch_size
¶ getter
-
forward_propagation
(F, x)¶ Hybrid forward with Gluon API.
Parameters: - F – mxnet.ndarray or mxnet.symbol.
- x – mxnet.ndarray of observed data points. The shape is … - batch. - sequence. - dimention.
Returns: mxnet.ndarray or mxnet.symbol of inferenced feature points.
-
get_batch_size
()¶ getter
-
get_seq_len
()¶ getter
-
seq_len
¶ getter
-
set_batch_size
(value)¶ setter
-
set_seq_len
(value)¶ setter