pydbm.cnn package¶
Subpackages¶
- pydbm.cnn.convolutionalneuralnetwork package
- Subpackages
- pydbm.cnn.convolutionalneuralnetwork.convolutionalautoencoder package
- Submodules
- pydbm.cnn.convolutionalneuralnetwork.convolutionalautoencoder.contractive_convolutional_auto_encoder module
- pydbm.cnn.convolutionalneuralnetwork.convolutionalautoencoder.convolutional_ladder_networks module
- pydbm.cnn.convolutionalneuralnetwork.convolutionalautoencoder.repelling_convolutional_auto_encoder module
- Module contents
- pydbm.cnn.convolutionalneuralnetwork.convolutionalautoencoder package
- Submodules
- pydbm.cnn.convolutionalneuralnetwork.convolutional_auto_encoder module
- pydbm.cnn.convolutionalneuralnetwork.residual_learning module
- Module contents
- Subpackages
- pydbm.cnn.featuregenerator package
- pydbm.cnn.layerablecnn package
Submodules¶
pydbm.cnn.convolutional_neural_network module¶
-
class
pydbm.cnn.convolutional_neural_network.
ConvolutionalNeuralNetwork
¶ Bases:
object
Convolutional Neural Network.
-
back_propagation
¶ Back propagation in CNN.
Parameters: Delta. – - Returns.
- Delta.
-
computable_loss
¶ getter
-
forward_propagation
¶ Forward propagation in CNN.
Parameters: img_arr – np.ndarray of image file array. Returns: Propagated np.ndarray.
-
get_computable_loss
¶ getter
-
get_layerable_cnn_list
¶ getter
-
get_opt_params
¶ getter
-
get_verificatable_result
¶ getter
-
get_weight_decay_term
¶ getter
-
inference
¶ Inference the feature points to reconstruct the time-series.
Override.
Parameters: observed_arr – Array like or sparse matrix as the observed data points. Returns: Predicted array like or sparse matrix.
-
layerable_cnn_list
¶ getter
-
learn
¶ Learn.
Parameters: - observed_arr – np.ndarray of observed data points.
- target_arr – np.ndarray of labeled data. If None, the function of this cnn model is equivalent to Convolutional Auto-Encoder.
-
learn_generated
¶ Learn features generated by FeatureGenerator.
Parameters: feature_generator – is-a FeatureGenerator.
-
opt_params
¶ getter
-
optimize
¶ Back propagation.
Parameters: - learning_rate – Learning rate.
- epoch – Now epoch.
-
output_back_propagate
¶ Back propagation in output layer.
Parameters: - pred_arr – np.ndarray of predicted data points.
- delta_output_arr – Delta.
Returns: Tuple data. - np.ndarray of Delta, - list of gradations.
-
output_forward_propagate
¶ Forward propagation in output layer.
Parameters: pred_arr – np.ndarray of predicted data points. Returns: np.ndarray of propagated data points.
-
save_pre_learned_params
¶ Save pre-learned parameters.
Parameters: - dir_path – Path of dir. If None, the file is saved in the current directory.
- file_name – The naming rule of files. If None, this value is cnn.
-
set_computable_loss
¶ setter
-
set_layerable_cnn_list
¶ setter
-
set_opt_params
¶ setter
-
set_verificatable_result
¶ setter
-
set_weight_decay_term
¶ setter
-
setup_output_layer
¶ Setup output layer.
Parameters: - cnn_output_graph – Computation graph which is-a CNNOutputGraph to compute parameters in output layer.
- pre_learned_path – File path that stores pre-learned parameters.
-
verificatable_result
¶ getter
-
weight_decay_term
¶ getter
-
pydbm.cnn.feature_generator module¶
pydbm.cnn.layerable_cnn module¶
-
class
pydbm.cnn.layerable_cnn.
LayerableCNN
¶ Bases:
object
The abstract class of convolutional neural network.
-
affine_to_img
¶ Affine transform for Convolution.
Parameters: - reshaped_img_arr – np.ndarray of 2-rank image array.
- img_arr – np.ndarray of 4-rank image array.
- kernel_height – Height of kernel.
- kernel_width – Width of kernel.
- stride – Stride.
- pad – padding value.
Returns: 2-rank image array.
-
affine_to_matrix
¶ Affine transform for Convolution.
Parameters: - img_arr – np.ndarray of 4-rank image array.
- kernel_height – Height of kernel.
- kernel_width – Width of kernel.
- stride – Stride.
- pad – padding value.
Returns: 2-rank image array.
-
back_propagate
¶ Back propagation in CNN layers.
Parameters: delta_arr – 4-rank array like or sparse matrix. Returns: 3-rank array like or sparse matrix.
-
delta_bias_arr
¶ Delta of bias vector.
-
delta_weight_arr
¶ Delta of weight matirx.
-
forward_propagate
¶ Forward propagation in CNN layers.
Parameters: matriimg_arr – 4-rank array like or sparse matrix. Returns: 4-rank array like or sparse matrix.
-
graph
¶ Graph which is-a Synapse.
-
reset_delta
¶ Reset delta.
-
pydbm.cnn.spatio_temporal_auto_encoder module¶
-
class
pydbm.cnn.spatio_temporal_auto_encoder.
SpatioTemporalAutoEncoder
¶ Bases:
object
Spatio-Temporal Auto-Encoder.
The Spatio-Temporal Auto-Encoder can learn the regular patterns in the training videos(Baccouche, M., et al., 2012, Patraucean, V., et al. 2015).
This model consists of spatial Auto-Encoder and temporal Encoder/Decoder. The spatial Auto-Encoder is a Convolutional Auto-Encoder for learning spatial structures of each video frame. The temporal Encoder/Decoder is an Encoder/Decoder based on LSTM scheme for learning temporal patterns of the encoded spatial structures. The spatial encoder and decoder have two convolutional and deconvolutional layers respectively, while the temporal encoder and decoder are to act as a twin LSTM models.
References
- https://github.com/chimera0/accel-brain-code/blob/master/Deep-Learning-by-means-of-Design-Pattern/demo/demo_stacked_auto_encoder.ipynb
- Baccouche, M., Mamalet, F., Wolf, C., Garcia, C., & Baskurt, A. (2012, September). Spatio-Temporal Convolutional Sparse Auto-Encoder for Sequence Classification. In BMVC (pp. 1-12).
- Chong, Y. S., & Tay, Y. H. (2017, June). Abnormal event detection in videos using spatiotemporal autoencoder. In International Symposium on Neural Networks (pp. 189-196). Springer, Cham.
- Masci, J., Meier, U., Cireşan, D., & Schmidhuber, J. (2011, June). Stacked convolutional auto-encoders for hierarchical feature extraction. In International Conference on Artificial Neural Networks (pp. 52-59). Springer, Berlin, Heidelberg.
- Patraucean, V., Handa, A., & Cipolla, R. (2015). Spatio-temporal video autoencoder with differentiable memory. arXiv preprint arXiv:1511.06309.
-
back_propagation
¶ Back propagation in CNN.
Parameters: Delta. – - Returns.
- Delta.
-
extract_features_points
¶ Extract features points.
Returns: Tuple data. - Temporal encoded feature points, - Temporal decoded feature points, - Fully-connected Spatio encoded feature points and Temporal decoded feature points
-
forward_propagation
¶ Forward propagation in Convolutional Auto-Encoder.
Override.
Parameters: img_arr – np.ndarray of image file array. Returns: Propagated np.ndarray.
-
get_layerable_cnn_list
¶ getter
-
get_verificatable_result
¶ getter
-
inference
¶ Inference the feature points to reconstruct the time-series.
Override.
Parameters: observed_arr – Array like or sparse matrix as the observed data points. Returns: Predicted array like or sparse matrix.
-
layerable_cnn_list
¶ getter
-
learn
¶ Learn.
Parameters: - observed_arr – np.ndarray of observed data points.
- target_arr – np.ndarray of labeled data. If None, the function of this cnn model is equivalent to Convolutional Auto-Encoder.
-
learn_generated
¶ Learn features generated by FeatureGenerator.
Parameters: feature_generator – is-a FeatureGenerator.
-
load_pre_learned_params
¶ Load pre-learned parameters.
Parameters: dir_path – Path of dir. If None, the file is saved in the current directory.
-
optimize
¶ Back propagation.
Parameters: - learning_rate – Learning rate.
- epoch – Now epoch.
-
save_pre_learned_params
¶ Save pre-learned parameters.
Parameters: dir_path – Path of dir. If None, the file is saved in the current directory.
-
set_layerable_cnn_list
¶ setter
-
set_verificatable_result
¶ setter
-
temporal_back_propagation
¶ Back propagation in temporal Encoder/Decoder.
Parameters: - pred_arr – np.ndarray of predicted data points from decoder.
- delta_output_arr – Delta.
Returns: Tuple data. - decoder’s list of gradations, - encoder’s np.ndarray of Delta, - encoder’s list of gradations.
-
temporal_inference
¶ Inference the feature points to reconstruct the time-series.
Override.
Parameters: - observed_arr – Array like or sparse matrix as the observed data ponts.
- hidden_activity_arr – Array like or sparse matrix as the state in hidden layer.
- rnn_activity_arr – Array like or sparse matrix as the state in RNN.
Returns: Tuple data. - Array like or sparse matrix of reconstructed instances of time-series, - Array like or sparse matrix of the state in hidden layer, - Array like or sparse matrix of the state in RNN.
-
temporal_optimize
¶ Back propagation in temporal Encoder/Decoder.
Parameters: - decoder_grads_list – decoder’s list of graduations.
- encoder_grads_list – encoder’s list of graduations.
- learning_rate – Learning rate.
- epoch – Now epoch.
-
verificatable_result
¶ getter