Snippets

Our code belongs to everyone. Thus, we strive to offer the most possible commented, documented, and exemplified code of all time. In Learnergy, we present code snippets in an attempt to fulfill everyone's needs.

Applications

• loading_pre_trained_model.py: Loads a pre-trained model and use it for reconstructing new data.

Bernoulli

• conv_rbm_classification.py: Convolutional Restricted Boltzmann Machines training and discriminative fine-tuning;
• conv_rbm_training.py: Convolutional Restricted Boltzmann Machines training;
• discriminative_rbm_training.py: Discriminative Restricted Boltzmann Machines training;
• dropconnect_rbm_training.py: DropConnect Restricted Boltzmann Machines training;
• dropout_rbm_training.py: Dropout Restricted Boltzmann Machines training;
• e_dropout_rbm_training.py: Energy-based Dropout Restricted Boltzmann Machines training;
• hybrid_discriminative_rbm_training.py: Hybrid Discriminative Restricted Boltzmann Machines training;
• rbm_classification.py: Restricted Boltzmann Machines training and discriminative fine-tuning;
• rbm_training.py: Restricted Boltzmann Machines training.

Deep

• conv_dbn_training.py: Convolutional Deep Belief Networks training;
• dbn_classification.py Deep Belief Networks training and discriminative fine-tuning;
• dbn_training.py: Deep Belief Networks training;
• residual_dbn_training.py: Residual Deep Belief Networks training.

Extra

• sigmoid_rbm_training.py: Sigmoid Restricted Boltzmann Machines training.

Gaussian

• gaussian_conv_rbm_classification.py: Gaussian Convolutional Restricted Boltzmann Machines training and discriminative fine-tuning;
• gaussian_conv_rbm_training.py: Gaussian Convolutional Restricted Boltzmann Machines training;
• gaussian_rbm_training.py: Gaussian Restricted Boltzmann Machines training;
• gaussian_relu_rbm_training.py: Gaussian ReLU Restricted Boltzmann Machines training;
• variance_gaussian_rbm_training.py: Variance Gaussian Restricted Boltzmann Machines training.

Core

• create_dataset.py: Dataset class creation;
• create_model.py: Model class creation.

Math

• calculate_ssim.py: Calculates the structural similarity of reconstructed images;
• unitary_scaling.py: Unitary scaling of an array.

Models

Bernoulli

• create_conv_rbm.py: How-to create a ConvRBM class;
• create_discriminative_rbm.py: How-to create a DiscriminativeRBM class;
• create_dropconnect_rbm.py: How-to create a DropConnectRBM class;
• create_dropout_rbm.py: How-to create a DropoutRBM class;
• create_e_dropout_rbm.py: How-to create a EDropoutRBM class;
• create_hybrid_discriminative_rbm.py: How-to create a HybridDiscriminativeRBM class;
• create_rbm.py: How-to create a RBM class.

Deep

• create_conv_dbn.py: How-to create a ConvDBN class;
• create_dbn.py: How-to create a DBN class;
• create_residual_dbn.py: How-to create a ResidualDBN class.

Extra

• create_sigmoid_rbm.py: How-to create a SigmoidRBM class.

Gaussian

• create_gaussian_conv_rbm.py: How-to create a GaussianConvRBM class;
• create_gaussian_rbm.py: How-to create a GaussianRBM class;
• create_gaussian_relu_rbm.py: How-to create a GaussianReluRBM class;
• create_variance_gaussian_rbm.py: How-to create a VarianceGaussianRBM class.

Visual

• create_weights_mosaic.py: Creates a weight mosaic from a model's weights;
• plot_metrics_convergence.py: Plots the training metrics convergence into pre-formatted graphics;
• show_reconstructed_sample.py: Fits a model, reconstruct a new sample and shows the reconstructed sample.