def __init__(self, latent_dim=100, sparsity_weight=1, sparsity_objective=0.1): """ Create a sparse shallow AE with the custom kl divergence regularizer. Arguments: sparsity_weight: positive float - the weight of the sparsity cost. sparsity_objective: float between 0 and 1 - the sparsity parameter """ self.latent_dim = latent_dim self.sparsity_weight = sparsity_weight self.sparsity_objective = sparsity_objective input_img = Input(shape=( 28, 28, 1)) # adapt this if using `channels_first` image data format x = Flatten()(input_img) encoded = Dense( latent_dim, activation='sigmoid', activity_regularizer=custom_regularizers.KL_divergence_sum( beta=self.sparsity_weight, rho=self.sparsity_objective))(x) self.encoder = Model(input_img, encoded, name='encoder') encoded_img = Input(shape=(self.latent_dim, )) x = Dense(28 * 28)(encoded_img) x = LeakyReLU(alpha=0.1)(x) decoded = Reshape((28, 28, 1))(x) self.decoder = Model(encoded_img, decoded, name='decoder') encoded = self.encoder(input_img) decoded = self.decoder(encoded) self.autoencoder = Model(input_img, decoded) self.autoencoder.compile(optimizer='adadelta', loss='mean_squared_error')
def __init__(self, latent_dim=100, nb_rows=28, nb_columns=28, nb_input_channels=1, one_channel_output=True, sparsity_weight=0.1, sparsity_objective=0.1): """ Create a sparse shallow AE with the custom kl divergence regularizer, enforcing weights non negativity with Keras NonNeg constraint. Arguments: sparsity_weight: positive float - the weight of the sparsity cost. sparsity_objective: float between 0 and 1 - the sparsity parameter. """ self.latent_dim = latent_dim self.nb_rows=nb_rows self.nb_columns=nb_columns self.nb_input_channels=nb_input_channels if one_channel_output: self.nb_output_channels=1 else: self.nb_output_channels=nb_input_channels self.sparsity_weight = sparsity_weight self.sparsity_objective = sparsity_objective input_img = Input(shape=(self.nb_rows, self.nb_columns, nb_input_channels)) # adapt this if using `channels_first` image data format x = Flatten()(input_img) encoded = Dense(latent_dim, activation='sigmoid', activity_regularizer=custom_regularizers.KL_divergence_sum(beta=self.sparsity_weight, rho=self.sparsity_objective))(x) self.encoder = Model(input_img, encoded, name='encoder') encoded_img = Input(shape=(self.latent_dim,)) x = Dense(self.nb_rows*self.nb_columns*self.nb_output_channels, kernel_constraint=constraints.non_neg())(encoded_img) x = LeakyReLU(alpha=0.1)(x) decoded = Reshape((self.nb_rows,self.nb_columns,self.nb_output_channels))(x) self.decoder = Model(encoded_img, decoded, name='decoder') encoded = self.encoder(input_img) decoded = self.decoder(encoded) self.autoencoder = Model(input_img, decoded) self.autoencoder.compile(optimizer='adadelta', loss='mean_squared_error', metrics=['mse'])
def __init__(self, latent_dim=100, nb_rows=28, nb_columns=28, nb_input_channels=1, one_channel_output=True, sparsity_weight=0.1, sparsity_objective=0.1, dropout_rate=None): """ Create and initialize an autoencoder. """ self.latent_dim = latent_dim self.nb_input_channels=nb_input_channels self.nb_rows=nb_rows self.nb_columns=nb_columns self.sparsity_weight = sparsity_weight self.sparsity_objective = sparsity_objective if one_channel_output: self.nb_output_channels=1 else: self.nb_output_channels=nb_input_channels input_img = Input(shape=(self.nb_rows, self.nb_columns, nb_input_channels)) # adapt this if using `channels_first` image data format x = Flatten()(input_img) encoded = Dense(latent_dim, activation='sigmoid', activity_regularizer=custom_regularizers.KL_divergence_sum(beta=self.sparsity_weight, rho=self.sparsity_objective))(x) self.encoder = Model(input_img, encoded, name='encoder') encoded_img = Input(shape=(self.latent_dim,)) if dropout_rate is None: x = MaxPlusDense(self.nb_rows*self.nb_columns*self.nb_output_channels, use_bias=False, kernel_constraint=custom_constraints.Between_0_and_1())(encoded_img) else: x = Dropout(dropout_rate)(encoded_img) x = MaxPlusDense(self.nb_rows*self.nb_columns*self.nb_output_channels, use_bias=False, kernel_constraint=custom_constraints.Between_0_and_1())(x) decoded = Reshape((self.nb_rows,self.nb_columns,self.nb_output_channels))(x) self.decoder = Model(encoded_img, decoded, name='decoder') encoded = self.encoder(input_img) decoded = self.decoder(encoded) self.autoencoder = Model(input_img, decoded) self.autoencoder.compile(optimizer='adadelta', loss='mean_squared_error', metrics=['mse'])