def get_cnn():
c_nn = ClusterNNTry00_V51(dp,
20,
en,
lstm_layers=7,
internal_embedding_size=96,
cluster_count_dense_layers=1,
cluster_count_dense_units=256,
output_dense_layers=1,
output_dense_units=256,
cluster_count_lstm_layers=1,
cluster_count_lstm_units=128,
kl_embedding_size=128,
kl_divergence_factor=0.1)
c_nn.include_self_comparison = False
c_nn.weighted_classes = True
c_nn.class_weights_approximation = 'stochastic'
c_nn.minibatch_size = 15
c_nn.class_weights_post_processing_f = lambda x: np.sqrt(x)
c_nn.set_loss_weight('similarities_output', 5.0)
c_nn.optimizer = Adadelta(lr=5.0)
validation_factor = 10
c_nn.early_stopping_iterations = 15001
c_nn.validate_every_nth_epoch = 10 * validation_factor
c_nn.validation_data_count = c_nn.minibatch_size * validation_factor
# c_nn.prepend_base_name_to_layer_name = False
return c_nn
cnn_layers_per_block=1,
block_feature_counts=[32, 64, 128],
fc_layer_feature_counts=[256],
hidden_activation=LeakyReLU(),
final_activation=LeakyReLU(),
batch_norm_for_init_layer=False,
batch_norm_after_activation=True,
batch_norm_for_final_layer=True)
c_nn = ClusterNNTry00_V51(dp,
40,
en,
lstm_layers=21,
internal_embedding_size=384,
cluster_count_dense_layers=1,
cluster_count_dense_units=256,
output_dense_layers=1,
output_dense_units=256,
cluster_count_lstm_layers=1,
cluster_count_lstm_units=512,
kl_embedding_size=128,
kl_divergence_factor=0.1)
c_nn.include_self_comparison = False
c_nn.weighted_classes = True
c_nn.class_weights_approximation = 'stochastic'
c_nn.minibatch_size = 15
c_nn.class_weights_post_processing_f = lambda x: np.sqrt(x)
c_nn.set_loss_weight('similarities_output', 5.0)
c_nn.optimizer = Adadelta(lr=5.0)
validation_factor = 10
minimum_snippets_per_cluster=2,
# Use this mode for the real avaluation
snippet_merge_mode=[8, 2] if used_input_count == required_input_count else None
# minimum_snippets_per_cluster=[(200, 200), (100, 100)],
# window_width=[(100, 200)]
)
en = CnnEmbedding(
output_size=256, cnn_layers_per_block=1, block_feature_counts=[32, 64, 128],
fc_layer_feature_counts=[256], hidden_activation=LeakyReLU(), final_activation=LeakyReLU(),
batch_norm_for_init_layer=False, batch_norm_after_activation=True, batch_norm_for_final_layer=True
)
c_nn = ClusterNNTry00_V51(dp, used_input_count, en, lstm_layers=7, internal_embedding_size=96, cluster_count_dense_layers=1, cluster_count_dense_units=256,
output_dense_layers=1, output_dense_units=256, cluster_count_lstm_layers=1, cluster_count_lstm_units=128,
kl_embedding_size=128, kl_divergence_factor=0.1)
c_nn.include_self_comparison = False
c_nn.weighted_classes = True
c_nn.class_weights_approximation = 'stochastic'
c_nn.minibatch_size = 35
c_nn.class_weights_post_processing_f = lambda x: np.sqrt(x)
c_nn.set_loss_weight('similarities_output', 5.0)
c_nn.optimizer = Adadelta(lr=5.0)
validation_factor = 10
c_nn.early_stopping_iterations = 10001
c_nn.validate_every_nth_epoch = 10 * validation_factor
c_nn.validation_data_count = c_nn.minibatch_size * validation_factor
# c_nn.prepend_base_name_to_layer_name = False
print_loss_plot_every_nth_itr = 100