layers - Contains the definitions of all the types of layers.

The module yann.layers contains the definition for the different types of layers that are accessible in yann. It contains various layers including:

• abstract.layer
• input.input_layer

• fully_connected.dropout_dot_product_layer and

  fully_connected.dot_product_layer

• conv_pool.dropout_conv_pool_layer_2d and

  conv_pool.conv_pool_layer_2d

• ouput.classifier_layer
• output.objective_layer
• merge.merge_layer
• flatten.flatten_layer
• flatten.unflatten_layer
• random.random_layer

• batch_norm.batch_norm_layer_2d and

  batch_norm.dropout_batch_norm_layer_2d

• batch_norm.batch_norm_layer_1d and

  batch_norm.dropout_batch_norm_layer_1d

All these are inherited classes from layer class, which is abstract.

Specific layers that can be used are

• abstract - abstraction class
• input - input layer classes
• fully_connected - fully connected layer classes
• conv_pool - conv pool layer classes
• merge - merge layer classes
• flatten - flatten layer classes
• output - output layer classes
• random - random layer classes
• transform - transform layers
  • LICENSE
• batch_norm - Batch normalization layer classes