Method init

imagernn/generic_batch_generator.py:23–50

(params, misc)

  @staticmethod
  def init(params, misc):

    # inputs
    image_encoding_size = params.get('image_encoding_size', 128)
    word_encoding_size = params.get('word_encoding_size', 128)
    hidden_size = params.get('hidden_size', 128)
    generator = params.get('generator', 'lstm')
    vocabulary_size = len(misc['wordtoix'])
    output_size = len(misc['ixtoword']) # these should match though
    image_size = 4096 # size of CNN vectors hardcoded here

    if generator == 'lstm':
      assert image_encoding_size == word_encoding_size, 'this implementation does not support different sizes for these parameters'

    # initialize the encoder models
    model = {}
    model['We'] = initw(image_size, image_encoding_size) # image encoder
    model['be'] = np.zeros((1,image_encoding_size))
    model['Ws'] = initw(vocabulary_size, word_encoding_size) # word encoder
    update = ['We', 'be', 'Ws']
    regularize = ['We', 'Ws']
    init_struct = { 'model' : model, 'update' : update, 'regularize' : regularize}

    # descend into the specific Generator and initialize it
    Generator = decodeGenerator(generator)
    generator_init_struct = Generator.init(word_encoding_size, hidden_size, output_size)
    merge_init_structs(init_struct, generator_init_struct)
    return init_struct

  @staticmethod
  def forward(batch, model, params, misc, predict_mode = False):