def _generator_wrapper():
"""
Wraps data_generator to precompute labels in python before everything
becomes tensors.
NOTE: Local to get_dataset for sensible passing of args to generator
function.
Returns:
caption : ground truth string
image : raw mat object image [32, ?, 1]
label : list of indices corresponding to out_charset plus a temporary
increment; length=len( caption )
"""
# Extract args
[ config_path, num_producers ] = args[0:2]
# TODO/NOTE currently using 0 to get true single threaded synthesis
gen = data_generator( config_path, num_producers )
while True:
caption, image = next( gen )
# Transform string text to sequence of indices using charset dict
label = charset.string_to_label(caption)
# Temporarily increment all labels so that zero can be the EOS token
# during post-batch dense-to-sparse conversion
label = [index+1 for index in label]
yield caption, image, label
def get_text_and_labels(filename):
"""
Extract the human-readable text and label sequence from image filename
"""
# Ground truth string lines embedded within base
# filename between underscores
# 2697/6/466_MONIKER_49537.jpg --> MONIKER
text = os.path.basename(filename).split('_', 2)[1]
# Transform string text to sequence of indices using charset, e.g.,
# MONIKER -> [12, 14, 13, 8, 10, 4, 17]
labels = charset.string_to_label(text)
return text, labels