import colorsys
import numpy as np
import operator
import theano.tensor as T
import skimage.color
from collections import Sequence, Counter
from lasagne.layers import InputLayer, EmbeddingLayer, reshape
from matplotlib.colors import hsv_to_rgb
from stanza.research.rng import get_rng
rng = get_rng()
class SymbolVectorizer(object):
'''
Maps symbols from an alphabet/vocabulary of indefinite size to and from
sequential integer ids.
>>> vec = SymbolVectorizer()
>>> vec.add_all(['larry', 'moe', 'larry', 'curly', 'moe'])
>>> vec.vectorize_all(['curly', 'larry', 'moe', 'pikachu'])
array([3, 1, 2, 0], dtype=int32)
>>> vec.unvectorize_all([3, 3, 2])
['curly', 'curly', 'moe']
'''
def __init__(self):
self.tokens = []
self.token_indices = {}
self.indices_token = {}
self.add('<unk>')
parser = config.get_options_parser()
parser.add_argument(
'--split',
type=str,
default='dev',
help='The data split to draw the human evaluation data from.')
parser.add_argument('--test_size',
type=int,
default=None,
help='The number of examples to use in human evaluation. '
'If None, use the whole dev/test set.')
BATCH_SIZE = 10
random = rng.get_rng()
class HumanListener(learner.Learner):
def __init__(self):
self.num_params = 0
self.memory = {}
with open('human_listener.txt', 'r') as infile:
for line in infile:
if '\t' in line:
desc, color_str = line.strip().split('\t')
assert color_str.startswith('(') and color_str.endswith(
')'), color_str
color = tuple(
float(d) for d in color_str[1:-1].split(', '))
self.memory[desc] = color
OPTIMIZERS = {
name: func
for name, func in lasagne.updates.__dict__.iteritems()
if (name in lasagne.updates.__all__ and
not name.startswith('apply_') and not name.endswith('_constraint'))
}
CELLS = {
name[:-len('Layer')]: func
for name, func in lasagne.layers.recurrent.__dict__.iteritems()
if (name in lasagne.layers.recurrent.__all__ and name.endswith('Layer') and
name != 'CustomRecurrentLayer')
}
rng = get_rng()
lasagne.random.set_rng(rng)
def detect_nan(i, node, fn):
if not isinstance(node.op, (T.AllocEmpty, T.IncSubtensor,
G.GpuAllocEmpty, G.GpuIncSubtensor)):
for output in fn.outputs:
if (not isinstance(output[0], np.random.RandomState) and
not np.isfinite(output[0]).all()):
print('*** NaN detected ***')
theano.printing.debugprint(node)
print('Inputs : %s' % [input[0] for input in fn.inputs])
print('Outputs: %s' % [output[0] for output in fn.outputs])
raise AssertionError
from lasagne.nonlinearities import softmax
from lasagne.updates import rmsprop
from stanza.monitoring import progress
from stanza.research import config, instance, iterators, rng
import color_instances
import speaker
import data_aug
from helpers import ForgetSizeLayer, GaussianScoreLayer, logit_softmax_nd
from neural import NeuralLearner, SimpleLasagneModel
from neural import NONLINEARITIES, OPTIMIZERS, CELLS, sample
from vectorizers import SequenceVectorizer, BucketsVectorizer, SymbolVectorizer
from vectorizers import strip_invalid_tokens, COLOR_REPRS
from tokenizers import TOKENIZERS
random = rng.get_rng()
parser = config.get_options_parser()
parser.add_argument('--listener_cell_size', type=int, default=20,
help='The number of dimensions of all hidden layers and cells in '
'the listener model. If 0 and using the AtomicListenerLearner, '
'remove all hidden layers and only train a linear classifier.')
parser.add_argument('--listener_forget_bias', type=float, default=5.0,
help='The initial value of the forget gate bias in LSTM cells in '
'the listener model. A positive initial forget gate bias '
'encourages the model to remember everything by default.')
parser.add_argument('--listener_nonlinearity', choices=NONLINEARITIES.keys(), default='tanh',
help='The nonlinearity/activation function to use for dense and '
'LSTM layers in the listener model.')
parser.add_argument('--listener_cell', choices=CELLS.keys(), default='LSTM',
help='The recurrent cell to use for the listener model.')
