def generator_cfg():
cfg = AttrDict()
cfg.fonts = fonts
# cfg.dict = lines
cfg.bgs = bgs
cfg.fs = [n for n in range(15,50,3)]
cfg.sw = np.linspace(1,2.5,10)
cfg.d = d
cfg.fnames = file_ids
_alph = ''
for l in cfg.d:
for c in l:
if c not in _alph:
_alph += c
cfg.alph = ''.join(sorted(_alph))
cfg.colors = 'black,yellow,red,green,magenta,blue'
return cfg
def get_params():
checkpoint_dir = './arxiv-predictive-coding'
max_length = 50
sampling_temperature = 0.7
rnn_cell = tf.nn.rnn_cell.GRUCell
rnn_hidden = 200
rnn_layers = 2
learning_rate = 0.002
optimizer = tf.train.AdamOptimizer(0.002)
gradient_clipping = 5
batch_size = 100
epochs = 20
epoch_size = 200
return AttrDict(**locals())
def get_params():
corpus_name = "tiny-shakespeare.txt"
checkpoint_dir = './shakespeare_model'
max_length = 50
sampling_temperature = 0.7
rnn_cell = tf.nn.rnn_cell.GRUCell
rnn_hidden = 200
rnn_layers = 2
learning_rate = 0.002
optimizer = tf.train.AdamOptimizer(0.002)
gradient_clipping = 5
batch_size = 100
epochs = 20
epoch_size = 200
return AttrDict(**locals())
import tensorflow as tf
from helpers import AttrDict
from Embedding import Embedding
from ImdbMovieReviews import ImdbMovieReviews
from preprocess_batched import preprocess_batched
from SequenceClassificationModel import SequenceClassificationModel
IMDB_DOWNLOAD_DIR = './imdb'
WIKI_VOCAB_DIR = '../01_wikipedia/wikipedia'
WIKI_EMBED_DIR = '../01_wikipedia/wikipedia'
params = AttrDict(
rnn_cell=tf.nn.rnn_cell.GRUCell,
rnn_hidden=300,
optimizer=tf.train.RMSPropOptimizer(0.002),
batch_size=20,
)
reviews = ImdbMovieReviews(IMDB_DOWNLOAD_DIR)
length = max(len(x[0]) for x in reviews)
embedding = Embedding(WIKI_VOCAB_DIR + '/vocabulary.bz2',
WIKI_EMBED_DIR + '/embeddings.npy', length)
batches = preprocess_batched(reviews, length, embedding, params.batch_size)
data = tf.placeholder(tf.float32, [None, length, embedding.dimensions])
target = tf.placeholder(tf.float32, [None, 2])
model = SequenceClassificationModel(data, target, params)
sess = tf.Session()
import tensorflow as tf
import numpy as np
from helpers import AttrDict
from OcrDataset import OcrDataset
from BidirectionalSequenceLabellingModel import \
BidirectionalSequenceLabellingModel
from batched import batched
params = AttrDict(rnn_cell=tf.nn.rnn_cell.GRUCell,
rnn_hidden=300,
optimizer=tf.train.RMSPropOptimizer(0.002),
gradient_clipping=5,
batch_size=10,
epochs=5,
epoch_size=50)
def get_dataset():
dataset = OcrDataset('./ocr')
# Flatten images into vectors.
dataset.data = dataset.data.reshape(dataset.data.shape[:2] + (-1, ))
# One-hot encode targets.
target = np.zeros(dataset.target.shape + (26, ))
for index, letter in np.ndenumerate(dataset.target):
if letter:
target[index][ord(letter) - ord('a')] = 1
dataset.target = target
# Shuffle order of examples.
order = np.random.permutation(len(dataset.data))
import numpy as np
from batched import batched
from EmbeddingModel import EmbeddingModel
from skipgrams import skipgrams
from Wikipedia import Wikipedia
from helpers import AttrDict
WIKI_DOWNLOAD_DIR = './wikipedia'
params = AttrDict(
vocabulary_size=10000,
max_context=10,
embedding_size=200,
contrastive_examples=100,
learning_rate=0.5,
momentum=0.5,
batch_size=1000,
)
data = tf.placeholder(tf.int32, [None])
target = tf.placeholder(tf.int32, [None])
model = EmbeddingModel(data, target, params)
corpus = Wikipedia(
'https://dumps.wikimedia.org/enwiki/20160501/'
'enwiki-20160501-pages-meta-current1.xml-p000000010p000030303.bz2',
WIKI_DOWNLOAD_DIR, params.vocabulary_size)
examples = skipgrams(corpus, params.max_context)
batches = batched(examples, params.batch_size)
def trainer_cfg():
cfg = AttrDict()
cfg.DATANAME = './data2/data.csv'
cfg.bs = 256
cfg.epochs = 60
cfg.lr = 1e-3
cfg.wl2 = 1e-7
cfg.pivot = 15
cfg.valid_loss = float('Inf')
cfg.train_loss = float('Inf')
cfg.val_acc = float('Inf')
cfg.train_acc = float('Inf')
return cfg
