filename, modelfile, outputfile = argv
# load gotdata
gotData = PickleHandler("./got.pkl")
def loss(labels, logits):
return tf.keras.losses.sparse_categorical_crossentropy(labels,
logits,
from_logits=True)
# define a new model
model = tf.keras.Sequential([
# a embedding layer
tf.keras.layers.Embedding(gotData.vocab_size(),
256,
batch_input_shape=[1, None]),
# lstm layer
tf.keras.layers.LSTM(
512,
stateful=True,
return_sequences=True,
recurrent_initializer="glorot_uniform",
),
# dropout layer
tf.keras.layers.Dropout(0.4),
tf.keras.layers.LSTM(
256,
stateful=True,
return_sequences=True,
# load gotdata
gotData = PickleHandler("./got.pkl")
def loss(labels, logits):
return tf.keras.losses.sparse_categorical_crossentropy(
labels, logits, from_logits=True
)
# define a new model
model = tf.keras.Sequential(
[
# a embedding layer
tf.keras.layers.Embedding(
gotData.vocab_size(), 256, batch_input_shape=[1, None]
),
# lstm layer
# bidirectional rnn layer
tf.keras.layers.Bidirectional(
tf.keras.layers.SimpleRNN(
1024,
return_sequences=True,
stateful=True,
recurrent_initializer="glorot_uniform",
)
),
# dropout layer
tf.keras.layers.Dropout(0.4),
# dense layer
tf.keras.layers.Dense(gotData.vocab_size()),
# define some dataset params
BATCH_SIZE = 64
# buffer size for storage
BUFFER_SIZE = 1000
# shuffle dataset for our model
dataset = dataset.shuffle(BUFFER_SIZE).batch(BATCH_SIZE, drop_remainder=True)
# some hyper prams
rnn_units = 1024 # number of rnn units
embedding_units = 256 # size of embedding
vocab_size = gotData.vocab_size() # vocab size for input
# build model function
def build_model(vocab_size, rnn_units, embedding_units, batch_size):
# make a sequenctial model
model = tf.keras.Sequential([
# first embedding layer
tf.keras.layers.Embedding(vocab_size,
embedding_units,
batch_input_shape=[batch_size, None]),
# hidden gru layer
tf.keras.layers.GRU(
rnn_units,
return_sequences=True,
stateful=True,
