repr(idx2char[target_idx])))
# Buffer size to shuffle the dataset
# (TF data is designed to work with possibly infinite sequences,
# so it doesn't attempt to shuffle the entire sequence in memory. Instead,
# it maintains a buffer in which it shuffles elements).
BUFFER_SIZE = 10000
dataset = dataset.shuffle(BUFFER_SIZE).batch(BATCH_SIZE, drop_remainder=True)
model = Model(len(char2idx), EMBEDDING_DIM, UNITS)
# Using adam optimizer with default arguments
optimizer = tf.train.AdamOptimizer()
model.build(tf.TensorShape([BATCH_SIZE, SEQ_LENGTH]))
model.summary()
# Training step
EPOCHS = 30
# Directory where the checkpoints will be saved
checkpoint_dir = os.getenv('TRAINING_CHECKPOINT_DIR',
'./data/training_checkpoints')
# Name of the checkpoint files
checkpoint_prefix = os.path.join(checkpoint_dir, "ckpt")
# Checkpoint instance
checkpoint = tf.train.Checkpoint(optimizer=optimizer, model=model)
import time
import os
print("Starting up")
with open(os.getenv('VOCAB_FILE', './data/vocab.txt'), 'r') as text_file:
vocab = text_file.read().split("\n")
(char2idx, idx2char) = vocab_to_char2idx_idx2char(vocab)
model = Model(len(char2idx), EMBEDDING_DIM, UNITS)
checkpoint_dir = os.getenv('TRAINING_CHECKPOINT_DIR',
'./data/training_checkpoints')
model.load_weights(tf.train.latest_checkpoint(checkpoint_dir))
model.build(tf.TensorShape([1, None]))
# Number of characters to generate
num_generate = 1000
# You can change the start string to experiment
start_string = 'Q'
# Converting our start string to numbers (vectorizing)
input_eval = [char2idx[s] for s in start_string]
input_eval = tf.expand_dims(input_eval, 0)
# Empty string to store our results
text_generated = []
# Low temperatures results in more predictable text.
