# remove file ending
model_name = model_name[:model_name.find('.json')]
# In[5]:
print('Building model graph...')
tf.reset_default_graph()
batch_size = tf.placeholder_with_default(1, [], name='batch_size')
# input_op, seq_len, label = data.ops.get_batch_producer(
# batch_size=batch_size, path='./data/train.TFRecord')
input_op = tf.placeholder(tf.float32, [1, None])
seq_len = tf.placeholder(tf.float32, [1])
c = cnn.model(seq_len=seq_len, input_op=input_op, **cnn_params)
r = rnn.get_model(batch_size=batch_size,
seq_len=seq_len,
input_op=c.output,
**rnn_params)
f = fourier.get_output(seq_len=seq_len, input_op=input_op, **fourier_params)
td = time_domain.get_output(seq_len=seq_len,
input_op=input_op,
**time_domain_params)
concatenated_features = tf.concat([r.last_output, f, td], 1)
fc = classifier.model(input_op=concatenated_features, **fc_params)
logits = fc.logits
pred = fc.pred
print('Building model... done!')
# Load recording
print('Loading record...', end=' ')
# dir = "./validation/"
batch = 128
optimizer = 'rmsprop'
seq = 5
new_words = 1000
temperature = 0.5
file = inp(text, seq)
file.text_seq()
x, y = file.rnn_input()
rnn = rnn(text,
x,
y,
layer1=layer,
dropout=drop,
epochs=epochs,
batch=batch,
optimizer=optimizer)
rnn.define()
# rnn.load()
rnn.train()
new = output(file.get_content(),
seq=seq,
words=new_words,
temp=temperature)
vocab, dict1, dict2 = file.get_vocab()
new_text = new.generate(rnn.get_model(), vocab, dict1, dict2)
# print new_text
file.save(new_text)