3h4

init_state = tf.placeholder(tf.float32, [num_layers, 2, batch_size, state_size])

3h4

_total_loss, _train_step, _current_state, _predictions_series = sess.run(
    [total_loss, train_step, current_state, predictions_series],
    feed_dict={
        batchX_placeholder: batchX,
        batchY_placeholder: batchY,
        init_state: _current_state
    })

3h4

_current_state = np.zeros((num_layers, 2, batch_size, state_size))

3h4

from __future__ import print_function, division
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt

num_epochs = 100
total_series_length = 50000
truncated_backprop_length = 15
state_size = 4
num_classes = 2

3h4

_total_loss, _train_step, _current_state, _predictions_series = sess.run(
    [total_loss, train_step, current_state, predictions_series],
    feed_dict={
        batchX_placeholder: batchX,
        batchY_placeholder: batchY,
        cell_state: _current_cell_state,
        hidden_state: _current_hidden_state

    })

3h4

cell = tf.nn.rnn_cell.BasicLSTMCell(state_size, state_is_tuple=True)
states_series, current_state = tf.nn.rnn(cell, inputs_series, init_state)

3h4

cell_state = tf.placeholder(tf.float32, [batch_size, state_size])
hidden_state = tf.placeholder(tf.float32, [batch_size, state_size])
init_state = tf.nn.rnn_cell.LSTMStateTuple(cell_state, hidden_state)

3h4

_current_cell_state = np.zeros((batch_size, state_size))
_current_hidden_state = np.zeros((batch_size, state_size))

3h4

from __future__ import print_function, division
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt

num_epochs = 100
total_series_length = 50000
truncated_backprop_length = 15
state_size = 4
num_classes = 2

3h4

# Unpack columns
inputs_series = tf.split(1, truncated_backprop_length, batchX_placeholder)
labels_series = tf.unpack(batchY_placeholder, axis=1)

# Forward passes
cell = tf.nn.rnn_cell.BasicRNNCell(state_size)
states_series, current_state = tf.nn.rnn(cell, inputs_series, init_state)