Наткнулся на такой код
# tf Graph input
x = tf.placeholder("float", [None, seq_max_len, 1])
y = tf.placeholder("float", [None, n_classes])
# A placeholder for indicating each sequence length
seqlen = tf.placeholder(tf.int32, [None])
# Define weights
weights = {
'out': tf.Variable(tf.random_normal([n_hidden, n_classes]))
}
biases = {
'out': tf.Variable(tf.random_normal([n_classes]))
}
def dynamicRNN(x, seqlen, weights, biases):
# Prepare data shape to match `rnn` function requirements
# Current data input shape: (batch_size, n_steps, n_input)
# Required shape: 'n_steps' tensors list of shape (batch_size, n_input)
# Unstack to get a list of 'n_steps' tensors of shape (batch_size, n_input)
x = tf.unstack(x, seq_max_len, 1)
# Define a lstm cell with tensorflow
lstm_cell = tf.contrib.rnn.BasicLSTMCell(n_hidden)
# Get lstm cell output, providing 'sequence_length' will perform dynamic
# calculation.
outputs, states = tf.contrib.rnn.static_rnn(lstm_cell, x, dtype=tf.float32,
sequence_length=seqlen)
# When performing dynamic calculation, we must retrieve the last
# dynamically computed output, i.e., if a sequence length is 10, we need
# to retrieve the 10th output.
# However TensorFlow doesn't support advanced indexing yet, so we build
# a custom op that for each sample in batch size, get its length and
# get the corresponding relevant output.
# 'outputs' is a list of output at every timestep, we pack them in a Tensor
# and change back dimension to [batch_size, n_step, n_input]
outputs = tf.stack(outputs)
outputs = tf.transpose(outputs, [1, 0, 2])
# Hack to build the indexing and retrieve the right output.
batch_size = tf.shape(outputs)[0]
# Start indices for each sample
index = tf.range(0, batch_size) * seq_max_len + (seqlen - 1)
# Indexing
outputs = tf.gather(tf.reshape(outputs, [-1, n_hidden]), index)
# Linear activation, using outputs computed above
return tf.matmul(outputs, weights['out']) + biases['out']
pred = dynamicRNN(x, seqlen, weights, biases)
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate).minimize(cost)
Cобственно вопрос:
Разве при каждом обращении к функции dynamic_rnn lstm слои не будут заново инициализироваться?
Простой