def reduce_to_final(images, num_filters_out, nhidden=None, scope=None):
"""Reduce an image to a final state by running two LSTMs.
Args:
images: (num_images, height, width, depth) tensor
num_filters_out: output layer depth
nhidden: hidden layer depth (defaults to num_filters_out)
scope: optional scope name
Returns:
A (num_images, num_filters_out) batch.
"""
with variable_scope.variable_scope(scope, "ReduceToFinal", [images]):
nhidden = nhidden or num_filters_out
batch_size, height, width, depth = _shape(images)
transposed = array_ops.transpose(images, [1, 0, 2, 3])
reshaped = array_ops.reshape(transposed,
[height, batch_size * width, depth])
with variable_scope.variable_scope("reduce1"):
reduced = lstm1d.sequence_to_final(reshaped, nhidden)
transposed_hidden = array_ops.reshape(reduced,
[batch_size, width, nhidden])
hidden = array_ops.transpose(transposed_hidden, [1, 0, 2])
with variable_scope.variable_scope("reduce2"):
output = lstm1d.sequence_to_final(hidden, num_filters_out)
return output
def testSequenceToFinalDims(self):
with self.test_session():
inputs = tf.constant(_rand(17, 6, 5))
outputs = lstm1d.sequence_to_final(inputs, 8)
tf.initialize_all_variables().run()
result = outputs.eval()
self.assertEqual(tuple(result.shape), (6, 8))
def reduce_to_sequence(images, num_filters_out, scope=None):
"""Reduce an image to a sequence by scanning an LSTM vertically.
Args:
images: (num_images, height, width, depth) tensor
num_filters_out: output layer depth
scope: optional scope name
Returns:
A (width, num_images, num_filters_out) sequence.
"""
with tf.variable_scope(scope, "ReduceToSequence", [images]):
batch_size, height, width, depth = _shape(images)
transposed = tf.transpose(images, [1, 0, 2, 3])
reshaped = tf.reshape(transposed, [height, batch_size * width, depth])
reduced = lstm1d.sequence_to_final(reshaped, num_filters_out)
output = tf.reshape(reduced, [batch_size, width, num_filters_out])
return output
def reduce_to_sequence(images, num_filters_out, scope=None):
"""Reduce an image to a sequence by scanning an LSTM vertically.
Args:
images: (num_images, height, width, depth) tensor
num_filters_out: output layer depth
scope: optional scope name
Returns:
A (width, num_images, num_filters_out) sequence.
"""
with tf.variable_scope(scope, "ReduceToSequence", [images]):
batch_size, height, width, depth = _shape(images)
transposed = tf.transpose(images, [1, 0, 2, 3])
reshaped = tf.reshape(transposed, [height, batch_size * width, depth])
reduced = lstm1d.sequence_to_final(reshaped, num_filters_out)
output = tf.reshape(reduced, [batch_size, width, num_filters_out])
return output
