def _get_pyramid_pooling_arguments(self,
crop_size,
output_stride,
image_grid,
image_pooling_crop_size=None):
"""Gets arguments for pyramid pooling.
Args:
crop_size: A list of two integers, [crop_height, crop_width] specifying
whole patch crop size.
output_stride: Integer, output stride value for extracted features.
image_grid: A list of two integers, [image_grid_height, image_grid_width],
specifying the grid size of how the pyramid pooling will be performed.
image_pooling_crop_size: A list of two integers, [crop_height, crop_width]
specifying the crop size for image pooling operations. Note that we
decouple whole patch crop_size and image_pooling_crop_size as one could
perform the image_pooling with different crop sizes.
Returns:
A list of (resize_value, pooled_kernel)
"""
resize_height = utils.scale_dimension(crop_size[0], 1. / output_stride)
resize_width = utils.scale_dimension(crop_size[1], 1. / output_stride)
# If image_pooling_crop_size is not specified, use crop_size.
if image_pooling_crop_size is None:
image_pooling_crop_size = crop_size
pooled_height = utils.scale_dimension(
image_pooling_crop_size[0], 1. / (output_stride * image_grid[0]))
pooled_width = utils.scale_dimension(
image_pooling_crop_size[1], 1. / (output_stride * image_grid[1]))
return ([resize_height, resize_width], [pooled_height, pooled_width])
def _apply_conv_operation(self, net, operation, stride,
is_from_original_input):
"""Applies the predicted conv operation to net."""
if stride > 1 and not is_from_original_input:
stride = 1
input_filters = net.shape[3]
filter_size = self._filter_size
if 'separable' in operation:
num_layers = int(operation.split('_')[-1])
kernel_size = int(operation.split('x')[0][-1])
for layer_num in range(num_layers):
net = tf.nn.relu(net)
net = slim.separable_conv2d(
net,
filter_size,
kernel_size,
depth_multiplier=1,
scope='separable_{0}x{0}_{1}'.format(kernel_size, layer_num + 1),
stride=stride)
net = slim.batch_norm(
net, scope='bn_sep_{0}x{0}_{1}'.format(kernel_size, layer_num + 1))
stride = 1
elif 'atrous' in operation:
kernel_size = int(operation.split('x')[0][-1])
net = tf.nn.relu(net)
if stride == 2:
scaled_height = scale_dimension(tf.shape(net)[1], 0.5)
scaled_width = scale_dimension(tf.shape(net)[2], 0.5)
net = resize_bilinear(net, [scaled_height, scaled_width], net.dtype)
net = slim.conv2d(net, filter_size, kernel_size, rate=1,
scope='atrous_{0}x{0}'.format(kernel_size))
else:
net = slim.conv2d(net, filter_size, kernel_size, rate=2,
scope='atrous_{0}x{0}'.format(kernel_size))
net = slim.batch_norm(net, scope='bn_atr_{0}x{0}'.format(kernel_size))
elif operation in ['none']:
if stride > 1 or (input_filters != filter_size):
net = tf.nn.relu(net)
net = slim.conv2d(net, filter_size, 1, stride=stride, scope='1x1')
net = slim.batch_norm(net, scope='bn_1')
elif 'pool' in operation:
pooling_type = operation.split('_')[0]
pooling_shape = int(operation.split('_')[-1].split('x')[0])
if pooling_type == 'avg':
net = slim.avg_pool2d(net, pooling_shape, stride=stride, padding='SAME')
elif pooling_type == 'max':
net = slim.max_pool2d(net, pooling_shape, stride=stride, padding='SAME')
else:
raise ValueError('Unimplemented pooling type: ', pooling_type)
if input_filters != filter_size:
net = slim.conv2d(net, filter_size, 1, stride=1, scope='1x1')
net = slim.batch_norm(net, scope='bn_1')
else:
raise ValueError('Unimplemented operation', operation)
if operation != 'none':
net = self._apply_drop_path(net)
return net
def _build_nas_base(images,
cell,
backbone,
num_classes,
hparams,
global_pool=False,
reuse=None,
scope=None,
final_endpoint=None):
"""Constructs a NAS model.
Args:
images: A tensor of size [batch, height, width, channels].
cell: Cell structure used in the network.
backbone: Backbone structure used in the network. A list of integers in
which value 0 means "output_stride=4", value 1 means "output_stride=8",
value 2 means "output_stride=16", and value 3 means "output_stride=32".
num_classes: Number of classes to predict.
hparams: Hyperparameters needed to construct the network.
global_pool: If True, we perform global average pooling before computing the
logits. Set to True for image classification, False for dense prediction.
reuse: Whether or not the network and its variables should be reused. To be
able to reuse 'scope' must be given.
scope: Optional variable_scope.
final_endpoint: The endpoint to construct the network up to.
Returns:
net: A rank-4 tensor of size [batch, height_out, width_out, channels_out].
end_points: A dictionary from components of the network to the corresponding
activation.
"""
with tf.variable_scope(scope, 'nas', [images], reuse=reuse):
end_points = {}
def add_and_check_endpoint(endpoint_name, net):
end_points[endpoint_name] = net
return final_endpoint and (endpoint_name == final_endpoint)
net, cell_outputs = _nas_stem(images)
if add_and_check_endpoint('Stem', net):
return net, end_points
# Run the cells
filter_scaling = 1.0
for cell_num in range(len(backbone)):
stride = 1
if cell_num == 0:
if backbone[0] == 1:
stride = 2
filter_scaling *= hparams.filter_scaling_rate
else:
if backbone[cell_num] == backbone[cell_num - 1] + 1:
stride = 2
filter_scaling *= hparams.filter_scaling_rate
elif backbone[cell_num] == backbone[cell_num - 1] - 1:
scaled_height = scale_dimension(net.shape[1].value, 2)
scaled_width = scale_dimension(net.shape[2].value, 2)
net = resize_bilinear(net, [scaled_height, scaled_width],
net.dtype)
filter_scaling /= hparams.filter_scaling_rate
net = cell(net,
scope='cell_{}'.format(cell_num),
filter_scaling=filter_scaling,
stride=stride,
prev_layer=cell_outputs[-2],
cell_num=cell_num)
if add_and_check_endpoint('Cell_{}'.format(cell_num), net):
return net, end_points
cell_outputs.append(net)
net = tf.nn.relu(net)
if global_pool:
# Global average pooling.
net = tf.reduce_mean(net, [1, 2],
name='global_pool',
keepdims=True)
if num_classes is not None:
net = slim.conv2d(net,
num_classes, [1, 1],
activation_fn=None,
normalizer_fn=None,
scope='logits')
end_points['predictions'] = slim.softmax(net, scope='predictions')
return net, end_points