def _test(self, input_shape, block_shape, base_paddings):
input_shape = np.array(input_shape)
block_shape = np.array(block_shape)
if base_paddings is not None:
base_paddings = np.array(base_paddings)
# Check with constants.
paddings, crops = tf.required_space_to_batch_paddings(
input_shape, block_shape, base_paddings)
paddings_const = tensor_util.constant_value(paddings)
crops_const = tensor_util.constant_value(crops)
self.assertIsNotNone(paddings_const)
self.assertIsNotNone(crops_const)
self._checkProperties(input_shape, block_shape, base_paddings,
paddings_const, crops_const)
# Check with non-constants.
assignments = {}
input_shape_placeholder = tf.placeholder(tf.int32)
assignments[input_shape_placeholder] = input_shape
block_shape_placeholder = tf.placeholder(tf.int32, [len(block_shape)])
assignments[block_shape_placeholder] = block_shape
if base_paddings is not None:
base_paddings_placeholder = tf.placeholder(tf.int32,
[len(block_shape), 2])
assignments[base_paddings_placeholder] = base_paddings
else:
base_paddings_placeholder = None
t_paddings, t_crops = tf.required_space_to_batch_paddings(
input_shape_placeholder, block_shape_placeholder,
base_paddings_placeholder)
with self.test_session():
paddings_result = t_paddings.eval(assignments)
crops_result = t_crops.eval(assignments)
self.assertAllEqual(paddings_result, paddings_const)
self.assertAllEqual(crops_result, crops_const)
def _build_dilated(image, is_training=False):
#image = tf.Print(image, [tf.shape(image)], message='img_shape = ', summarize=10)
bn_params['is_training'] = is_training
with arg_scope([layers.conv2d],
data_format=data_format, stride=1, padding='SAME', activation_fn=None,
normalizer_fn=None, normalizer_params=None,
weights_initializer=init_func, biases_initializer=None,
weights_regularizer=layers.l2_regularizer(weight_decay)):
with tf.variable_scope('conv0'):
net = layers.conv2d(image, 2*growth, 7, stride=2)
#net = layers.conv2d(image, 2*growth, 7, stride=1)
# TODO
net = tf.contrib.layers.batch_norm(net, **bn_params)
net = tf.nn.relu(net)
net = layers.max_pool2d(net, 2, stride=2, padding='SAME',
data_format=data_format, scope='pool0')
skip_layers = []
# no diff with double BN from orig densenet, first=True
net = dense_block(net, block_sizes[0], growth, 'block0', is_training, first=True)
#net, skip = dense_block(net, block_sizes[0], growth, 'block0', is_training,
# first=True, split=True)
#skip_layers.append([skip, 256, growth_up, 'block0_mid_refine', depth])
#skip_layers.append([skip, up_sizes[0], growth_up, 'block0_mid_refine'])
skip_layers.append([net, up_sizes[0], growth_up, 'block0_refine'])
net, _ = transition(net, compression, 'block0/transition')
#skip_layers.append([skip, up_sizes[0], growth_up, 'block0_refine'])
#net, skip = dense_block(net, block_sizes[1], growth, 'block1', is_training, split=True)
#skip_layers.append([skip, up_sizes[1], growth_up, 'block1_mid_refine'])
net = dense_block(net, block_sizes[1], growth, 'block1', is_training)
skip_layers.append([net, up_sizes[1], growth_up, 'block1_refine'])
net, _ = transition(net, compression, 'block1/transition')
#skip_layers.append([skip, up_sizes[1], growth_up, 'block1_refine'])
# works the same with split, not 100%
#context_pool_num = 3
#context_pool_num = 4
context_pool_num = 5
#net, skip = dense_block(net, block_sizes[2], growth, 'block2', is_training, split=True)
#skip_layers.append([skip, up_sizes[2], growth_up, 'block2_mid_refine'])
net = dense_block(net, block_sizes[2], growth, 'block2', is_training)
#skip_layers.append([net, up_sizes[3], growth_up, 'block2_refine'])
#skip_layers.append([net, up_sizes[2], growth_up, 'block2_refine'])
net, _ = transition(net, compression, 'block2/transition', stride=1)
bsz = 2
paddings, crops = tf.required_space_to_batch_paddings(image_size(net), [bsz, bsz])
net = tf.space_to_batch(net, paddings=paddings, block_size=bsz)
net = dense_block(net, block_sizes[3], growth, 'block3', is_training)
net = tf.batch_to_space(net, crops=crops, block_size=bsz)
print('before context = ', net)
with tf.variable_scope('head'):
net = BNReluConv(net, 512, 'bottleneck', k=1)
net = _pyramid_pooling(net, size=context_pool_num)
#net = BNReluConv(net, context_size, 'context_conv', k=3)
print('Before upsampling: ', net)
all_logits = [net]
for skip_layer in reversed(skip_layers):
net = refine(net, skip_layer)
all_logits.append(net)
print('after upsampling = ', net)
all_logits = [all_logits[0], all_logits[-1]]
#all_logits = [all_logits[1], all_logits[-1]]
#all_logits = [all_logits[2], all_logits[-1]]
with tf.variable_scope('head'):
for i, logits in enumerate(all_logits):
with tf.variable_scope('logits_'+str(i)):
# FIX
#net = tf.nn.relu(layers.batch_norm(net, **bn_params))
#logits = layers.conv2d(net, FLAGS.num_classes, 1, activation_fn=None,
# data_format=data_format)
logits = layers.conv2d(tf.nn.relu(logits), FLAGS.num_classes, 1,
activation_fn=None, data_format=data_format)
if data_format == 'NCHW':
logits = tf.transpose(logits, perm=[0,2,3,1])
input_shape = tf.shape(image)[height_dim:height_dim+2]
logits = tf.image.resize_bilinear(logits, input_shape, name='resize_logits')
all_logits[i] = logits
logits = all_logits.pop()
return logits, all_logits
def inputter_crop(): _, crops = tf.required_space_to_batch_paddings(input_shape, block_shape) return tf.cast(crops, tf.float64)
def inputter_pad(): pads, _ = tf.required_space_to_batch_paddings(input_shape, block_shape) return tf.cast(pads, tf.float64)
def inputter_crop():
_, crops = tf.required_space_to_batch_paddings(inputs_int32[0],
inputs_int32[1],
base_paddings=inputs_int32[2])
return tf.cast(crops, tf.float64)
def inputter_pad():
pads, _ = tf.required_space_to_batch_paddings(inputs_int32[0],
inputs_int32[1],
base_paddings=inputs_int32[2])
return tf.cast(pads, tf.float64)