def testForward(self):
batch_size = 1
height, width = 224, 224
with self.test_session() as sess:
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_16(inputs)
sess.run(tf.global_variables_initializer())
output = sess.run(logits)
self.assertTrue(output.any())
def testModelVariables(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
vgg.vgg_16(inputs, num_classes)
expected_names = [
'vgg_16/conv1/conv1_1/weights',
'vgg_16/conv1/conv1_1/biases',
'vgg_16/conv1/conv1_2/weights',
'vgg_16/conv1/conv1_2/biases',
'vgg_16/conv2/conv2_1/weights',
'vgg_16/conv2/conv2_1/biases',
'vgg_16/conv2/conv2_2/weights',
'vgg_16/conv2/conv2_2/biases',
'vgg_16/conv3/conv3_1/weights',
'vgg_16/conv3/conv3_1/biases',
'vgg_16/conv3/conv3_2/weights',
'vgg_16/conv3/conv3_2/biases',
'vgg_16/conv3/conv3_3/weights',
'vgg_16/conv3/conv3_3/biases',
'vgg_16/conv4/conv4_1/weights',
'vgg_16/conv4/conv4_1/biases',
'vgg_16/conv4/conv4_2/weights',
'vgg_16/conv4/conv4_2/biases',
'vgg_16/conv4/conv4_3/weights',
'vgg_16/conv4/conv4_3/biases',
'vgg_16/conv5/conv5_1/weights',
'vgg_16/conv5/conv5_1/biases',
'vgg_16/conv5/conv5_2/weights',
'vgg_16/conv5/conv5_2/biases',
'vgg_16/conv5/conv5_3/weights',
'vgg_16/conv5/conv5_3/biases',
'vgg_16/fc6/weights',
'vgg_16/fc6/biases',
'vgg_16/fc7/weights',
'vgg_16/fc7/biases',
'vgg_16/fc8/weights',
'vgg_16/fc8/biases',
]
model_variables = [v.op.name for v in slim.get_model_variables()]
self.assertSetEqual(set(model_variables), set(expected_names))
def testFullyConvolutional(self):
batch_size = 1
height, width = 256, 256
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_16(inputs, num_classes, spatial_squeeze=False)
self.assertEquals(logits.op.name, 'vgg_16/fc8/BiasAdd')
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, 2, 2, num_classes])
def testBuild(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_16(inputs, num_classes)
self.assertEquals(logits.op.name, 'vgg_16/fc8/squeezed')
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
def testEvaluation(self):
batch_size = 2
height, width = 224, 224
num_classes = 1000
with self.test_session():
eval_inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_16(eval_inputs, is_training=False)
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
predictions = tf.argmax(logits, 1)
self.assertListEqual(predictions.get_shape().as_list(),
[batch_size])
def testTrainEvalWithReuse(self):
train_batch_size = 2
eval_batch_size = 1
train_height, train_width = 224, 224
eval_height, eval_width = 256, 256
num_classes = 1000
with self.test_session():
train_inputs = tf.random_uniform(
(train_batch_size, train_height, train_width, 3))
logits, _ = vgg.vgg_16(train_inputs)
self.assertListEqual(logits.get_shape().as_list(),
[train_batch_size, num_classes])
tf.get_variable_scope().reuse_variables()
eval_inputs = tf.random_uniform(
(eval_batch_size, eval_height, eval_width, 3))
logits, _ = vgg.vgg_16(eval_inputs,
is_training=False,
spatial_squeeze=False)
self.assertListEqual(logits.get_shape().as_list(),
[eval_batch_size, 2, 2, num_classes])
logits = tf.reduce_mean(logits, [1, 2])
predictions = tf.argmax(logits, 1)
self.assertEquals(predictions.get_shape().as_list(),
[eval_batch_size])
def testEndPoints(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = vgg.vgg_16(inputs, num_classes)
expected_names = [
'vgg_16/conv1/conv1_1', 'vgg_16/conv1/conv1_2', 'vgg_16/pool1',
'vgg_16/conv2/conv2_1', 'vgg_16/conv2/conv2_2', 'vgg_16/pool2',
'vgg_16/conv3/conv3_1', 'vgg_16/conv3/conv3_2',
'vgg_16/conv3/conv3_3', 'vgg_16/pool3', 'vgg_16/conv4/conv4_1',
'vgg_16/conv4/conv4_2', 'vgg_16/conv4/conv4_3', 'vgg_16/pool4',
'vgg_16/conv5/conv5_1', 'vgg_16/conv5/conv5_2',
'vgg_16/conv5/conv5_3', 'vgg_16/pool5', 'vgg_16/fc6',
'vgg_16/fc7', 'vgg_16/fc8'
]
self.assertSetEqual(set(end_points.keys()), set(expected_names))
def get_network_byname(net_name,
inputs,
num_classes=None,
is_training=True,
global_pool=True,
output_stride=None,
spatial_squeeze=True):
if net_name == 'resnet_v1_50':
FLAGS = get_flags_byname(net_name)
with slim.arg_scope(
resnet_v1.resnet_arg_scope(weight_decay=FLAGS.weight_decay)):
logits, end_points = resnet_v1.resnet_v1_50(
inputs=inputs,
num_classes=num_classes,
is_training=is_training,
global_pool=global_pool,
output_stride=output_stride,
spatial_squeeze=spatial_squeeze)
return logits, end_points
if net_name == 'resnet_v1_101':
FLAGS = get_flags_byname(net_name)
with slim.arg_scope(
resnet_v1.resnet_arg_scope(weight_decay=FLAGS.weight_decay)):
logits, end_points = resnet_v1.resnet_v1_101(
inputs=inputs,
num_classes=num_classes,
is_training=is_training,
global_pool=global_pool,
output_stride=output_stride,
spatial_squeeze=spatial_squeeze)
return logits, end_points
if net_name == 'pvanet':
FLAGS = get_flags_byname(net_name)
with slim.arg_scope(
pvanet.pvanet_scope(
is_training=is_training,
weights_initializer=slim.xavier_initializer(),
batch_norm_param_initializer=None,
beta_initializer=tf.zeros_initializer(),
gamma_initializer=tf.ones_initializer(),
weight_decay=0.99)):
logits, end_points = pvanet.pvanet(net=inputs,
include_last_bn_relu=True)
return logits, end_points
if net_name == 'vgg_16':
FLAGS = get_flags_byname(net_name)
with slim.arg_scope(
vgg.vgg_arg_scope(weight_decay=FLAGS.weight_decay)):
logits, end_points = vgg.vgg_16(
inputs=inputs,
num_classes=num_classes,
is_training=is_training,
dropout_keep_prob=0.5,
spatial_squeeze=spatial_squeeze,
)
return logits, end_points
# if net_name == 'inception_resnet_v2':
# FLAGS = get_flags_byname(net_name)
# with slim.arg_scope(inception_resnet_v2.inception_resnet_v2_arg_scope(weight_decay=FLAGS.weight_decay)):
# logits, end_points = inception_resnet_v2.inception_resnet_v2(inputs=inputs,
# num_classes=num_classes,
# is_training=is_training,
# dropout_keep_prob=0.8,
# )
# return logits, end_points
if net_name == 'inception_resnet':
FLAGS = get_flags_byname(net_name)
arg_sc = inception_resnet_v2.inception_resnet_v2_arg_scope(
weight_decay=FLAGS.weight_decay)
with slim.arg_scope(arg_sc):
logits, end_points = inception_resnet_v2.inception_resnet_v2(
inputs=inputs,
num_classes=num_classes,
is_training=is_training)
return logits, end_points
if net_name == 'inception_v4':
FLAGS = get_flags_byname(net_name)
arg_sc = inception_v4.inception_v4_arg_scope(
weight_decay=FLAGS.weight_decay)
with slim.arg_scope(arg_sc):
logits, end_points = inception_v4.inception_v4(
inputs=inputs,
num_classes=num_classes,
is_training=is_training)
return logits, end_points
if net_name == 'mobilenet_224':
FLAGS = get_flags_byname(net_name)
with slim.arg_scope(
mobilenet_v1.mobilenet_v1_arg_scope(
weight_decay=FLAGS.weight_decay)):
logits, end_points = mobilenet_v1.mobilenet_v1(
inputs=inputs,
num_classes=num_classes,
is_training=is_training,
spatial_squeeze=spatial_squeeze)
return logits, end_points