def testModelVariables(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
with self.test_session():
inputs = random_ops.random_uniform((batch_size, height, width, 3))
vgg.vgg_19(inputs, num_classes)
expected_names = [
'vgg_19/conv1/conv1_1/weights',
'vgg_19/conv1/conv1_1/biases',
'vgg_19/conv1/conv1_2/weights',
'vgg_19/conv1/conv1_2/biases',
'vgg_19/conv2/conv2_1/weights',
'vgg_19/conv2/conv2_1/biases',
'vgg_19/conv2/conv2_2/weights',
'vgg_19/conv2/conv2_2/biases',
'vgg_19/conv3/conv3_1/weights',
'vgg_19/conv3/conv3_1/biases',
'vgg_19/conv3/conv3_2/weights',
'vgg_19/conv3/conv3_2/biases',
'vgg_19/conv3/conv3_3/weights',
'vgg_19/conv3/conv3_3/biases',
'vgg_19/conv3/conv3_4/weights',
'vgg_19/conv3/conv3_4/biases',
'vgg_19/conv4/conv4_1/weights',
'vgg_19/conv4/conv4_1/biases',
'vgg_19/conv4/conv4_2/weights',
'vgg_19/conv4/conv4_2/biases',
'vgg_19/conv4/conv4_3/weights',
'vgg_19/conv4/conv4_3/biases',
'vgg_19/conv4/conv4_4/weights',
'vgg_19/conv4/conv4_4/biases',
'vgg_19/conv5/conv5_1/weights',
'vgg_19/conv5/conv5_1/biases',
'vgg_19/conv5/conv5_2/weights',
'vgg_19/conv5/conv5_2/biases',
'vgg_19/conv5/conv5_3/weights',
'vgg_19/conv5/conv5_3/biases',
'vgg_19/conv5/conv5_4/weights',
'vgg_19/conv5/conv5_4/biases',
'vgg_19/fc6/weights',
'vgg_19/fc6/biases',
'vgg_19/fc7/weights',
'vgg_19/fc7/biases',
'vgg_19/fc8/weights',
'vgg_19/fc8/biases',
]
model_variables = [
v.op.name for v in variables_lib.get_model_variables()
]
self.assertSetEqual(set(model_variables), set(expected_names))
def testModelVariables(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
with self.test_session():
inputs = random_ops.random_uniform((batch_size, height, width, 3))
vgg.vgg_19(inputs, num_classes)
expected_names = [
'vgg_19/conv1/conv1_1/weights',
'vgg_19/conv1/conv1_1/biases',
'vgg_19/conv1/conv1_2/weights',
'vgg_19/conv1/conv1_2/biases',
'vgg_19/conv2/conv2_1/weights',
'vgg_19/conv2/conv2_1/biases',
'vgg_19/conv2/conv2_2/weights',
'vgg_19/conv2/conv2_2/biases',
'vgg_19/conv3/conv3_1/weights',
'vgg_19/conv3/conv3_1/biases',
'vgg_19/conv3/conv3_2/weights',
'vgg_19/conv3/conv3_2/biases',
'vgg_19/conv3/conv3_3/weights',
'vgg_19/conv3/conv3_3/biases',
'vgg_19/conv3/conv3_4/weights',
'vgg_19/conv3/conv3_4/biases',
'vgg_19/conv4/conv4_1/weights',
'vgg_19/conv4/conv4_1/biases',
'vgg_19/conv4/conv4_2/weights',
'vgg_19/conv4/conv4_2/biases',
'vgg_19/conv4/conv4_3/weights',
'vgg_19/conv4/conv4_3/biases',
'vgg_19/conv4/conv4_4/weights',
'vgg_19/conv4/conv4_4/biases',
'vgg_19/conv5/conv5_1/weights',
'vgg_19/conv5/conv5_1/biases',
'vgg_19/conv5/conv5_2/weights',
'vgg_19/conv5/conv5_2/biases',
'vgg_19/conv5/conv5_3/weights',
'vgg_19/conv5/conv5_3/biases',
'vgg_19/conv5/conv5_4/weights',
'vgg_19/conv5/conv5_4/biases',
'vgg_19/fc6/weights',
'vgg_19/fc6/biases',
'vgg_19/fc7/weights',
'vgg_19/fc7/biases',
'vgg_19/fc8/weights',
'vgg_19/fc8/biases',
]
model_variables = [v.op.name for v in variables_lib.get_model_variables()]
self.assertSetEqual(set(model_variables), set(expected_names))
def testEndPoints(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
for is_training in [True, False]:
with ops.Graph().as_default():
inputs = random_ops.random_uniform(
(batch_size, height, width, 3))
_, end_points = vgg.vgg_19(inputs,
num_classes,
is_training=is_training)
expected_names = [
'vgg_19/conv1/conv1_1', 'vgg_19/conv1/conv1_2',
'vgg_19/pool1', 'vgg_19/conv2/conv2_1',
'vgg_19/conv2/conv2_2', 'vgg_19/pool2',
'vgg_19/conv3/conv3_1', 'vgg_19/conv3/conv3_2',
'vgg_19/conv3/conv3_3', 'vgg_19/conv3/conv3_4',
'vgg_19/pool3', 'vgg_19/conv4/conv4_1',
'vgg_19/conv4/conv4_2', 'vgg_19/conv4/conv4_3',
'vgg_19/conv4/conv4_4', 'vgg_19/pool4',
'vgg_19/conv5/conv5_1', 'vgg_19/conv5/conv5_2',
'vgg_19/conv5/conv5_3', 'vgg_19/conv5/conv5_4',
'vgg_19/pool5', 'vgg_19/fc6', 'vgg_19/fc7', 'vgg_19/fc8'
]
self.assertSetEqual(set(end_points.keys()),
set(expected_names))
def tower_loss(scope):
images, labels = read_and_decode()
if net == 'vgg_16':
with slim.arg_scope(vgg.vgg_arg_scope()):
logits, end_points = vgg.vgg_16(images, num_classes=FLAGS.num_classes)
elif net == 'vgg_19':
with slim.arg_scope(vgg.vgg_arg_scope()):
logits, end_points = vgg.vgg_19(images, num_classes=FLAGS.num_classes)
elif net == 'resnet_v1_101':
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
logits, end_points = resnet_v1.resnet_v1_101(images, num_classes=FLAGS.num_classes)
logits = tf.reshape(logits, [FLAGS.batch_size, FLAGS.num_classes])
elif net == 'resnet_v1_50':
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
logits, end_points = resnet_v1.resnet_v1_50(images, num_classes=FLAGS.num_classes)
logits = tf.reshape(logits, [FLAGS.batch_size, FLAGS.num_classes])
elif net == 'resnet_v2_50':
with slim.arg_scope(resnet_v2.resnet_arg_scope()):
logits, end_points = resnet_v2.resnet_v2_50(images, num_classes=FLAGS.num_classes)
logits = tf.reshape(logits, [FLAGS.batch_size, FLAGS.num_classes])
else:
raise Exception('No network matched with net %s.' % net)
assert logits.shape == (FLAGS.batch_size, FLAGS.num_classes)
_ = cal_loss(logits, labels)
losses = tf.get_collection('losses', scope)
total_loss = tf.add_n(losses, name='total_loss')
for l in losses + [total_loss]:
loss_name = re.sub('%s_[0-9]*/' % TOWER_NAME, '', l.op.name)
tf.summary.scalar(loss_name, l)
return total_loss
def testForward(self):
batch_size = 1
height, width = 224, 224
with self.test_session() as sess:
inputs = random_ops.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_19(inputs)
sess.run(variables.global_variables_initializer())
output = sess.run(logits)
self.assertTrue(output.any())
def testForward(self):
batch_size = 1
height, width = 224, 224
with self.test_session() as sess:
inputs = random_ops.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_19(inputs)
sess.run(variables.global_variables_initializer())
output = sess.run(logits)
self.assertTrue(output.any())
def model_fn(features, labels, mode):
img_mean = tf.reshape(tf.constant(IMAGENET_MEAN), (1, 1, 3))
img = tf.cast(features, tf.float32)
output = vgg.vgg_19(img - img_mean,
is_training=(mode == tf.estimator.ModeKeys.TRAIN))
logits = tf.layers.dense(tf.layers.flatten(output[1]['vgg_19/fc7']),
2,
activation=None,
name="new_logits")
probabilities = tf.nn.softmax(logits)
predicted_classes = tf.argmax(probabilities, axis=1)
loss = None
train_op = None
if mode in [tf.estimator.ModeKeys.TRAIN, tf.estimator.ModeKeys.EVAL]:
loss = tf.losses.softmax_cross_entropy(labels, logits)
if mode == tf.estimator.ModeKeys.TRAIN:
with tf.variable_scope('', reuse=tf.AUTO_REUSE):
train_vars = [
tf.get_variable('new_logits/kernel'),
tf.get_variable('new_logits/bias')
]
train_vars.extend([
var for var in tf.trainable_variables()
if var.name.startswith('vgg_19/fc')
and not var.name.startswith("vgg_19/fc8")
])
print(train_vars)
train_op = tf.train.AdamOptimizer(learning_rate=0.001).minimize(
loss,
global_step=tf.train.get_or_create_global_step(),
var_list=train_vars)
metrics = None
if mode == tf.estimator.ModeKeys.EVAL:
metrics = {
'accuracy':
tf.metrics.accuracy(labels=tf.argmax(labels, axis=1),
predictions=predicted_classes)
}
predictions = None
if mode == tf.estimator.ModeKeys.PREDICT:
predictions = {
'probabilities': probabilities,
'predictions': predicted_classes
}
return tf.estimator.EstimatorSpec(mode=mode,
predictions=predictions,
loss=loss,
train_op=train_op,
eval_metric_ops=metrics)
def testBuild(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
with self.test_session():
inputs = random_ops.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_19(inputs, num_classes)
self.assertEquals(logits.op.name, 'vgg_19/fc8/squeezed')
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
def testFullyConvolutional(self):
batch_size = 1
height, width = 256, 256
num_classes = 1000
with self.test_session():
inputs = random_ops.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_19(inputs, num_classes, spatial_squeeze=False)
self.assertEquals(logits.op.name, 'vgg_19/fc8/BiasAdd')
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, 2, 2, num_classes])
def testFullyConvolutional(self):
batch_size = 1
height, width = 256, 256
num_classes = 1000
with self.test_session():
inputs = random_ops.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_19(inputs, num_classes, spatial_squeeze=False)
self.assertEquals(logits.op.name, 'vgg_19/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 = random_ops.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_19(inputs, num_classes)
self.assertEquals(logits.op.name, 'vgg_19/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 = random_ops.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_19(eval_inputs, is_training=False)
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
predictions = math_ops.argmax(logits, 1)
self.assertListEqual(predictions.get_shape().as_list(), [batch_size])
def testEvaluation(self):
batch_size = 2
height, width = 224, 224
num_classes = 1000
with self.test_session():
eval_inputs = random_ops.random_uniform(
(batch_size, height, width, 3))
logits, _ = vgg.vgg_19(eval_inputs, is_training=False)
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
predictions = math_ops.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 = random_ops.random_uniform(
(train_batch_size, train_height, train_width, 3))
logits, _ = vgg.vgg_19(train_inputs)
self.assertListEqual(logits.get_shape().as_list(),
[train_batch_size, num_classes])
variable_scope.get_variable_scope().reuse_variables()
eval_inputs = random_ops.random_uniform(
(eval_batch_size, eval_height, eval_width, 3))
logits, _ = vgg.vgg_19(
eval_inputs, is_training=False, spatial_squeeze=False)
self.assertListEqual(logits.get_shape().as_list(),
[eval_batch_size, 2, 2, num_classes])
logits = math_ops.reduce_mean(logits, [1, 2])
predictions = math_ops.argmax(logits, 1)
self.assertEquals(predictions.get_shape().as_list(), [eval_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 = random_ops.random_uniform(
(train_batch_size, train_height, train_width, 3))
logits, _ = vgg.vgg_19(train_inputs)
self.assertListEqual(logits.get_shape().as_list(),
[train_batch_size, num_classes])
variable_scope.get_variable_scope().reuse_variables()
eval_inputs = random_ops.random_uniform(
(eval_batch_size, eval_height, eval_width, 3))
logits, _ = vgg.vgg_19(eval_inputs,
is_training=False,
spatial_squeeze=False)
self.assertListEqual(logits.get_shape().as_list(),
[eval_batch_size, 2, 2, num_classes])
logits = math_ops.reduce_mean(logits, [1, 2])
predictions = math_ops.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
for is_training in [True, False]:
with ops.Graph().as_default():
inputs = random_ops.random_uniform((batch_size, height, width, 3))
_, end_points = vgg.vgg_19(inputs, num_classes, is_training=is_training)
expected_names = [
'vgg_19/conv1/conv1_1', 'vgg_19/conv1/conv1_2', 'vgg_19/pool1',
'vgg_19/conv2/conv2_1', 'vgg_19/conv2/conv2_2', 'vgg_19/pool2',
'vgg_19/conv3/conv3_1', 'vgg_19/conv3/conv3_2',
'vgg_19/conv3/conv3_3', 'vgg_19/conv3/conv3_4', 'vgg_19/pool3',
'vgg_19/conv4/conv4_1', 'vgg_19/conv4/conv4_2',
'vgg_19/conv4/conv4_3', 'vgg_19/conv4/conv4_4', 'vgg_19/pool4',
'vgg_19/conv5/conv5_1', 'vgg_19/conv5/conv5_2',
'vgg_19/conv5/conv5_3', 'vgg_19/conv5/conv5_4', 'vgg_19/pool5',
'vgg_19/fc6', 'vgg_19/fc7', 'vgg_19/fc8'
]
self.assertSetEqual(set(end_points.keys()), set(expected_names))
def generate_graph(conv_layer=(1, 1), filter_idx=0, lr=0.01, graph=None):
assert len(conv_layer) == 2 and all([isinstance(item, int) for item in
conv_layer]), "`conv_filter` must be a tuple of two integers that identify the conv layer in the VGG 19 network"
layer_name = 'vgg_19/conv{0}/conv{0}_{1}'.format(*conv_layer)
if graph is None:
graph = tf.get_default_graph()
with graph.as_default():
img_mean = tf.reshape(tf.constant(IMAGENET_MEAN), (1, 1, 3))
params = tf.get_variable("synthetic_img",
initializer=tf.random_normal((1, 224, 224, 3), 0, 0.001, dtype=tf.float32))
img = (tf.nn.tanh(params) * 255.0) + img_mean
img = tf.clip_by_value(img, 0, 255)
test_img = tf.cast(img, tf.uint8)
output = vgg.vgg_19(img - img_mean, is_training=False)
layer = output[1][layer_name]
loss = -tf.reduce_mean(layer[:, :, :, filter_idx])
train_op = tf.train.AdamOptimizer(learning_rate=lr).minimize(loss, var_list=[params])
init_op = tf.global_variables_initializer()
saver = tf.train.Saver(list(filter(lambda v: v != params, tf.trainable_variables())))
def init_fn(sess):
sess.run(init_op)
saver.restore(sess, get_model_checkpoint("VGG 19"))
return {
'graph': graph,
'test_img': test_img,
'init_fn': init_fn,
'train_op': train_op,
'loss': loss
}
def vgg_19_extract(images,
trainable=True,
is_training=True,
weight_decay=0.00004,
stddev=0.1,
dropout_keep_prob=0.8,
use_batch_norm=True,
batch_norm_params=None,
add_summaries=True,
scope="vgg_19"):
"""Builds an VGG_19 subgraph for image embeddings.
Args:
images: A float32 Tensor of shape [batch, height, width, channels].
trainable: Whether the VGG_19 submodel should be trainable or not.
is_training: Boolean indicating training mode or not.
weight_decay: Coefficient for weight regularization.
stddev: The standard deviation of the trunctated normal weight initializer.
dropout_keep_prob: Dropout keep probability.
use_batch_norm: Whether to use batch normalization.
batch_norm_params: Parameters for batch normalization. See
tf.contrib.layers.batch_norm for details.
add_summaries: Whether to add activation summaries.
scope: Optional Variable scope.
Returns:
end_points: A dictionary of activations from inception_v3 layers.
"""
# Only consider the inception model to be in training mode if it's trainable.
is_vgg_model_training = trainable and is_training
if use_batch_norm:
# Default parameters for batch normalization.
if not batch_norm_params:
batch_norm_params = {
"is_training": is_vgg_model_training,
"trainable": trainable,
# Decay for the moving averages.
"decay": 0.9997,
# Epsilon to prevent 0s in variance.
"epsilon": 0.001,
# Collection containing the moving mean and moving variance.
"variables_collections": {
"beta": None,
"gamma": None,
"moving_mean": ["moving_vars"],
"moving_variance": ["moving_vars"],
}
}
else:
batch_norm_params = None
if trainable:
weights_regularizer = tf.contrib.layers.l2_regularizer(weight_decay)
else:
weights_regularizer = None
with tf.variable_scope(scope, [images]) as scope:
with slim.arg_scope([slim.conv2d, slim.fully_connected],
weights_regularizer=weights_regularizer,
trainable=trainable):
with slim.arg_scope(
[slim.conv2d],
weights_initializer=tf.truncated_normal_initializer(
stddev=stddev),
activation_fn=tf.nn.relu,
normalizer_fn=None, #slim.batch_norm,
normalizer_params=None, #batch_norm_params
):
net, end_points = vgg_19(images, scope=scope)
# Add summaries.
if add_summaries:
for v in end_points.values():
tf.contrib.layers.summaries.summarize_activation(v)
return end_points['vgg_19/vgg_19/conv5/conv5_3']
