def testNoBatchNormScaleByDefault(self):
height, width = 299, 299
num_classes = 1000
inputs = tf.placeholder(tf.float32, (1, height, width, 3))
with tf.contrib.slim.arg_scope(inception.inception_resnet_v2_arg_scope()):
inception.inception_resnet_v2(inputs, num_classes, is_training=False)
self.assertEqual(tf.global_variables('.*/BatchNorm/gamma:0$'), [])
def testBatchNormScale(self):
height, width = 299, 299
num_classes = 1000
inputs = tf.placeholder(tf.float32, (1, height, width, 3))
with tf.contrib.slim.arg_scope(
inception.inception_resnet_v2_arg_scope(batch_norm_scale=True)):
inception.inception_resnet_v2(inputs, num_classes, is_training=False)
gamma_names = set(
v.op.name for v in tf.global_variables('.*/BatchNorm/gamma:0$'))
self.assertGreater(len(gamma_names), 0)
for v in tf.global_variables('.*/BatchNorm/moving_mean:0$'):
self.assertIn(v.op.name[:-len('moving_mean')] + 'gamma', gamma_names)
def testTrainEvalWithReuse(self):
train_batch_size = 5
eval_batch_size = 2
height, width = 150, 150
num_classes = 1000
with self.test_session() as sess:
train_inputs = tf.random_uniform((train_batch_size, height, width, 3))
inception.inception_resnet_v2(train_inputs, num_classes)
eval_inputs = tf.random_uniform((eval_batch_size, height, width, 3))
logits, _ = inception.inception_resnet_v2(eval_inputs, num_classes, is_training=False, reuse=True)
predictions = tf.argmax(logits, 1)
sess.run(tf.initialize_all_variables())
output = sess.run(predictions)
self.assertEquals(output.shape, (eval_batch_size,))
def testVariablesSetDevice(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
# Force all Variables to reside on the device.
with tf.variable_scope("on_cpu"), tf.device("/cpu:0"):
inception.inception_resnet_v2(inputs, num_classes)
with tf.variable_scope("on_gpu"), tf.device("/gpu:0"):
inception.inception_resnet_v2(inputs, num_classes)
for v in tf.get_collection(tf.GraphKeys.VARIABLES, scope="on_cpu"):
self.assertDeviceEqual(v.device, "/cpu:0")
for v in tf.get_collection(tf.GraphKeys.VARIABLES, scope="on_gpu"):
self.assertDeviceEqual(v.device, "/gpu:0")
def testVariablesSetDevice(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
# Force all Variables to reside on the device.
with tf.variable_scope('on_cpu'), tf.device('/cpu:0'):
inception.inception_resnet_v2(inputs, num_classes)
with tf.variable_scope('on_gpu'), tf.device('/gpu:0'):
inception.inception_resnet_v2(inputs, num_classes)
for v in tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='on_cpu'):
self.assertDeviceEqual(v.device, '/cpu:0')
for v in tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='on_gpu'):
self.assertDeviceEqual(v.device, '/gpu:0')
def evaluate():
"""Eval KAGGLE-128 for a number of steps."""
with tf.Graph().as_default() as g:
# Get images and labels for KAGGLE-128.
eval_data = FLAGS.eval_data
images, labels = kaggle128.inputs(eval_data=eval_data)
# Build a Graph that computes the logits predictions from the
# inference model.
logits, end_points = inception.inception_resnet_v2(
images,
num_classes=kaggle128.NUM_CLASSES,
create_aux_logits=False,
is_training=False)
# Calculate predictions.
top_k_op = tf.nn.in_top_k(logits, labels, 1)
# Restore the moving average version of the learned variables for eval.
variable_averages = tf.train.ExponentialMovingAverage(
kaggle128.MOVING_AVERAGE_DECAY)
variables_to_restore = variable_averages.variables_to_restore()
saver = tf.train.Saver(variables_to_restore)
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
summary_writer = tf.summary.FileWriter(FLAGS.eval_dir, g)
#while True:
eval_once(saver, summary_writer, top_k_op, summary_op)
def __call__(self, x_input, batch_size=None, is_training=False):
"""Constructs model and return probabilities for given input."""
reuse = True if self.built else None
with slim.arg_scope(inception.inception_resnet_v2_arg_scope()):
with tf.variable_scope(self.name):
min_pooled = -tf.nn.max_pool(-x_input,
ksize=[1, 10, 10, 1],
strides=[1, 1, 1, 1],
padding='SAME')
max_pooled = tf.nn.max_pool(x_input,
ksize=[1, 10, 10, 1],
strides=[1, 1, 1, 1],
padding='SAME')
avg_pooled = (min_pooled + max_pooled) / 2
compress_pooled = avg_pooled + (x_input - avg_pooled) * (
tf.sign(max_pooled - min_pooled - 0.3) + 1) / 2
logits, end_points = inception.inception_resnet_v2(
compress_pooled,
num_classes=self.num_classes,
is_training=is_training,
reuse=reuse)
preds = tf.argmax(logits, axis=1)
self.built = True
self.logits = logits
self.preds = preds
return logits
def freeze_model(name):
#checkpoints_dir = '/data/huang/behaviour/data/tfmodel'
OUTPUT_PB_FILENAME = 'inception_resnet_v2_behaviour_371_9_25_{}k.pb'.format(name[0:3])
NUM_CLASSES = 371
tensorName_v4='InceptionResnetV2/Logits/Predictions'
with tf.Graph().as_default():
image_placeholder = tf.placeholder(tf.float32, shape=(1,512,512,3), name='input_image')
with slim.arg_scope(inception.inception_resnet_v2_arg_scope()):
_, probabilities = inception.inception_resnet_v2(image_placeholder,
num_classes = NUM_CLASSES,
is_training=False)
#model_path = tf.train.latest_checkpoint(checkpoints_dir)
model_path = '/data/huang/behaviour/data/tfmodel/model_backup/model.ckpt-{}'.format(name)
init_fn = slim.assign_from_checkpoint_fn(
model_path,
slim.get_model_variables())
with tf.Session() as sess:
# Now call the initialization function within the session
init_fn(sess)
constant_graph = convert_variables_to_constants(sess, sess.graph_def, ["input_image",tensorName_v4])
tf.train.write_graph(constant_graph, '.', OUTPUT_PB_FILENAME, as_text=False)
def classify_from_url(url):
image_string = urllib.urlopen(url).read()
image = tf.image.decode_jpeg(image_string, channels=3)
processed_image = inception_preprocessing.preprocess_image(image, image_size, image_size, is_training=False)
processed_images = tf.expand_dims(processed_image, 0)
# Create the model, use the default arg scope to configure the batch norm parameters.
with slim.arg_scope(inception.inception_resnet_v2_arg_scope()):
logits, _ = inception.inception_resnet_v2(processed_images, num_classes=1001, is_training=False)
probabilities = tf.nn.softmax(logits)
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir, checkpoints_filename),
slim.get_model_variables(model_name))
init_fn(sess)
np_image, probabilities = sess.run([image, probabilities])
probabilities = probabilities[0, 0:]
sorted_inds = [i[0] for i in sorted(enumerate(-probabilities), key=lambda x:x[1])]
plt.figure()
plt.imshow(np_image.astype(np.uint8))
plt.axis('off')
plt.show()
names = imagenet.create_readable_names_for_imagenet_labels()
for i in range(5):
index = sorted_inds[i]
print('Probability %0.2f%% => [%s]' % (probabilities[index], names[index]))
def testTrainEvalWithReuse(self):
train_batch_size = 5
eval_batch_size = 2
height, width = 150, 150
num_classes = 1000
with self.test_session() as sess:
train_inputs = tf.random_uniform((train_batch_size, height, width, 3))
inception.inception_resnet_v2(train_inputs, num_classes)
eval_inputs = tf.random_uniform((eval_batch_size, height, width, 3))
logits, _ = inception.inception_resnet_v2(eval_inputs,
num_classes,
is_training=False,
reuse=True)
predictions = tf.argmax(logits, 1)
sess.run(tf.global_variables_initializer())
output = sess.run(predictions)
self.assertEquals(output.shape, (eval_batch_size,))
def inference(images, keep_prob, is_training):
images = tf.reshape(images,
[-1, IMAGE_HEIGHT, IMAGE_WIDTH, 3]) # 256,256,3
softmax_linear, end_points = inception.inception_resnet_v2(
images, CLASSES_NUM)
# return softmax_linear
return tf.reshape(softmax_linear, [-1, CLASSES_NUM])
def testBuildLogits(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = inception.inception_resnet_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith("InceptionResnetV2/Logits"))
self.assertListEqual(logits.get_shape().as_list(), [batch_size, num_classes])
def testBuildLogits(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = inception.inception_resnet_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionResnetV2/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
def testHalfSizeImages(self):
batch_size = 5
height, width = 150, 150
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, end_points = inception.inception_resnet_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith("InceptionResnetV2/Logits"))
self.assertListEqual(logits.get_shape().as_list(), [batch_size, num_classes])
pre_pool = end_points["PrePool"]
self.assertListEqual(pre_pool.get_shape().as_list(), [batch_size, 3, 3, 1536])
def testEvaluation(self):
batch_size = 2
height, width = 299, 299
num_classes = 1000
with self.test_session() as sess:
eval_inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = inception.inception_resnet_v2(eval_inputs, num_classes, is_training=False)
predictions = tf.argmax(logits, 1)
sess.run(tf.initialize_all_variables())
output = sess.run(predictions)
self.assertEquals(output.shape, (batch_size,))
def testBuildNoClasses(self):
batch_size = 5
height, width = 299, 299
num_classes = None
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
net, endpoints = inception.inception_resnet_v2(inputs, num_classes)
self.assertTrue('AuxLogits' not in endpoints)
self.assertTrue('Logits' not in endpoints)
self.assertTrue(
net.op.name.startswith('InceptionResnetV2/Logits/AvgPool'))
self.assertListEqual(net.get_shape().as_list(), [batch_size, 1, 1, 1536])
def testBuildWithoutAuxLogits(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, endpoints = inception.inception_resnet_v2(inputs, num_classes,
create_aux_logits=False)
self.assertTrue('AuxLogits' not in endpoints)
self.assertTrue(logits.op.name.startswith('InceptionResnetV2/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
def testEvaluation(self):
batch_size = 2
height, width = 299, 299
num_classes = 1000
with self.test_session() as sess:
eval_inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = inception.inception_resnet_v2(eval_inputs,
num_classes,
is_training=False)
predictions = tf.argmax(logits, 1)
sess.run(tf.global_variables_initializer())
output = sess.run(predictions)
self.assertEquals(output.shape, (batch_size, ))
def testUnknownBatchSize(self):
batch_size = 1
height, width = 299, 299
num_classes = 1000
with self.test_session() as sess:
inputs = tf.placeholder(tf.float32, (None, height, width, 3))
logits, _ = inception.inception_resnet_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith("InceptionResnetV2/Logits"))
self.assertListEqual(logits.get_shape().as_list(), [None, num_classes])
images = tf.random_uniform((batch_size, height, width, 3))
sess.run(tf.initialize_all_variables())
output = sess.run(logits, {inputs: images.eval()})
self.assertEquals(output.shape, (batch_size, num_classes))
def testHalfSizeImages(self):
batch_size = 5
height, width = 150, 150
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, end_points = inception.inception_resnet_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionResnetV2/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['PrePool']
self.assertListEqual(pre_pool.get_shape().as_list(),
[batch_size, 3, 3, 1536])
def testGlobalPool(self):
batch_size = 1
height, width = 330, 400
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, end_points = inception.inception_resnet_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionResnetV2/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Conv2d_7b_1x1']
self.assertListEqual(pre_pool.get_shape().as_list(),
[batch_size, 8, 11, 1536])
def testUnknownBatchSize(self):
batch_size = 1
height, width = 299, 299
num_classes = 1000
with self.test_session() as sess:
inputs = tf.placeholder(tf.float32, (None, height, width, 3))
logits, _ = inception.inception_resnet_v2(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionResnetV2/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[None, num_classes])
images = tf.random_uniform((batch_size, height, width, 3))
sess.run(tf.global_variables_initializer())
output = sess.run(logits, {inputs: images.eval()})
self.assertEquals(output.shape, (batch_size, num_classes))
def __call__(self, x_input, batch_size=None, is_training=False):
"""Constructs model and return probabilities for given input."""
reuse = True if self.built else None
with slim.arg_scope(inception.inception_resnet_v2_arg_scope()):
with tf.variable_scope(self.ckpt):
logits, end_points = inception.inception_resnet_v2(
x_input, num_classes=self.num_classes, is_training=is_training,
reuse=reuse)
preds = tf.argmax(logits, axis=1)
self.built = True
self.logits = logits
self.preds = preds
return logits
def inception_resnet_v2(inputs, is_training, opts):
with slim.arg_scope(inception.inception_resnet_v2_arg_scope(
weight_decay=opts.weight_decay,
batch_norm_decay=opts.batch_norm_decay,
batch_norm_epsilon=opts.batch_norm_epsilon,
activation_fn=tf.nn.relu)):
return inception.inception_resnet_v2(
inputs,
num_classes=opts.num_classes,
is_training=is_training,
dropout_keep_prob=opts.dropout_keep_prob,
reuse=None,
create_aux_logits=opts.create_aux_logits,
global_pool=opts.global_pool)
def __call__(self, x_input):
"""Constructs model and return probabilities for given input."""
reuse = True if self.built else None
x_input = image_normalize(x_input, normalization_method[4])
with slim.arg_scope(inception.inception_resnet_v2_arg_scope()):
_, end_points = inception.inception_resnet_v2(
x_input,
num_classes=self.num_classes,
is_training=False,
reuse=reuse)
self.built = True
output = end_points['Predictions']
# Strip off the extra reshape op at the output
probs = output.op.inputs[0]
return output
def testBuildEndPoints(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = inception.inception_resnet_v2(inputs, num_classes)
self.assertTrue("Logits" in end_points)
logits = end_points["Logits"]
self.assertListEqual(logits.get_shape().as_list(), [batch_size, num_classes])
self.assertTrue("AuxLogits" in end_points)
aux_logits = end_points["AuxLogits"]
self.assertListEqual(aux_logits.get_shape().as_list(), [batch_size, num_classes])
pre_pool = end_points["PrePool"]
self.assertListEqual(pre_pool.get_shape().as_list(), [batch_size, 8, 8, 1536])
def testBuildEndPoints(self):
batch_size = 5
height, width = 299, 299
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = inception.inception_resnet_v2(inputs, num_classes)
self.assertTrue('Logits' in end_points)
logits = end_points['Logits']
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertTrue('AuxLogits' in end_points)
aux_logits = end_points['AuxLogits']
self.assertListEqual(aux_logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Conv2d_7b_1x1']
self.assertListEqual(pre_pool.get_shape().as_list(),
[batch_size, 8, 8, 1536])
def testGlobalPoolUnknownImageShape(self):
batch_size = 1
height, width = 330, 400
num_classes = 1000
with self.test_session() as sess:
inputs = tf.placeholder(tf.float32, (batch_size, None, None, 3))
logits, end_points = inception.inception_resnet_v2(
inputs, num_classes, create_aux_logits=False)
self.assertTrue(logits.op.name.startswith('InceptionResnetV2/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Conv2d_7b_1x1']
images = tf.random_uniform((batch_size, height, width, 3))
sess.run(tf.global_variables_initializer())
logits_out, pre_pool_out = sess.run([logits, pre_pool],
{inputs: images.eval()})
self.assertTupleEqual(logits_out.shape, (batch_size, num_classes))
self.assertTupleEqual(pre_pool_out.shape, (batch_size, 8, 11, 1536))
def freeze_model(name):
checkpoints_dir = '/data/huang/behaviour/data/tfmodel'
OUTPUT_PB_FILENAME = 'inception_resnet_v2_behaviour_309_4_10_{}k.pb'.format(
name[0:3])
NUM_CLASSES = 309
tensorName_v4 = 'InceptionResnetV2/Logits/Predictions'
image_size = inception.inception_resnet_v2.default_image_size
with tf.Graph().as_default():
input_image_t = tf.placeholder(tf.string, name='input_image')
image = tf.image.decode_jpeg(input_image_t, channels=3)
processed_image = inception_preprocessing.preprocess_for_eval(
image, image_size, image_size, central_fraction=None)
processed_images = tf.expand_dims(processed_image, 0)
with slim.arg_scope(inception.inception_resnet_v2_arg_scope()):
logits, _ = inception.inception_resnet_v2(processed_images,
num_classes=NUM_CLASSES,
is_training=False)
# Apply softmax function to the logits (output of the last layer of the network)
probabilities = tf.nn.softmax(logits)
#model_path = tf.train.latest_checkpoint(checkpoints_dir)
model_path = '/data/huang/behaviour/data/tfmodel/model_backup/model.ckpt-{}'.format(
name)
init_fn = slim.assign_from_checkpoint_fn(model_path,
slim.get_model_variables())
with tf.Session() as sess:
# Now call the initialization function within the session
init_fn(sess)
constant_graph = convert_variables_to_constants(
sess, sess.graph_def,
["input_image", "DecodeJpeg", tensorName_v4])
tf.train.write_graph(constant_graph,
'.',
OUTPUT_PB_FILENAME,
as_text=False)
def __call__(self, x_input, batch_size=None, is_training=False):
"""Constructs model and return probabilities for given input."""
reuse = True if self.built else None
with slim.arg_scope(inception.inception_resnet_v2_arg_scope()):
with tf.variable_scope(self.name):
avg_pooled = tf.nn.avg_pool(x_input,
ksize=[1, 6, 6, 1],
strides=[1, 1, 1, 1],
padding='SAME')
logits, end_points = inception.inception_resnet_v2(
avg_pooled,
num_classes=self.num_classes,
is_training=is_training,
reuse=reuse)
preds = tf.argmax(logits, axis=1)
self.built = True
self.logits = logits
self.preds = preds
return logits
def evaluate():
"""Eval KAGGLE-128 for a number of steps."""
with tf.Graph().as_default() as g:
# Get images and labels for KAGGLE-128.
eval_data = FLAGS.eval_data
images, labels = kaggle128.inputs(eval_data=eval_data)
# Build a Graph that computes the logits predictions from the
# inference model.
logits, end_points = inception.inception_resnet_v2(images, num_classes=kaggle128.NUM_CLASSES,
create_aux_logits=False,
is_training=False)
# Calculate predictions.
predictions = tf.argmax(logits, 1)
# Restore the moving average version of the learned variables for eval.
variable_averages = tf.train.ExponentialMovingAverage(
kaggle128.MOVING_AVERAGE_DECAY)
variables_to_restore = variable_averages.variables_to_restore()
saver = tf.train.Saver(variables_to_restore)
eval_once(saver, predictions, labels)
def configure_inception_resnet(self):
try:
from nets import inception
from datasets import dataset_utils
except:
import sys
print(
"Make sure you have installed tensorflow/models and it's accessible in the environment"
)
print("export PYTHONPATH=/home/ubuntu/models/slim")
sys.exit()
image_size = inception.inception_resnet_v2.default_image_size
self.crop_generator = deepprofiler.imaging.cropping.SingleImageCropGenerator(
self.config, self.dset)
# Setup pretrained model
network_input = crop_transform(self.raw_crops, image_size)
url = self.config["profiling"]["url"]
checkpoint = self.config["profiling"]["checkpoint"]
if not os.path.isfile(checkpoint):
dataset_utils.download_and_uncompress_tarball(
url, os.path.dirname(checkpoint))
with slim.arg_scope(inception.inception_resnet_v2_arg_scope()):
_, self.endpoints = inception.inception_resnet_v2(
network_input, num_classes=1001, is_training=False)
init_fn = slim.assign_from_checkpoint_fn(checkpoint,
slim.get_model_variables())
# Session configuration
configuration = tf.ConfigProto()
configuration.gpu_options.allow_growth = True
configuration.gpu_options.visible_device_list = self.config[
"profiling"]["gpu"]
self.sess = tf.Session(config=configuration)
init_fn(self.sess)
self.crop_generator.start(self.sess)
def main(_):
batch_shape = [FLAGS.batch_size, FLAGS.image_height, FLAGS.image_width, 3]
num_classes = 1001
ensemble_type = FLAGS.ensemble_type
tf.logging.set_verbosity(tf.logging.INFO)
checkpoint_path_list = [
FLAGS.checkpoint_path_inception_v1, FLAGS.checkpoint_path_inception_v2,
FLAGS.checkpoint_path_inception_v3, FLAGS.checkpoint_path_inception_v4,
FLAGS.checkpoint_path_inception_resnet_v2,
FLAGS.checkpoint_path_resnet_v1_101,
FLAGS.checkpoint_path_resnet_v1_152,
FLAGS.checkpoint_path_resnet_v2_101,
FLAGS.checkpoint_path_resnet_v2_152, FLAGS.checkpoint_path_vgg_16,
FLAGS.checkpoint_path_vgg_19
]
normalization_method = [
'default', 'default', 'default', 'default', 'global', 'caffe_rgb',
'caffe_rgb', 'default', 'default', 'caffe_rgb', 'caffe_rgb'
]
pred_list = []
for idx, checkpoint_path in enumerate(checkpoint_path_list, 1):
with tf.Graph().as_default():
if int(FLAGS.test_idx) == 20 and idx in [3]:
continue
if int(FLAGS.test_idx) in [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11
] and int(FLAGS.test_idx) != idx:
continue
# Prepare graph
if idx in [1, 2, 6, 7, 10, 11]:
_x_input = tf.placeholder(tf.float32, shape=batch_shape)
x_input = tf.image.resize_images(_x_input, [224, 224])
else:
_x_input = tf.placeholder(tf.float32, shape=batch_shape)
x_input = _x_input
x_input = image_normalize(x_input, normalization_method[idx - 1])
if idx == 1:
with slim.arg_scope(inception.inception_v1_arg_scope()):
_, end_points = inception.inception_v1(
x_input, num_classes=num_classes, is_training=False)
elif idx == 2:
with slim.arg_scope(inception.inception_v2_arg_scope()):
_, end_points = inception.inception_v2(
x_input, num_classes=num_classes, is_training=False)
elif idx == 3:
with slim.arg_scope(inception.inception_v3_arg_scope()):
_, end_points = inception.inception_v3(
x_input, num_classes=num_classes, is_training=False)
elif idx == 4:
with slim.arg_scope(inception.inception_v4_arg_scope()):
_, end_points = inception.inception_v4(
x_input, num_classes=num_classes, is_training=False)
elif idx == 5:
with slim.arg_scope(inception.inception_resnet_v2_arg_scope()):
_, end_points = inception.inception_resnet_v2(
x_input, num_classes=num_classes, is_training=False)
elif idx == 6:
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
_, end_points = resnet_v1.resnet_v1_101(x_input,
num_classes=1000,
is_training=False)
elif idx == 7:
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
_, end_points = resnet_v1.resnet_v1_152(x_input,
num_classes=1000,
is_training=False)
elif idx == 8:
with slim.arg_scope(resnet_v2.resnet_arg_scope()):
_, end_points = resnet_v2.resnet_v2_101(
x_input, num_classes=num_classes, is_training=False)
elif idx == 9:
with slim.arg_scope(resnet_v2.resnet_arg_scope()):
_, end_points = resnet_v2.resnet_v2_152(
x_input, num_classes=num_classes, is_training=False)
elif idx == 10:
with slim.arg_scope(vgg.vgg_arg_scope()):
_, end_points = vgg.vgg_16(x_input,
num_classes=1000,
is_training=False)
end_points['predictions'] = tf.nn.softmax(
end_points['vgg_16/fc8'])
elif idx == 11:
with slim.arg_scope(vgg.vgg_arg_scope()):
_, end_points = vgg.vgg_19(x_input,
num_classes=1000,
is_training=False)
end_points['predictions'] = tf.nn.softmax(
end_points['vgg_19/fc8'])
#end_points = tf.reduce_mean([end_points1['Predictions'], end_points2['Predictions'], end_points3['Predictions'], end_points4['Predictions']], axis=0)
#predicted_labels = tf.argmax(end_points, 1)
# Run computation
saver = tf.train.Saver(slim.get_model_variables())
session_creator = tf.train.ChiefSessionCreator(
scaffold=tf.train.Scaffold(saver=saver),
checkpoint_filename_with_path=checkpoint_path,
master=FLAGS.master)
pred_in = []
filenames_list = []
with tf.train.MonitoredSession(
session_creator=session_creator) as sess:
for filenames, images in load_images(FLAGS.input_dir,
batch_shape):
#if idx in [1,2,6,7,10,11]:
# # 16x299x299x3
# images = zoom(images, (1, 0.7491638795986622, 0.7491638795986622, 1), order=2)
filenames_list.extend(filenames)
end_points_dict = sess.run(end_points,
feed_dict={_x_input: images})
if idx in [6, 7, 10, 11]:
end_points_dict['predictions'] = \
np.concatenate([np.zeros([FLAGS.batch_size, 1]),
np.array(end_points_dict['predictions'].reshape(-1, 1000))],
axis=1)
try:
pred_in.extend(end_points_dict['Predictions'].reshape(
-1, num_classes))
except KeyError:
pred_in.extend(end_points_dict['predictions'].reshape(
-1, num_classes))
pred_list.append(pred_in)
if ensemble_type == 'mean':
pred = np.mean(pred_list, axis=0)
labels = np.argmax(
pred, axis=1
) # model_num X batch X class_num ==(np.mean)==> batch X class_num ==(np.argmax)==> batch
elif ensemble_type == 'vote':
pred = np.argmax(
pred_list, axis=2
) # model_num X batch X class_num ==(np.mean)==> batch X class_num ==(np.argmax)==> batch
labels = np.median(pred, axis=0)
with tf.gfile.Open(FLAGS.output_file, 'w') as out_file:
for filename, label in zip(filenames_list, labels):
out_file.write('{0},{1}\n'.format(filename, label))
print(img.shape)
inputs = np.ones((1, 299, 299, 3), dtype=np.float32)
inputs[0, 0, 0, 0] = -1
#inputs[0] = img
print(inputs.mean())
print(inputs.std())
inputs = tf.pack(inputs)
# tensorflow normalization
# https://github.com/tensorflow/models/blob/master/slim/preprocessing/inception_preprocessing.py#L273
#inputs = tf.sub(inputs, 0.5)
#inputs = tf.mul(inputs, 2.0)
with slim.arg_scope(inception.inception_resnet_v2_arg_scope()):
logits, _ = inception.inception_resnet_v2(inputs,
num_classes=1001,
is_training=False)
with tf.Session() as sess:
# Initialize model
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(checkpoints_dir,
'inception_resnet_v2_2016_08_30.ckpt'),
slim.get_model_variables('InceptionResnetV2'))
init_fn(sess)
# Display model variables
for v in slim.get_model_variables():
print('name = {}, shape = {}'.format(v.name, v.get_shape()))
# the network.
# I use the "preprocess_for_eval()" method instead of "inception_preprocessing()"
# because the latter crops all images to the center by 85% at
# prediction time (training=False).
processed_image = inception_preprocessing.preprocess_for_eval(
image, image_size, image_size, central_fraction=None)
# Networks accept images in batches.
# The first dimension usually represents the batch size.
# In our case the batch size is one.
processed_images = tf.expand_dims(processed_image, 0)
# Load the inception network structure
with slim.arg_scope(inception.inception_resnet_v2_arg_scope()):
logits, _ = inception.inception_resnet_v2(processed_images,
num_classes=NUM_CLASSES,
is_training=False)
# Apply softmax function to the logits (output of the last layer of the network)
probabilities = tf.nn.softmax(logits)
model_path = tf.train.latest_checkpoint(checkpoints_dir)
# Get the function that initializes the network structure (its variables) with
# the trained values contained in the checkpoint
init_fn = slim.assign_from_checkpoint_fn(model_path,
slim.get_model_variables())
with tf.Session() as sess:
# Now call the initialization function within the session
init_fn(sess)
def main(_):
batch_shape = [FLAGS.batch_size, FLAGS.image_height, FLAGS.image_width, 3]
num_classes = 1001
# max_epsilon over checking
# get original images
origin_img_list=np.sort(glob.glob(FLAGS.origin_img_dir+"*.png"));
origin_imgs=np.zeros((len(origin_img_list),FLAGS.image_height,FLAGS.image_width,3),dtype=float);
for i in range(len(origin_img_list)):
origin_imgs[i]=imread(origin_img_list[i],mode='RGB').astype(np.float);
# get adv images
adv_img_list=np.sort(glob.glob(FLAGS.input_dir+"*.png"));
adv_imgs=np.zeros((len(adv_img_list),FLAGS.image_height,FLAGS.image_width,3),dtype=float);
for i in range(len(adv_img_list)):
adv_imgs[i]=imread(adv_img_list[i],mode='RGB').astype(np.float);
epsilon_list=np.linalg.norm(np.reshape(abs(origin_imgs-adv_imgs),[-1,FLAGS.image_height*FLAGS.image_width*3]),ord=np.inf,axis=1);
#print(epsilon_list);exit(1);
over_epsilon_list=np.zeros((len(origin_img_list),2),dtype=object);
cnt=0;
for i in range(len(origin_img_list)):
file_name=origin_img_list[i].split("/")[-1];
file_name=file_name.split(".")[0];
over_epsilon_list[i,0]=file_name;
if(epsilon_list[i]>FLAGS.max_epsilon):
over_epsilon_list[i,1]="1";
cnt+=1;
tf.logging.set_verbosity(tf.logging.INFO)
with tf.Graph().as_default():
# Prepare graph
x_input = tf.placeholder(tf.float32, shape=batch_shape)
if(FLAGS.checkpoint_file_name=="inception_v3.ckpt"):
with slim.arg_scope(inception.inception_v3_arg_scope()):
_, end_points = inception.inception_v3(
x_input, num_classes=num_classes, is_training=False)
predicted_labels = tf.argmax(end_points['Predictions'], 1)
elif(FLAGS.checkpoint_file_name=="inception_v4.ckpt"):
with slim.arg_scope(inception.inception_v4_arg_scope()):
_, end_points = inception.inception_v4(
x_input, num_classes=num_classes, is_training=False)
predicted_labels = tf.argmax(end_points['Predictions'], 1)
elif(FLAGS.checkpoint_file_name=="inception_resnet_v2_2016_08_30.ckpt"):
with slim.arg_scope(inception.inception_resnet_v2_arg_scope()):
_, end_points = inception.inception_resnet_v2(
x_input, num_classes=num_classes, is_training=False)
predicted_labels = tf.argmax(end_points['Predictions'], 1)
elif(FLAGS.checkpoint_file_name=="resnet_v2_101.ckpt"):
x_input2 = tf.image.resize_bilinear(x_input,[224,224],align_corners=False);
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points = resnet_v2.resnet_v2_101(
x_input2, num_classes=num_classes, is_training=False)
predicted_labels = tf.argmax(end_points['predictions'], 1)
elif(FLAGS.checkpoint_file_name=="resnet_v2_50.ckpt"):
x_input2 = tf.image.resize_bilinear(x_input,[224,224],align_corners=False);
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points = resnet_v2.resnet_v2_50(
x_input2, num_classes=num_classes, is_training=False)
predicted_labels = tf.argmax(end_points['predictions'], 1)
elif(FLAGS.checkpoint_file_name=="resnet_v2_152.ckpt"):
x_input2 = tf.image.resize_bilinear(x_input,[224,224],align_corners=False);
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points = resnet_v2.resnet_v2_152(
x_input2, num_classes=num_classes, is_training=False)
predicted_labels = tf.argmax(end_points['predictions'], 1)
elif(FLAGS.checkpoint_file_name=="inception_v1.ckpt"):
x_input2 = tf.image.resize_bilinear(x_input,[224,224],align_corners=False);
with slim.arg_scope(inception.inception_v1_arg_scope()):
_, end_points = inception.inception_v1(
x_input2, num_classes=num_classes, is_training=False)
predicted_labels = tf.argmax(end_points['Predictions'], 1)
elif(FLAGS.checkpoint_file_name=="inception_v2.ckpt"):
x_input2 = tf.image.resize_bilinear(x_input,[224,224],align_corners=False);
with slim.arg_scope(inception.inception_v2_arg_scope()):
_, end_points = inception.inception_v2(
x_input2, num_classes=num_classes, is_training=False)
predicted_labels = tf.argmax(end_points['Predictions'], 1)
# Resnet v1 and vgg are not working now
elif(FLAGS.checkpoint_file_name=="vgg_16.ckpt"):
x_input_list=tf.unstack(x_input,FLAGS.batch_size,0);
for i in range(FLAGS.batch_size):
x_input_list[i]=vgg_preprocessing.preprocess_image(x_input_list[i],224,224);
x_input2=tf.stack(x_input_list,0);
with slim.arg_scope(vgg.vgg_arg_scope()):
_, end_points = vgg.vgg_16(
x_input2, num_classes=num_classes-1, is_training=False)
predicted_labels = tf.argmax(end_points['vgg_16/fc8'], 1)+1
elif(FLAGS.checkpoint_file_name=="vgg_19.ckpt"):
x_input_list=tf.unstack(x_input,FLAGS.batch_size,0);
for i in range(FLAGS.batch_size):
x_input_list[i]=vgg_preprocessing.preprocess_image(x_input_list[i],224,224);
x_input2=tf.stack(x_input_list,0);
with slim.arg_scope(vgg.vgg_arg_scope()):
_, end_points = vgg.vgg_19(
x_input2, num_classes=num_classes-1, is_training=False)
predicted_labels = tf.argmax(end_points['vgg_19/fc8'], 1)+1
elif(FLAGS.checkpoint_file_name=="resnet_v1_50.ckpt"):
x_input_list=tf.unstack(x_input,FLAGS.batch_size,0);
for i in range(FLAGS.batch_size):
x_input_list[i]=vgg_preprocessing.preprocess_image(x_input_list[i],224,224);
x_input2=tf.stack(x_input_list,0);
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points = resnet_v1.resnet_v1_50(
x_input, num_classes=num_classes-1, is_training=False)
predicted_labels = tf.argmax(end_points['predictions'], 1)+1
elif(FLAGS.checkpoint_file_name=="resnet_v1_101.ckpt"):
x_input_list=tf.unstack(x_input,FLAGS.batch_size,0);
for i in range(FLAGS.batch_size):
x_input_list[i]=vgg_preprocessing.preprocess_image(x_input_list[i],224,224);
x_input2=tf.stack(x_input_list,0);
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points = resnet_v1.resnet_v1_101(
x_input2, num_classes=num_classes-1, is_training=False)
predicted_labels = tf.argmax(end_points['predictions'], 1)+1
elif(FLAGS.checkpoint_file_name=="resnet_v1_152.ckpt"):
x_input_list=tf.unstack(x_input,FLAGS.batch_size,0);
for i in range(FLAGS.batch_size):
x_input_list[i]=vgg_preprocessing.preprocess_image(x_input_list[i],224,224);
x_input2=tf.stack(x_input_list,0);
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
_, end_points = resnet_v1.resnet_v1_152(
x_input2, num_classes=num_classes-1, is_training=False)
predicted_labels = tf.argmax(end_points['predictions'], 1)+1
# Run computation
saver = tf.train.Saver(slim.get_model_variables())
session_creator = tf.train.ChiefSessionCreator(
scaffold=tf.train.Scaffold(saver=saver),
checkpoint_filename_with_path=FLAGS.checkpoint_path+FLAGS.checkpoint_file_name,
master=FLAGS.master)
f=open(FLAGS.true_label,"r");
t_label_list=np.array([i[:-1].split(",") for i in f.readlines()]);
score=0;
with tf.train.MonitoredSession(session_creator=session_creator) as sess:
with tf.gfile.Open(FLAGS.output_file, 'w') as out_file:
for filenames, images in load_images(FLAGS.input_dir, batch_shape):
labels = sess.run(predicted_labels, feed_dict={x_input: images})
for filename, label in zip(filenames, labels):
f_name=filename.split(".")[0];
t_label=int(t_label_list[t_label_list[:,0]==f_name,1][0]);
if(t_label!=label):
if(over_epsilon_list[over_epsilon_list[:,0]==f_name,1]!="1"):
score+=1;
#out_file.write('{0},{1}\n'.format(filename, label))
print("Over max epsilon#: "+str(cnt));
print(str(FLAGS.max_epsilon)+" max epsilon Score: "+str(score));
# image_placeholder = tf.placeholder(tf.uint8, shape=(None,None,3), name='input_image')
# image_rgb = tf.reverse(image_placeholder, [-1])
# image = tf.image.convert_image_dtype(image_rgb, dtype=tf.float32)
# image = tf.expand_dims(image,0)
# image = tf.image.resize_bilinear(image, [image_size, image_size],
# align_corners=False)
# image = tf.squeeze(image, [0])
# image = tf.subtract(image, 0.5)
# image = tf.multiply(image, 2.0)
# image = tf.expand_dims(image,0)
image_placeholder = tf.placeholder(tf.float32,
shape=(1, 512, 512, 3),
name='input_image')
with slim.arg_scope(inception.inception_resnet_v2_arg_scope()):
_, probabilities = inception.inception_resnet_v2(
image_placeholder, num_classes=NUM_CLASSES, is_training=False)
#model_path = tf.train.latest_checkpoint(checkpoints_dir)
model_path = '/data1/model_backup/2018-9-21-model/ckpt-model/model.ckpt-518732'
# Get the function that initializes the network structure (its variables) with
# the trained values contained in the checkpoint
init_fn = slim.assign_from_checkpoint_fn(model_path,
slim.get_model_variables())
with tf.Session() as sess:
# Now call the initialization function within the session
init_fn(sess)
# Convert variables to constants and make sure the placeholder input_image is included
# in the graph as well as the other neccesary tensors.