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[3])
with slim.arg_scope(inception.inception_v4_arg_scope()):
_, end_points = inception.inception_v4(
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 __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[10])
x_input = tf.image.resize_images(x_input, [224, 224])
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['predictions'] = \
tf.concat([tf.zeros([tf.shape(x_input)[0], 1]),
tf.reshape(end_points['predictions'], [-1, 1000])],
axis=1)
self.built = True
output = end_points['predictions']
return output
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[6])
x_input = tf.image.resize_images(x_input, [224, 224])
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
_, end_points = resnet_v1.resnet_v1_152(
x_input,
num_classes=self.num_classes - 1,
is_training=False,
reuse=reuse)
self.built = True
end_points['predictions'] = \
tf.concat([tf.zeros([tf.shape(x_input)[0], 1]),
tf.reshape(end_points['predictions'], [-1, 1000])],
axis=1)
output = end_points['predictions']
# Strip off the extra reshape op at the output
return output
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))
def main(_):
# Images for inception classifier are normalized to be in [-1, 1] interval,
# eps is a difference between pixels so it should be in [0, 2] interval.
# Renormalizing epsilon from [0, 255] to [0, 2].
batch_shape = [FLAGS.batch_size, FLAGS.image_height, FLAGS.image_width, 3]
num_classes = 1001
total_labels = load_total_labels('images.csv')
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]
tf.logging.set_verbosity(tf.logging.INFO)
graph_list = []
sess_list = []
x_input_list = []
y_list = []
prob_list = []
loss_list = []
x_adv_list = []
type_list = []
for i in range(len(checkpoint_path_list)):
graph = tf.Graph()
with graph.as_default():
x_input_list.append(tf.placeholder(tf.float32, shape=batch_shape))
type_list.append(tf.placeholder(tf.string, shape=[None]))
y_list.append(tf.placeholder(tf.float32, shape=[FLAGS.batch_size, num_classes]))
shift = 0
if i == 0:
model = InceptionV1(num_classes)
scale = 2.0 * FLAGS.max_epsilon / 255.0
if i == 1:
model = InceptionV2(num_classes)
scale = 2.0 * FLAGS.max_epsilon / 255.0
if i == 2:
model = InceptionV3(num_classes)
scale = 2.0 * FLAGS.max_epsilon / 255.0
if i == 3:
model = InceptionV4(num_classes)
scale = 2.0 * FLAGS.max_epsilon / 255.0
if i == 4:
model = InceptionResnetV2(num_classes)
scale = 4.3 * FLAGS.max_epsilon / 255.0
if i == 5:
model = ResnetV1_101(num_classes)
scale = FLAGS.max_epsilon
if i == 6:
model = ResnetV1_152(num_classes)
scale = FLAGS.max_epsilon
if i == 7:
model = ResnetV2_101(num_classes)
scale = 2.0 * FLAGS.max_epsilon / 255.0
if i == 8:
model = ResnetV2_152(num_classes)
scale = 2.0 * FLAGS.max_epsilon / 255.0
if i == 9:
model = Vgg_16(num_classes)
scale = FLAGS.max_epsilon
if i == 10:
model = Vgg_19(num_classes)
scale = FLAGS.max_epsilon
#prob_list.append(model(x_input_list[i]))
input_image = image_normalize(x_input_list[i], normalization_method[i])
fgsm = FastGradientMethod(model)
x_adv = fgsm.generate(input_image, y=y_list[i], scale=scale, shift=shift, clip_min=None, clip_max=None)
x_adv = image_invert(x_adv, normalization_method[i])
x_adv_list.append(x_adv)
#loss_list.append(tf.nn.softmax_cross_entropy_with_logits(labels=y_list[i], logits=prob_list[i]))
graph_list.append(graph)
for i in range(len(checkpoint_path_list)):
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
graph = graph_list[i]
sess_list.append(tf.Session(graph=graph, config=config))
for i in range(len(checkpoint_path_list)):
graph = graph_list[i]
sess = sess_list[i]
with sess.as_default():
with graph.as_default():
model_saver = tf.train.Saver(tf.global_variables())
model_saver.restore(sess, checkpoint_path_list[i])
for filenames, images in load_images(FLAGS.input_dir, batch_shape):
print("make adversarial images [%s]"%filenames[0])
x_fgsm_list = []
for i in xrange(len(checkpoint_path_list)):
graph = graph_list[i]
sess = sess_list[i]
with sess.as_default():
y_labels = load_labels(filenames, total_labels, FLAGS.batch_size)
x_fgsm = sess.run(x_adv_list[i], feed_dict={x_input_list[i]: images, y_list[i]: y_labels})
x_fgsm_list.append(x_fgsm)
#save_images(x_fgsm, filenames, FLAGS.output_dir, i)
x_fgsm_ens = np.mean(x_fgsm_list, axis=0)
save_images(x_fgsm_ens, filenames, FLAGS.output_dir)