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 Setup(self):
image_pre = vgg_preprocessing.preprocess_image(self.image,
self.image_size,
self.image_size,
is_training=False)
self.image_4d = tf.expand_dims(image_pre, 0)
# net forward
with slim.arg_scope(vgg.vgg_arg_scope()):
# 1000 classes instead of 1001.
_, _ = vgg.vgg_16(self.image_4d,
num_classes=1000,
is_training=False)
self.log("Model loading...")
self.init_fn = slim.assign_from_checkpoint_fn(
VGG16_CKPT, slim.get_model_variables('vgg_16'))
# net output
self.fc7 = tf.get_default_graph().get_tensor_by_name(
"vgg_16/fc7/Relu:0")
self.sess = tf.Session()
# variables need to be initialized before any sess.run() calls
self.init_fn(self.sess)
self.log("Restored model")
def eval(x, num_classes=110):
with slim.arg_scope(inception.inception_v1_arg_scope()):
logits_inc_v1, end_points_inc_v1 = inception.inception_v1(
x, num_classes=num_classes, is_training=False, scope='InceptionV1')
pred1 = tf.argmax(end_points_inc_v1['Predictions'], 1)
# rescale pixle range from [-1, 1] to [0, 255] for resnet_v1 and vgg's input
image = (((x + 1.0) * 0.5) * 255.0)
processed_imgs_res_v1_50 = preprocess_for_model(image, 'resnet_v1_50')
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
logits_res_v1_50, end_points_res_v1_50 = resnet_v1.resnet_v1_50(
processed_imgs_res_v1_50,
num_classes=num_classes,
is_training=False,
scope='resnet_v1_50')
end_points_res_v1_50['logits'] = tf.squeeze(
end_points_res_v1_50['resnet_v1_50/logits'], [1, 2])
end_points_res_v1_50['probs'] = tf.nn.softmax(
end_points_res_v1_50['logits'])
pred2 = tf.argmax(end_points_res_v1_50['probs'], 1)
# image = (((x + 1.0) * 0.5) * 255.0)#.astype(np.uint8)
processed_imgs_vgg_16 = preprocess_for_model(image, 'vgg_16')
with slim.arg_scope(vgg.vgg_arg_scope()):
logits_vgg_16, end_points_vgg_16 = vgg.vgg_16(processed_imgs_vgg_16,
num_classes=num_classes,
is_training=False,
scope='vgg_16')
end_points_vgg_16['logits'] = end_points_vgg_16['vgg_16/fc8']
end_points_vgg_16['probs'] = tf.nn.softmax(end_points_vgg_16['logits'])
pred3 = tf.argmax(end_points_vgg_16['probs'], 1)
return [pred1, pred2, pred3]
def testEndPoints(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
for is_training in [True, False]:
with tf.Graph().as_default():
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = vgg.vgg_16(inputs, num_classes, is_training=is_training)
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 __init__(self):
self.num_classes = 200
IMAGE_SIZE = 224
train_log_dir = 'cnn_model/vgg_16_2016_08_28/slim_fine_tune'
feature_vecs = np.load('cnn_model/vgg_feature_vecs.npz')
# 将训练集作为 检索库
self.feature_vecs_database = self.normalize(feature_vecs['train'])
assert (tf.gfile.Exists(train_log_dir) == True)
self.image_holder = tf.placeholder(tf.float32, [None, IMAGE_SIZE, IMAGE_SIZE, 3])
self.is_training = tf.placeholder(dtype=tf.bool)
# 创建vgg16网络 如果想冻结所有层，可以指定slim.conv2d中的 trainable=False
_, self.end_points = vgg.vgg_16(self.image_holder, is_training=self.is_training, num_classes=self.num_classes)
# 用于保存检查点文件
save = tf.train.Saver()
# 恢复模型
self.sess = tf.Session()
self.sess.run(tf.global_variables_initializer())
# 检查最近的检查点文件
ckpt = tf.train.latest_checkpoint(train_log_dir)
if ckpt != None:
save.restore(self.sess, ckpt)
print('加载上次训练保存后的模型！')
else:
assert (False)
def graph(x, y, i, x_max, x_min, grad, vgg_y):
eps = FLAGS.max_epsilon
num_iter = FLAGS.num_iter
alpha = eps / num_iter
momentum = FLAGS.momentum
one_hot_vgg = tf.one_hot(vgg_y, 1000)
x_div = input_diversity(x)
with slim.arg_scope(vgg.vgg_arg_scope()):
logits, end_points = vgg.vgg_16(x_div,
num_classes=1001,
is_training=False)
cross_entropy = tf.losses.softmax_cross_entropy(one_hot_vgg, logits)
noise = tf.gradients(cross_entropy, x)[0]
noise = noise / tf.reduce_mean(tf.abs(noise), [1, 2, 3], keep_dims=True)
noise = momentum * grad + noise
x = x + alpha * tf.sign(noise)
x = tf.clip_by_value(x, x_min, x_max)
i = tf.add(i, 1)
return x, y, i, x_max, x_min, noise, vgg_y
def build_model(inputs, style, learning_rate, content_loss_weight,
style_loss_weight):
with slim.arg_scope(transfer_arg_scope()):
trans, var = transfer_net(inputs - MEAN_VALUES, reuse=False)
inputs = tf.concat([trans, inputs, style], axis=0)
_, end_points = vgg.vgg_16(inputs - MEAN_VALUES, spatial_squeeze=False)
f1 = end_points["vgg_16/conv1/conv1_2"]
f2 = end_points["vgg_16/conv2/conv2_2"]
f3 = end_points["vgg_16/conv3/conv3_3"]
f4 = end_points["vgg_16/conv4/conv4_3"]
trans_f3, inputs_f3, _ = tf.split(f3, 3, 0)
content_loss = tf.nn.l2_loss(trans_f3 - inputs_f3) / tf.to_float(
tf.size(trans_f3))
content_loss = content_loss_weight * content_loss
style_loss = style_loss_weight * styleloss(f1, f2, f3, f4)
total_loss = content_loss + style_loss
optimizer = tf.train.AdamOptimizer(learning_rate).minimize(total_loss,
var_list=var)
return optimizer, trans, total_loss, content_loss, style_loss
def non_target_graph(x, y, i, x_max, x_min, grad):
eps = 2.0 * max_epsilon / 255.0
alpha = eps / num_iter
num_classes = 110
with slim.arg_scope(inception.inception_v1_arg_scope()):
logits_inc_v1, end_points_inc_v1 = inception.inception_v1(
x, num_classes=num_classes, is_training=False, scope='InceptionV1')
# rescale pixle range from [-1, 1] to [0, 255] for resnet_v1 and vgg's input
image = (((x + 1.0) * 0.5) * 255.0)
processed_imgs_res_v1_50 = preprocess_for_model(image, 'resnet_v1_50')
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
logits_res_v1_50, end_points_res_v1_50 = resnet_v1.resnet_v1_50(
processed_imgs_res_v1_50,
num_classes=num_classes,
is_training=False,
scope='resnet_v1_50')
end_points_res_v1_50['logits'] = tf.squeeze(
end_points_res_v1_50['resnet_v1_50/logits'], [1, 2])
end_points_res_v1_50['probs'] = tf.nn.softmax(
end_points_res_v1_50['logits'])
# image = (((x + 1.0) * 0.5) * 255.0)#.astype(np.uint8)
processed_imgs_vgg_16 = preprocess_for_model(image, 'vgg_16')
with slim.arg_scope(vgg.vgg_arg_scope()):
logits_vgg_16, end_points_vgg_16 = vgg.vgg_16(processed_imgs_vgg_16,
num_classes=num_classes,
is_training=False,
scope='vgg_16')
end_points_vgg_16['logits'] = end_points_vgg_16['vgg_16/fc8']
end_points_vgg_16['probs'] = tf.nn.softmax(end_points_vgg_16['logits'])
########################
# Using model predictions as ground truth to avoid label leaking
pred = tf.argmax(
end_points_inc_v1['Predictions'] + end_points_res_v1_50['probs'] +
end_points_vgg_16['probs'], 1)
first_round = tf.cast(tf.equal(i, 0), tf.int64)
y = first_round * pred + (1 - first_round) * y
one_hot = tf.one_hot(y, num_classes)
########################
logits = (end_points_inc_v1['Logits'] + end_points_res_v1_50['logits']
+ end_points_vgg_16['logits']) / 3.0
cross_entropy = tf.losses.softmax_cross_entropy(one_hot,
logits,
label_smoothing=0.0,
weights=1.0)
noise = tf.gradients(cross_entropy, x)[0]
noise = noise / tf.reduce_mean(tf.abs(noise), [1, 2, 3],
keep_dims=True)
noise = momentum * grad + noise
x = x + alpha * tf.sign(noise)
x = tf.clip_by_value(x, x_min, x_max)
i = tf.add(i, 1)
return x, y, i, x_max, x_min, noise
def target_graph(x, y, i, x_max, x_min, grad):
eps = 2.0 * max_epsilon / 255.0
alpha = eps / num_iter
num_classes = 110
#input image size[224,224,3]
images3 = tf.image.resize_bilinear(input_diversity(x), [224, 224], align_corners=False)
with slim.arg_scope(inception.inception_v1_arg_scope()):
logits_inc_v1, end_points_inc_v1 = inception.inception_v1(
images3, num_classes=num_classes, is_training=False, scope='InceptionV1')
# rescale pixle range from [-1, 1] to [0, 255] for resnet_v1 and vgg's input
image1 = (((input_diversity(x) + 1.0) * 0.5) * 255.0)
processed_imgs_res_v1_50 = preprocess_for_model(image1, 'resnet_v1_50')
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
logits_res_v1_50, end_points_res_v1_50 = resnet_v1.resnet_v1_50(
processed_imgs_res_v1_50, num_classes=num_classes, is_training=False, scope='resnet_v1_50')
end_points_res_v1_50['logits'] = tf.squeeze(end_points_res_v1_50['resnet_v1_50/logits'], [1, 2])
end_points_res_v1_50['probs'] = tf.nn.softmax(end_points_res_v1_50['logits'])
# image = (((x + 1.0) * 0.5) * 255.0)#.astype(np.uint8)
image2 = (((input_diversity(x) + 1.0) * 0.5) * 255.0)
processed_imgs_vgg_16 = preprocess_for_model(image2, 'vgg_16')
with slim.arg_scope(vgg.vgg_arg_scope()):
logits_vgg_16, end_points_vgg_16 = vgg.vgg_16(
processed_imgs_vgg_16, num_classes=num_classes, is_training=False, scope='vgg_16')
end_points_vgg_16['logits'] = end_points_vgg_16['vgg_16/fc8']
end_points_vgg_16['probs'] = tf.nn.softmax(end_points_vgg_16['logits'])
one_hot = tf.one_hot(y, num_classes)
logits = (end_points_inc_v1['Logits'] + end_points_res_v1_50['logits'] + end_points_vgg_16['logits']) / 3.0
cross_entropy = tf.losses.softmax_cross_entropy(one_hot,
logits,
label_smoothing=0.0,
weights=1.0)
noise = tf.gradients(cross_entropy, x)[0]
noise = tf.nn.depthwise_conv2d(noise, stack_kernel, strides=[1, 1, 1, 1], padding='SAME')
noise = noise / tf.reshape(tf.contrib.keras.backend.std(tf.reshape(noise, [batch_size, -1]), axis=1),
[batch_size, 1, 1, 1])
noise = momentum * grad + noise
noise = noise / tf.reshape(tf.contrib.keras.backend.std(tf.reshape(noise, [batch_size, -1]), axis=1),
[batch_size, 1, 1, 1])
noise1 = tf.image.resize_images(noise, [140, 140], method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
print("noise shape:", noise.shape)
noise1 = alpha * tf.clip_by_value(tf.round(noise1), -2, 2)
noise_paded = tf.pad(noise1,[[0, 0], [42, 42], [42, 42], [0, 0]], constant_values=0.)
x = x - noise_paded
x = tf.clip_by_value(x, x_min, x_max)
print("x.shape:", x.shape)
i = tf.add(i, 1)
return x, y, i, x_max, x_min, noise
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.initialize_all_variables())
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 = tf.random_uniform((batch_size, height, width, 3))
logits, _ = vgg.vgg_16(inputs)
sess.run(tf.initialize_all_variables())
output = sess.run(logits)
self.assertTrue(output.any())
def target_graph(x, y, i, x_max, x_min, grad):
eps = 2.0 * max_epsilon / 255.0
alpha = eps / num_iter
num_classes = 110
with slim.arg_scope(inception.inception_v1_arg_scope()):
logits_inc_v1, end_points_inc_v1 = inception.inception_v1(
x, num_classes=num_classes, is_training=False, scope='InceptionV1')
# rescale pixle range from [-1, 1] to [0, 255] for resnet_v1 and vgg's input
image = (((x + 1.0) * 0.5) * 255.0)
processed_imgs_res_v1_50 = preprocess_for_model(image, 'resnet_v1_50')
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
logits_res_v1_50, end_points_res_v1_50 = resnet_v1.resnet_v1_50(
processed_imgs_res_v1_50,
num_classes=num_classes,
is_training=False,
scope='resnet_v1_50')
end_points_res_v1_50['logits'] = tf.squeeze(
end_points_res_v1_50['resnet_v1_50/logits'], [1, 2])
end_points_res_v1_50['probs'] = tf.nn.softmax(
end_points_res_v1_50['logits'])
# image = (((x + 1.0) * 0.5) * 255.0)#.astype(np.uint8)
processed_imgs_vgg_16 = preprocess_for_model(image, 'vgg_16')
with slim.arg_scope(vgg.vgg_arg_scope()):
logits_vgg_16, end_points_vgg_16 = vgg.vgg_16(processed_imgs_vgg_16,
num_classes=num_classes,
is_training=False,
scope='vgg_16')
end_points_vgg_16['logits'] = end_points_vgg_16['vgg_16/fc8']
end_points_vgg_16['probs'] = tf.nn.softmax(end_points_vgg_16['logits'])
########################
one_hot = tf.one_hot(y, num_classes)
########################
logits = (end_points_inc_v1['Logits'] + end_points_res_v1_50['logits'] +
end_points_vgg_16['logits']) / 3.0
cross_entropy = tf.losses.softmax_cross_entropy(one_hot,
logits,
label_smoothing=0.0,
weights=1.0)
noise = tf.gradients(cross_entropy, x)[0]
noise = noise / tf.reshape(
tf.contrib.keras.backend.std(tf.reshape(noise, [batch_size, -1]),
axis=1), [batch_size, 1, 1, 1])
noise = momentum * grad + noise
noise = noise / tf.reshape(
tf.contrib.keras.backend.std(tf.reshape(noise, [batch_size, -1]),
axis=1), [batch_size, 1, 1, 1])
x = x - alpha * tf.clip_by_value(tf.round(noise), -2, 2)
x = tf.clip_by_value(x, x_min, x_max)
i = tf.add(i, 1)
return x, y, i, x_max, x_min, noise
def test_imagenet_vgg16(self):
tf.get_logger().setLevel('ERROR')
session = tf.compat.v1.InteractiveSession(graph=tf.Graph())
input = tf.compat.v1.placeholder(tf.float32, shape=(None, 224, 224, 3))
with warnings.catch_warnings():
warnings.simplefilter('ignore', category=DeprecationWarning)
logits, _ = vgg.vgg_16(input, is_training=False)
restorer = tf.compat.v1.train.Saver()
restorer.restore(
session,
utils.python_file_dir(__file__) +
'/models/tensorflow_vgg_16/vgg_16.ckpt')
mean = (123.68, 116.78, 103.94)
std = (1, 1, 1)
data_preprocess = self.ImageNetValData(224,
224,
'vgg16',
transform=lambda x:
(x - mean) / std,
label_offset=0)
data_original = self.ImageNetValData(224,
224,
'vgg16',
transform=None,
label_offset=0)
bounds = (0, 255)
measure_model = TensorFlowModel(session, logits, input)
accuracy = Accuracy()
measure_model.predict(data_preprocess.x, data_preprocess.y,
[accuracy.update, accuracy.report])
neuron_coverage = NeuronCoverage()
measure_model.intermediate_layer_outputs(
data_preprocess.x,
[neuron_coverage.update, neuron_coverage.report])
robustness = Robustness(bounds)
measure_model.adversarial_samples(
data_original.x,
data_original.y,
3,
bounds, [
robustness.update, robustness.report,
utils.draw_adversarial_samples
],
batch_size=1,
preprocessing=(mean, std))
session.close()
self.assertAlmostEqual(accuracy.get(1), 0.600000)
self.assertAlmostEqual(accuracy.get(5), 0.925000)
self.assertAlmostEqual(neuron_coverage.get(0.3), 0.630143, places=2)
self.assertAlmostEqual(robustness.success_rate, 1.000000)
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 build_single_vggnet(train_tfdata, is_train, dropout_keep_prob):
if not FLAGS.is_train or FLAGS.debug_test:
is_train = False
with slim.arg_scope(vgg.vgg_arg_scope()):
identity, end_points = vgg.vgg_16(train_tfdata, num_classes=FLAGS.num_class, is_training=is_train, dropout_keep_prob = dropout_keep_prob)
# identity, end_points = vgg.vgg_19(train_tfdata, num_classes=FLAGS.num_class, is_training=is_train, dropout_keep_prob = dropout_keep_prob)
for key in end_points.keys():
if 'fc7' in key:
feature = tf.squeeze(end_points[key], [1, 2])
return identity, feature
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 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 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 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 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 test_batch():
with tf.Graph().as_default():
tra_image_batch, tra_label_batch = get_batch(img_batch_list, lab_batch_list)
logits, _ = vgg.vgg_16(tra_image_batch, num_classes=5, is_training=False)
# logits, _ = vgg.vgg_16(tra_image_batch, num_classes=5, is_training=False)
loss = slim.losses.softmax_cross_entropy(logits, tra_label_batch)
accuracy = tools.accuracy(logits, tra_label_batch)
saver = tf.train.Saver()
with tf.Session() as sess:
print("Reading checkpoints...")
ckpt = tf.train.get_checkpoint_state(model_dir)
if ckpt and ckpt.model_checkpoint_path:
global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
saver.restore(sess, ckpt.model_checkpoint_path)
print('Loading success, global_step is %s' % global_step)
else:
print('No checkpoint file found')
return
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
try:
print('\nEvaluating......')
num_step = int(math.floor(408 / 32))
num_sample = num_step * 32
step = 0
total_correct = 0
total_loss = 0
while step < num_step and not coord.should_stop():
batch_accuracy = sess.run(accuracy)
batch_loss = sess.run(loss)
total_correct += np.sum(batch_accuracy)
total_loss += np.sum(batch_loss)
step += 1
print(batch_accuracy)
print(batch_loss)
print('Total testing samples: %d' % num_sample)
print('Average accuracy: %.2f%%' % ( total_correct / step))
print('Average loss: %2.f' % (total_loss / step))
except Exception as e:
coord.request_stop(e)
finally:
coord.request_stop()
coord.join(threads)
def __init__(self, inputs, true_labels, is_train=False, num_classes=None):
self.true_labels = true_labels
self.NUM_CLASSES = num_classes
with slim.arg_scope(vgg.vgg_arg_scope()):
self.output, self.features = vgg.vgg_16(inputs=inputs,
num_classes=1000,
is_training=False)
self.classifier, _ = cnn.fc(input=self.extract_features('fc7'),
num_outputs=self.NUM_CLASSES,
use_relu=False,
name='classifier')
def forward(self, input_tensor, is_training):
dropout_value = 0.5
# input_tensor = tf.image.resize_images(input_tensor, [224, 224])
batch_size = tf.shape(input_tensor)[0]
print("Is training:", is_training)
with slim.arg_scope(vgg.vgg_arg_scope()):
h, end_points = vgg.vgg_16(input_tensor, is_training=is_training)
print(end_points)
print(list(end_points.keys()))
h = end_points['vgg_16/pool4']
h = L.convolution2d_transpose(h, 256, [5, 5], [2, 2], activation_fn=None)
h = tf.nn.relu(h)
h = tf.concat([h, end_points['vgg_16/pool3']], axis=3)
h = L.dropout(h, keep_prob=dropout_value, is_training=is_training)
np_seed_mask = np.zeros((1, 56, 56, 1))
np_seed_mask[:, 28:29, 28:29, :] = 1.0
seed_mask = tf.constant(np_seed_mask, dtype=tf.float32)
seed_mask = tf.tile(seed_mask, [batch_size, 1, 1, 1])
h = L.convolution2d_transpose(h, 128, [5, 5], [2, 2], activation_fn=None)
h = tf.nn.relu(h)
h = tf.concat([h, end_points['vgg_16/pool2'], seed_mask], axis=3)
h = L.dropout(h, keep_prob=dropout_value, is_training=is_training)
h = L.convolution2d_transpose(h, 64, [5, 5], [2, 2], activation_fn=None)
h = tf.nn.relu(h)
h = tf.concat([h, end_points['vgg_16/pool1']], axis=3)
h = L.dropout(h, keep_prob=dropout_value, is_training=is_training)
h = L.convolution2d_transpose(h, 64, [5, 5], [2, 2], activation_fn=None)
h = tf.concat([h, input_tensor], axis=3)
h = tf.nn.relu(h)
h = L.dropout(h, keep_prob=dropout_value, is_training=is_training)
# h = L.convolution2d_transpose(h, 64, [5, 5], [2, 2], activation_fn=None)
# h = tf.nn.relu(h)
# h = L.dropout(h, keep_prob=dropout_value, is_training=is_training)
# h = L.convolution2d_transpose(h, 64, [5, 5], [2, 2], activation_fn=None)
# h = tf.nn.relu(h)
# h = L.dropout(h, keep_prob=dropout_value, is_training=is_training)
h = L.convolution2d(h, len(self.classes) + 1, [1, 1], [1, 1], activation_fn=None)
return h
def build_single_vggnet(train_tfdata, is_train, dropout_keep_prob):
if not FLAGS.is_train or FLAGS.debug_test:
is_train = False
with slim.arg_scope(vgg.vgg_arg_scope()):
identity, end_points = vgg.vgg_16(train_tfdata,
num_classes=FLAGS.num_class,
is_training=is_train,
dropout_keep_prob=dropout_keep_prob)
# identity, end_points = vgg.vgg_19(train_tfdata, num_classes=FLAGS.num_class, is_training=is_train, dropout_keep_prob = dropout_keep_prob)
for key in end_points.keys():
if 'fc7' in key:
feature = tf.squeeze(end_points[key], [1, 2])
return identity, feature
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 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 __call__(self, x_input, return_logits=False):
"""Constructs model and return probabilities for given input."""
reuse = True if self.built else None
with slim.arg_scope(vgg.vgg_arg_scope()):
_, end_points = vgg.vgg_16(
x_input, num_classes=self.nb_classes, is_training=False)
self.built = True
self.logits = tf.squeeze(end_points['vgg_16/fc8'])
# Strip off the extra reshape op at the output
self.probs = tf.nn.softmax(end_points['vgg_16/fc8'])
if return_logits:
return self.logits
else:
return self.probs
def __call__(self, ens_x_input, vgg_x_input, inc_x_input, tcd_x_input):
"""Constructs model and return probabilities for given input."""
reuse = True if self.built else None
logits = None
aux_logits = None
weights = [[0.7, 0.1], [0.2, 0.1]]
all_inputs = [[ens_x_input, tcd_x_input], [inc_x_input, tcd_x_input]]
scopes = [
inception_resnet_v2.inception_resnet_v2_arg_scope(),
inception.inception_v3_arg_scope()
]
reuse_flags = [reuse, True]
for model_idx, model in enumerate(
[inception_resnet_v2.inception_resnet_v2, inception.inception_v3]):
with slim.arg_scope(scopes[model_idx]):
for idx, inputs in enumerate(all_inputs[model_idx]):
result = model(inputs,
num_classes=self.num_classes,
is_training=False,
reuse=reuse_flags[idx])
weight = weights[model_idx][idx]
# :1 is for slicing out the background class
if logits == None:
logits = result[0][:, 1:] * weight
aux_logits = result[1]['AuxLogits'][:, 1:] * weight
else:
logits += result[0][:, 1:] * weight
aux_logits += result[1]['AuxLogits'][:, 1:] * weight
with slim.arg_scope(vgg.vgg_arg_scope()):
weight = 0.1
result = vgg.vgg_16(vgg_x_input,
num_classes=1000,
is_training=False)
logits += result[0] * weight
with slim.arg_scope(resnet_utils.resnet_arg_scope()):
weight = 0.05
result = resnet_v2.resnet_v2_152(vgg_x_input,
num_classes=self.num_classes,
reuse=reuse)
logits += tf.squeeze(result[0])[:, 1:] * weight
self.built = True
aux_weight = 0.8
logits += aux_logits * aux_weight
predictions = layers_lib.softmax(logits)
return predictions
def main():
with tf.gfile.FastGFile('output_graph.pb', 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
tf.import_graph_def(graph_def, name='')
with tf.Graph().as_default() as graph:
inputs = tf.placeholder(dtype=tf.float32, shape=[1, 224, 224, 3])
with slim.arg_scope(vgg.vgg_arg_scope()):
_, end_points = vgg.vgg_16(inputs,
num_classes=1000,
is_training=True,
dropout_keep_prob=0.5,
spatial_squeeze=False,
scope='vgg_16')
stats_graph(graph)
def Deeplab_v1(inputs, num_classes):
'''A TensorFlow implementation of Deeplab_v1 model based on
http://liangchiehchen.com/projects/DeepLab-LargeFOV.html
Args:
inputs: A 4-D tensor with dimensions [batch_size, height, width, channels]
num_classes: Integer, the total number of categories in the dataset
Returns:
A score map with dimensions [batch_size, 1/8*height, 1/8*width, num_classes]
'''
with slim.arg_scope(vgg.vgg_arg_scope()):
_, end_points = vgg.vgg_16(inputs,
num_classes=1000,
is_training=True,
dropout_keep_prob=0.5,
spatial_squeeze=False,
scope='vgg_16')
conv4 = end_points["vgg_16/conv4/conv4_3"] # 1/8H * 1/8 * 256
with tf.variable_scope('Deeplab_v1'):
pool4 = slim.max_pool2d(conv4, [3, 3],
stride=1,
padding='SAME',
scope='pool4')
conv5_1 = slim.conv2d(pool4, 512, [3, 3], rate=2, scope='conv5_1')
conv5_2 = slim.conv2d(conv5_1, 512, [3, 3], rate=2, scope='conv5_2')
conv5_3 = slim.conv2d(conv5_2, 512, [3, 3], rate=2, scope='conv5_3')
pool5_1 = slim.max_pool2d(conv5_3, [3, 3],
stride=1,
padding='SAME',
scope='pool5_1')
pool5_2 = slim.avg_pool2d(pool5_1, [3, 3],
stride=1,
padding='SAME',
scope='pool5_2')
conv6 = slim.conv2d(pool5_2, 1024, [3, 3], rate=12, scope='conv6')
dropout1 = slim.dropout(conv6, keep_prob=0.5)
conv7 = slim.conv2d(dropout1, 1024, [1, 1], scope='conv7')
dropout2 = slim.dropout(conv7, keep_prob=0.5)
logits = slim.conv2d(dropout2,
num_classes, [1, 1],
activation_fn=None,
scope='logits')
return logits
def get_predicted_y(x, num_classes, args):
"""Calculate predicted label"""
slim = tf.contrib.slim
with slim.arg_scope(inception.inception_v1_arg_scope()):
logits_inc_v1, end_points_inc_v1 = inception.inception_v1(
dimension_224(x),
num_classes=num_classes,
is_training=False,
scope='InceptionV1')
image = (((x + 1.0) * 0.5) * 255.0)
processed_imgs_res_v1_50 = preprocess_for_model(image, 'resnet_v1_50')
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
logits_res_v1_50, end_points_res_v1_50 = resnet_v1.resnet_v1_50(
dimension_224(processed_imgs_res_v1_50),
num_classes=num_classes,
is_training=False,
scope='resnet_v1_50')
end_points_res_v1_50['logits'] = tf.squeeze(
end_points_res_v1_50['resnet_v1_50/logits'], [1, 2])
end_points_res_v1_50['probs'] = tf.nn.softmax(
end_points_res_v1_50['logits'])
processed_imgs_vgg_16 = preprocess_for_model(image, 'vgg_16')
with slim.arg_scope(vgg.vgg_arg_scope()):
logits_vgg_16, end_points_vgg_16 = vgg.vgg_16(
dimension_224(processed_imgs_vgg_16),
num_classes=num_classes,
is_training=False,
scope='vgg_16')
end_points_vgg_16['logits'] = end_points_vgg_16['vgg_16/fc8']
end_points_vgg_16['probs'] = tf.nn.softmax(end_points_vgg_16['logits'])
logits = [None] * args.num_model
pred_y = [None] * args.num_model
logits[0] = end_points_inc_v1['Logits']
logits[1] = end_points_res_v1_50['logits']
logits[2] = end_points_vgg_16['logits']
for i in range(args.num_model):
pred_y[i] = tf.argmax(tf.nn.softmax(logits[i]), 1)
return pred_y, logits
def ens_model(x):
#input remains in[0,1]
image = (x * 255.0)
num_classes = 110
processed_incv1 = preprocess_for_model(image, 'inception_v1')
with slim.arg_scope(inception.inception_v1_arg_scope()):
logits_inc_v1, end_points_inc_v1 = inception.inception_v1(
processed_incv1,
num_classes=num_classes,
is_training=False,
scope='InceptionV1')
processed_imgs_res_v1_50 = preprocess_for_model(image, 'resnet_v1_50')
with slim.arg_scope(resnet_v1.resnet_arg_scope()):
logits_res_v1_50, end_points_res_v1_50 = resnet_v1.resnet_v1_50(
processed_imgs_res_v1_50,
num_classes=num_classes,
is_training=False,
scope='resnet_v1_50')
end_points_res_v1_50['logits'] = tf.squeeze(
end_points_res_v1_50['resnet_v1_50/logits'], [1, 2])
end_points_res_v1_50['probs'] = tf.nn.softmax(
end_points_res_v1_50['logits'])
# image = (((x + 1.0) * 0.5) * 255.0)#.astype(np.uint8)
processed_imgs_vgg_16 = preprocess_for_model(image, 'vgg_16')
with slim.arg_scope(vgg.vgg_arg_scope()):
logits_vgg_16, end_points_vgg_16 = vgg.vgg_16(processed_imgs_vgg_16,
num_classes=num_classes,
is_training=False,
scope='vgg_16')
end_points_vgg_16['logits'] = end_points_vgg_16['vgg_16/fc8']
end_points_vgg_16['probs'] = tf.nn.softmax(end_points_vgg_16['logits'])
########################
#one_hot = tf.one_hot(y, num_classes)
########################
logits = (end_points_inc_v1['Logits'] + end_points_res_v1_50['logits'] +
end_points_vgg_16['logits']) / 3.0
print('logits.shape:', logits.shape)
return logits
def build_encoder(self):
_inputs = tf.reshape(self.x, [-1] + self.image_shape)
_net = vgg.vgg_16(_inputs)
_layers = _net[1]
del _layers['vgg_16/fc8'] # the last layer (ie softmax)
_encoding = _layers['vgg_16/fc7'] # the layer before the softmax
_encoding = _encoding[:, 0, 0, :]
_shape = _encoding.get_shape()[-1].value
_encoding = tf.reshape(_encoding, [self.batch_size, -1, _shape])
_encoding = tf.transpose(
_encoding, [1, 0, 2]) # shape is now [T_MAX, BATCH_SIZE, _shape]
self.encodings = _encoding
def test_vgg(self):
with slim.arg_scope(vgg.vgg_arg_scope()):
net, end_points = vgg.vgg_16(self.inputs,
self.nbclasses,
is_training=False)
net = slim.softmax(net)
saver = tf.train.Saver(tf.global_variables())
check_point = 'test/data/vgg_16.ckpt'
sess = tf.InteractiveSession()
saver.restore(sess, check_point)
self.sess = sess
self.graph_origin = tf.get_default_graph()
self.target_op_name = darkon.Gradcam.candidate_featuremap_op_names(
sess, self.graph_origin)[-2]
self.model_name = 'vgg'
def imageBreak():
imagepath = "../../data/beauty/001/2.jpg"
with tf.Graph().as_default():
image = tf.image.decode_jpeg(tf.read_file(imagepath), channels=3)
image = tf.image.resize_images(image, [224, 224])
#减去均值之前，将像素转为32位浮点数
image_float = tf.to_float(image, name="ToFloat")
#每个像素减去像素的均值
processed_image = _mean_image_subtraction(image_float,
[_R_MEAN, _G_MEAN, _B_MEAN])
input_image = tf.expand_dims(processed_image, 0)
with slim.arg_scope(vgg.vgg_arg_scope()):
logits, endpoints = vgg.vgg_16(inputs=input_image,
num_classes=1000,
is_training=False,
spatial_squeeze=False)
pred = tf.argmax(logits,
dimension=3) #对输出层进行逐个比较，取得不同层同一位置中最大的概率所对应的值
init_fn = slim.assign_from_checkpoint_fn(
os.path.join(configure.Vgg16ModelPath,
configure.Vgg16ModelName),
slim.get_model_variables("vgg_16"))
with tf.Session() as sess:
init_fn(sess)
fcn8s, fcn16s, fcn32s = sess.run([
endpoints["vgg_16/pool3"], endpoints["vgg_16/pool4"],
endpoints["vgg_16/pool5"]
])
upsampled_logits = upsample_tf(factor=16,
input_img=fcn8s.squeeze())
upsampled_predictions32 = upsampled_logits.squeeze().argmax(2)
unique_classes, relabeled_image = np.unique(
upsampled_predictions32, return_inverse=True)
relabeled_image = relabeled_image.reshape(
upsampled_predictions32.shape)
labels_names = []
names = imagenet_classes.class_names
for index, current_class_number in enumerate(unique_classes):
labels_names.append(
str(index) + " " + names[current_class_number + 1])
discrete_matshow(data=relabeled_image,
labels_names=labels_names,
title="Segmentation")
def test_reducing_vgg16_slim(self):
""" Test reducing vgg16 slim model """
tf.compat.v1.reset_default_graph()
sess = tf.compat.v1.Session()
module_zero_channels_list = []
inp = tf.compat.v1.placeholder(tf.float32, [1, 224, 224, 3])
_ = vgg.vgg_16(inp)
init = tf.compat.v1.global_variables_initializer()
sess.run(init)
input_op_names = ["Placeholder"]
output_op_names = ['vgg_16/fc8/squeezed']
tf_op = tf.compat.v1.get_default_graph().get_operation_by_name(
"vgg_16/fc7/Conv2D")
input_channels_to_winnow = [2, 3, 4]
module_mask_pair = (tf_op, input_channels_to_winnow)
module_zero_channels_list.append(module_mask_pair)
new_sess, ordered_modules_list = winnow.winnow_tf_model(
sess,
input_op_names,
output_op_names,
module_zero_channels_list,
reshape=True,
in_place=True,
verbose=True)
# Save and reload modified graph to allow changes to take effect
new_sess = save_and_load_graph('./saver', new_sess)
# _ = tf.compat.v1.summary.FileWriter('./reduced_graph', new_sess.graph)
with new_sess.graph.as_default():
inp = tf.random.uniform(shape=(1, 224, 224, 3))
inp_array = inp.eval(session=new_sess)
model_input = new_sess.graph.get_tensor_by_name("Placeholder:0")
model_output = new_sess.graph.get_tensor_by_name(
"vgg_16/fc8/squeezed:0")
# run through entire model to check no error is produced
_ = new_sess.run(model_output, feed_dict={model_input: inp_array})
self.assertEqual(4, len(ordered_modules_list))
new_sess.close()
sess.close()
