def run_benchmark():
with tf.Graph().as_default():
with tf.device('/gpu:0'):
#with tf.device('/cpu:0'):
# Generate some dummy images.
image_size = 224
inputs = tf.Variable(
tf.random_normal([FLAGS.batch_size, image_size, image_size, 3],
dtype=tf.float32,
stddev=1e-1))
with slim.arg_scope(mobilenet_arg_scope()):
logits, end_points = mobilenet(inputs, is_training=False)
init = tf.global_variables_initializer()
config = tf.ConfigProto()
config.gpu_options.allocator_type = 'BFC'
sess = tf.Session(config=config)
sess.run(init)
time_tensorflow_run(sess, logits, "Forward")
# Add a simple objective so we can calculate the backward pass.
objective = tf.nn.l2_loss(logits)
# Compute the gradient with respect to all the parameters.
grad = tf.gradients(objective, tf.trainable_variables())
# Run the backward benchmark.
time_tensorflow_run(sess, grad, "Forward-backward")
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, _ = mobilenet.mobilenet(inputs)
sess.run(tf.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 = tf.random_uniform((batch_size, height, width, 3))
logits, _ = mobilenet.mobilenet(inputs)
sess.run(tf.global_variables_initializer())
output = sess.run(logits)
self.assertTrue(output.any())
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, _ = mobilenet.mobilenet(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, _ = mobilenet.mobilenet(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 run_benchmark():
if FLAGS.quantized:
graph_filename = FLAGS.quantized_graph
# Create a graph def object to read the graph
with tf.gfile.GFile(graph_filename, "rb") as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
with tf.Graph().as_default() as graph:
with tf.device('/' + FLAGS.mode + ':0'):
image_size = 224
if FLAGS.quantized:
inputs = np.random.random(
(FLAGS.batch_size, image_size, image_size, 3))
tf.import_graph_def(graph_def)
config = tf.ConfigProto()
config.gpu_options.allocator_type = 'BFC'
sess = tf.Session(config=config)
# We define the input and output node we will feed in
input_node = graph.get_tensor_by_name(
'import/MobileNet/input_images:0')
output_node = graph.get_tensor_by_name(
'import/MobileNet/Predictions/Softmax:0')
time_tensorflow_run_placeholder(sess, output_node,
{input_node: inputs},
"Forward")
else:
image_size = 224
inputs = tf.Variable(
tf.random_normal(
[FLAGS.batch_size, image_size, image_size, 3],
dtype=tf.float32,
stddev=1e-1))
with slim.arg_scope(mobilenet_arg_scope()):
logits, end_points = mobilenet(inputs, is_training=False)
init = tf.global_variables_initializer()
config = tf.ConfigProto()
config.gpu_options.allocator_type = 'BFC'
sess = tf.Session(config=config)
sess.run(init)
time_tensorflow_run(sess, logits, "Forward")
# Add a simple objective so we can calculate the backward pass.
objective = tf.nn.l2_loss(logits)
# Compute the gradient with respect to all the parameters.
grad = tf.gradients(objective, tf.trainable_variables())
# Run the backward benchmark.
time_tensorflow_run(sess, grad, "Forward-backward")
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, end_points = mobilenet.mobilenet(inputs, num_classes)
self.assertEquals(
end_points['MobileNet/conv_ds_2/depthwise_conv'].get_shape().
as_list(), [5, 112, 112, 32])
self.assertEquals(
end_points['MobileNet/conv_ds_3/depthwise_conv'].get_shape().
as_list(), [5, 56, 56, 64])
self.assertEquals(
end_points['MobileNet/conv_ds_4/depthwise_conv'].get_shape().
as_list(), [5, 56, 56, 128])
self.assertEquals(
end_points['MobileNet/conv_ds_5/depthwise_conv'].get_shape().
as_list(), [5, 28, 28, 128])
self.assertEquals(
end_points['MobileNet/conv_ds_6/depthwise_conv'].get_shape().
as_list(), [5, 28, 28, 256])
self.assertEquals(
end_points['MobileNet/conv_ds_7/depthwise_conv'].get_shape().
as_list(), [5, 14, 14, 256])
self.assertEquals(
end_points['MobileNet/conv_ds_8/depthwise_conv'].get_shape().
as_list(), [5, 14, 14, 512])
self.assertEquals(
end_points['MobileNet/conv_ds_9/depthwise_conv'].get_shape().
as_list(), [5, 14, 14, 512])
self.assertEquals(
end_points['MobileNet/conv_ds_10/depthwise_conv'].get_shape().
as_list(), [5, 14, 14, 512])
self.assertEquals(
end_points['MobileNet/conv_ds_11/depthwise_conv'].get_shape().
as_list(), [5, 14, 14, 512])
self.assertEquals(
end_points['MobileNet/conv_ds_12/depthwise_conv'].get_shape().
as_list(), [5, 14, 14, 512])
self.assertEquals(
end_points['MobileNet/conv_ds_13/depthwise_conv'].get_shape().
as_list(), [5, 7, 7, 512])
self.assertEquals(
end_points['MobileNet/conv_ds_14/depthwise_conv'].get_shape().
as_list(), [5, 7, 7, 1024])
self.assertEquals(end_points['squeeze'].get_shape().as_list(),
[5, 1024])
self.assertEquals(logits.op.name, 'MobileNet/fc_16/BiasAdd')
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
def run_benchmark():
if FLAGS.quantized:
graph_filename = FLAGS.quantized_graph
# Create a graph def object to read the graph
with tf.gfile.GFile(graph_filename, "rb") as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
with tf.Graph().as_default() as graph:
with tf.device('/'+FLAGS.mode+':0'):
image_size = 224
if FLAGS.quantized:
inputs = np.random.random((FLAGS.batch_size, image_size, image_size, 3))
tf.import_graph_def(graph_def)
config = tf.ConfigProto()
config.gpu_options.allocator_type = 'BFC'
sess = tf.Session(config=config)
# We define the input and output node we will feed in
input_node = graph.get_tensor_by_name('import/MobileNet/input_images:0')
output_node = graph.get_tensor_by_name('import/MobileNet/Predictions/Softmax:0')
time_tensorflow_run_placeholder(sess, output_node, {input_node: inputs}, "Forward")
else:
image_size = 224
inputs = tf.Variable(tf.random_normal([FLAGS.batch_size,
image_size,
image_size, 3],
dtype=tf.float32,
stddev=1e-1))
with slim.arg_scope(mobilenet_arg_scope()):
logits, end_points = mobilenet(inputs, is_training=False)
init = tf.global_variables_initializer()
config = tf.ConfigProto()
config.gpu_options.allocator_type = 'BFC'
sess = tf.Session(config=config)
sess.run(init)
time_tensorflow_run(sess, logits, "Forward")
# Add a simple objective so we can calculate the backward pass.
objective = tf.nn.l2_loss(logits)
# Compute the gradient with respect to all the parameters.
grad = tf.gradients(objective, tf.trainable_variables())
# Run the backward benchmark.
time_tensorflow_run(sess, grad, "Forward-backward")
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, end_points = mobilenet.mobilenet(inputs, num_classes)
self.assertEquals(end_points['MobileNet/conv_ds_2/depthwise_conv'].get_shape().as_list(), [5, 112, 112, 32])
self.assertEquals(end_points['MobileNet/conv_ds_3/depthwise_conv'].get_shape().as_list(), [5, 56, 56, 64])
self.assertEquals(end_points['MobileNet/conv_ds_4/depthwise_conv'].get_shape().as_list(), [5, 56, 56, 128])
self.assertEquals(end_points['MobileNet/conv_ds_5/depthwise_conv'].get_shape().as_list(), [5, 28, 28, 128])
self.assertEquals(end_points['MobileNet/conv_ds_6/depthwise_conv'].get_shape().as_list(), [5, 28, 28, 256])
self.assertEquals(end_points['MobileNet/conv_ds_7/depthwise_conv'].get_shape().as_list(), [5, 14, 14, 256])
self.assertEquals(end_points['MobileNet/conv_ds_8/depthwise_conv'].get_shape().as_list(), [5, 14, 14, 512])
self.assertEquals(end_points['MobileNet/conv_ds_9/depthwise_conv'].get_shape().as_list(), [5, 14, 14, 512])
self.assertEquals(end_points['MobileNet/conv_ds_10/depthwise_conv'].get_shape().as_list(), [5, 14, 14, 512])
self.assertEquals(end_points['MobileNet/conv_ds_11/depthwise_conv'].get_shape().as_list(), [5, 14, 14, 512])
self.assertEquals(end_points['MobileNet/conv_ds_12/depthwise_conv'].get_shape().as_list(), [5, 14, 14, 512])
self.assertEquals(end_points['MobileNet/conv_ds_13/depthwise_conv'].get_shape().as_list(), [5, 7, 7, 512])
self.assertEquals(end_points['MobileNet/conv_ds_14/depthwise_conv'].get_shape().as_list(), [5, 7, 7, 1024])
self.assertEquals(end_points['squeeze'].get_shape().as_list(), [5, 1024])
self.assertEquals(logits.op.name, 'MobileNet/fc_16/BiasAdd')
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
def SSD300(input_shape, num_classes=21):
# 300,300,3
input_tensor = Input(shape=input_shape)
img_size = (input_shape[1], input_shape[0])
# SSD结构,net字典
net = mobilenet(input_tensor)
#-----------------------将提取到的主干特征进行处理---------------------------#
num_priors = 4
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
net['conv4_3_loc'] = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv4_3_loc')(net['conv4_3'])
net['conv4_3_loc_flat'] = Flatten(name='conv4_3_loc_flat')(
net['conv4_3_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
net['conv4_3_conf'] = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv4_3_conf')(net['conv4_3'])
net['conv4_3_conf_flat'] = Flatten(name='conv4_3_conf_flat')(
net['conv4_3_conf'])
priorbox = PriorBox(img_size,
30.0,
max_size=60.0,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv4_3_priorbox')
net['conv4_3_priorbox'] = priorbox(net['conv4_3'])
# 对fc7层进行处理
num_priors = 6
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
net['fc7_mbox_loc'] = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='fc7_mbox_loc')(net['fc7'])
net['fc7_mbox_loc_flat'] = Flatten(name='fc7_mbox_loc_flat')(
net['fc7_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
net['fc7_mbox_conf'] = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='fc7_mbox_conf')(net['fc7'])
net['fc7_mbox_conf_flat'] = Flatten(name='fc7_mbox_conf_flat')(
net['fc7_mbox_conf'])
priorbox = PriorBox(img_size,
60.0,
max_size=111.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')
net['fc7_mbox_priorbox'] = priorbox(net['fc7'])
# 对conv6_2进行处理
num_priors = 6
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv6_2_mbox_loc')(net['conv6_2'])
net['conv6_2_mbox_loc'] = x
net['conv6_2_mbox_loc_flat'] = Flatten(name='conv6_2_mbox_loc_flat')(
net['conv6_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv6_2_mbox_conf')(net['conv6_2'])
net['conv6_2_mbox_conf'] = x
net['conv6_2_mbox_conf_flat'] = Flatten(name='conv6_2_mbox_conf_flat')(
net['conv6_2_mbox_conf'])
priorbox = PriorBox(img_size,
111.0,
max_size=162.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')
net['conv6_2_mbox_priorbox'] = priorbox(net['conv6_2'])
# 对conv7_2进行处理
num_priors = 6
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv7_2_mbox_loc')(net['conv7_2'])
net['conv7_2_mbox_loc'] = x
net['conv7_2_mbox_loc_flat'] = Flatten(name='conv7_2_mbox_loc_flat')(
net['conv7_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv7_2_mbox_conf')(net['conv7_2'])
net['conv7_2_mbox_conf'] = x
net['conv7_2_mbox_conf_flat'] = Flatten(name='conv7_2_mbox_conf_flat')(
net['conv7_2_mbox_conf'])
priorbox = PriorBox(img_size,
162.0,
max_size=213.0,
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')
net['conv7_2_mbox_priorbox'] = priorbox(net['conv7_2'])
# 对conv8_2进行处理
num_priors = 4
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv8_2_mbox_loc')(net['conv8_2'])
net['conv8_2_mbox_loc'] = x
net['conv8_2_mbox_loc_flat'] = Flatten(name='conv8_2_mbox_loc_flat')(
net['conv8_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv8_2_mbox_conf')(net['conv8_2'])
net['conv8_2_mbox_conf'] = x
net['conv8_2_mbox_conf_flat'] = Flatten(name='conv8_2_mbox_conf_flat')(
net['conv8_2_mbox_conf'])
priorbox = PriorBox(img_size,
213.0,
max_size=264.0,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')
net['conv8_2_mbox_priorbox'] = priorbox(net['conv8_2'])
# 对conv9_2进行处理
num_priors = 4
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv9_2_mbox_loc')(net['conv9_2'])
net['conv9_2_mbox_loc'] = x
net['conv9_2_mbox_loc_flat'] = Flatten(name='conv9_2_mbox_loc_flat')(
net['conv9_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv9_2_mbox_conf')(net['conv9_2'])
net['conv9_2_mbox_conf'] = x
net['conv9_2_mbox_conf_flat'] = Flatten(name='conv9_2_mbox_conf_flat')(
net['conv9_2_mbox_conf'])
priorbox = PriorBox(img_size,
264.0,
max_size=315.0,
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv9_2_mbox_priorbox')
net['conv9_2_mbox_priorbox'] = priorbox(net['conv9_2'])
# 将所有结果进行堆叠
net['mbox_loc'] = concatenate([
net['conv4_3_loc_flat'], net['fc7_mbox_loc_flat'],
net['conv6_2_mbox_loc_flat'], net['conv7_2_mbox_loc_flat'],
net['conv8_2_mbox_loc_flat'], net['conv9_2_mbox_loc_flat']
],
axis=1,
name='mbox_loc')
net['mbox_conf'] = concatenate([
net['conv4_3_conf_flat'], net['fc7_mbox_conf_flat'],
net['conv6_2_mbox_conf_flat'], net['conv7_2_mbox_conf_flat'],
net['conv8_2_mbox_conf_flat'], net['conv9_2_mbox_conf_flat']
],
axis=1,
name='mbox_conf')
net['mbox_priorbox'] = concatenate([
net['conv4_3_priorbox'], net['fc7_mbox_priorbox'],
net['conv6_2_mbox_priorbox'], net['conv7_2_mbox_priorbox'],
net['conv8_2_mbox_priorbox'], net['conv9_2_mbox_priorbox']
],
axis=1,
name='mbox_priorbox')
# if hasattr(net['mbox_loc'], '_keras_shape'):
# num_boxes = net['mbox_loc']._keras_shape[-1] // 4
# elif hasattr(net['mbox_loc'], 'int_shape'):
num_boxes = K.int_shape(net['mbox_loc'])[-1] // 4
# 8732,4
net['mbox_loc'] = Reshape((num_boxes, 4),
name='mbox_loc_final')(net['mbox_loc'])
# 8732,21
net['mbox_conf'] = Reshape((num_boxes, num_classes),
name='mbox_conf_logits')(net['mbox_conf'])
net['mbox_conf'] = Activation('softmax',
name='mbox_conf_final')(net['mbox_conf'])
net['predictions'] = concatenate(
[net['mbox_loc'], net['mbox_conf'], net['mbox_priorbox']],
axis=2,
name='predictions')
net['predictions'] = tf.cast(net['predictions'], tf.float64)
print(net['predictions'])
model = tf.keras.Model(input_tensor, net['predictions'])
return model
def SSD300(input_shape,
num_classes=21,
anchors_size=[30, 60, 111, 162, 213, 264, 315]):
#---------------------------------#
# 典型的输入大小为[300,300,3]
#---------------------------------#
input_tensor = Input(shape=input_shape)
# net变量里面包含了整个SSD的结构，通过层名可以找到对应的特征层
net = mobilenet(input_tensor)
#-----------------------将提取到的主干特征进行处理---------------------------#
# 对conv4_3的通道进行l2标准化处理
# 38,38,512
num_priors = 4
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
net['conv4_3_loc'] = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv4_3_loc')(net['conv4_3'])
net['conv4_3_loc_flat'] = Flatten(name='conv4_3_loc_flat')(
net['conv4_3_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
net['conv4_3_conf'] = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv4_3_conf')(net['conv4_3'])
net['conv4_3_conf_flat'] = Flatten(name='conv4_3_conf_flat')(
net['conv4_3_conf'])
priorbox = PriorBox(input_shape,
anchors_size[0],
max_size=anchors_size[1],
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv4_3_priorbox')
net['conv4_3_priorbox'] = priorbox(net['conv4_3'])
# 对fc7层进行处理
# 19,19,1024
num_priors = 6
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
net['fc7_mbox_loc'] = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='fc7_mbox_loc')(net['fc7'])
net['fc7_mbox_loc_flat'] = Flatten(name='fc7_mbox_loc_flat')(
net['fc7_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
net['fc7_mbox_conf'] = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='fc7_mbox_conf')(net['fc7'])
net['fc7_mbox_conf_flat'] = Flatten(name='fc7_mbox_conf_flat')(
net['fc7_mbox_conf'])
priorbox = PriorBox(input_shape,
anchors_size[1],
max_size=anchors_size[2],
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='fc7_mbox_priorbox')
net['fc7_mbox_priorbox'] = priorbox(net['fc7'])
# 对conv6_2进行处理
# 10,10,512
num_priors = 6
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv6_2_mbox_loc')(net['conv6_2'])
net['conv6_2_mbox_loc'] = x
net['conv6_2_mbox_loc_flat'] = Flatten(name='conv6_2_mbox_loc_flat')(
net['conv6_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv6_2_mbox_conf')(net['conv6_2'])
net['conv6_2_mbox_conf'] = x
net['conv6_2_mbox_conf_flat'] = Flatten(name='conv6_2_mbox_conf_flat')(
net['conv6_2_mbox_conf'])
priorbox = PriorBox(input_shape,
anchors_size[2],
max_size=anchors_size[3],
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv6_2_mbox_priorbox')
net['conv6_2_mbox_priorbox'] = priorbox(net['conv6_2'])
# 对conv7_2进行处理
# 5,5,256
num_priors = 6
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv7_2_mbox_loc')(net['conv7_2'])
net['conv7_2_mbox_loc'] = x
net['conv7_2_mbox_loc_flat'] = Flatten(name='conv7_2_mbox_loc_flat')(
net['conv7_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv7_2_mbox_conf')(net['conv7_2'])
net['conv7_2_mbox_conf'] = x
net['conv7_2_mbox_conf_flat'] = Flatten(name='conv7_2_mbox_conf_flat')(
net['conv7_2_mbox_conf'])
priorbox = PriorBox(input_shape,
anchors_size[3],
max_size=anchors_size[4],
aspect_ratios=[2, 3],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv7_2_mbox_priorbox')
net['conv7_2_mbox_priorbox'] = priorbox(net['conv7_2'])
# 对conv8_2进行处理
# 3,3,256
num_priors = 4
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv8_2_mbox_loc')(net['conv8_2'])
net['conv8_2_mbox_loc'] = x
net['conv8_2_mbox_loc_flat'] = Flatten(name='conv8_2_mbox_loc_flat')(
net['conv8_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv8_2_mbox_conf')(net['conv8_2'])
net['conv8_2_mbox_conf'] = x
net['conv8_2_mbox_conf_flat'] = Flatten(name='conv8_2_mbox_conf_flat')(
net['conv8_2_mbox_conf'])
priorbox = PriorBox(input_shape,
anchors_size[4],
max_size=anchors_size[5],
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv8_2_mbox_priorbox')
net['conv8_2_mbox_priorbox'] = priorbox(net['conv8_2'])
# 对conv9_2进行处理
# 1,1,256
num_priors = 4
# 预测框的处理
# num_priors表示每个网格点先验框的数量，4是x,y,h,w的调整
x = Conv2D(num_priors * 4,
kernel_size=(3, 3),
padding='same',
name='conv9_2_mbox_loc')(net['conv9_2'])
net['conv9_2_mbox_loc'] = x
net['conv9_2_mbox_loc_flat'] = Flatten(name='conv9_2_mbox_loc_flat')(
net['conv9_2_mbox_loc'])
# num_priors表示每个网格点先验框的数量，num_classes是所分的类
x = Conv2D(num_priors * num_classes,
kernel_size=(3, 3),
padding='same',
name='conv9_2_mbox_conf')(net['conv9_2'])
net['conv9_2_mbox_conf'] = x
net['conv9_2_mbox_conf_flat'] = Flatten(name='conv9_2_mbox_conf_flat')(
net['conv9_2_mbox_conf'])
priorbox = PriorBox(input_shape,
anchors_size[5],
max_size=anchors_size[6],
aspect_ratios=[2],
variances=[0.1, 0.1, 0.2, 0.2],
name='conv9_2_mbox_priorbox')
net['conv9_2_mbox_priorbox'] = priorbox(net['conv9_2'])
# 将所有结果进行堆叠
net['mbox_loc'] = concatenate([
net['conv4_3_loc_flat'], net['fc7_mbox_loc_flat'],
net['conv6_2_mbox_loc_flat'], net['conv7_2_mbox_loc_flat'],
net['conv8_2_mbox_loc_flat'], net['conv9_2_mbox_loc_flat']
],
axis=1,
name='mbox_loc')
net['mbox_conf'] = concatenate([
net['conv4_3_conf_flat'], net['fc7_mbox_conf_flat'],
net['conv6_2_mbox_conf_flat'], net['conv7_2_mbox_conf_flat'],
net['conv8_2_mbox_conf_flat'], net['conv9_2_mbox_conf_flat']
],
axis=1,
name='mbox_conf')
net['mbox_priorbox'] = concatenate([
net['conv4_3_priorbox'], net['fc7_mbox_priorbox'],
net['conv6_2_mbox_priorbox'], net['conv7_2_mbox_priorbox'],
net['conv8_2_mbox_priorbox'], net['conv9_2_mbox_priorbox']
],
axis=1,
name='mbox_priorbox')
# 8732,4
net['mbox_loc'] = Reshape((-1, 4), name='mbox_loc_final')(net['mbox_loc'])
# 8732,21
net['mbox_conf'] = Reshape((-1, num_classes),
name='mbox_conf_logits')(net['mbox_conf'])
# 8732,8
net['mbox_conf'] = Activation('softmax',
name='mbox_conf_final')(net['mbox_conf'])
# 8732,33
net['predictions'] = concatenate(
[net['mbox_loc'], net['mbox_conf'], net['mbox_priorbox']],
axis=2,
name='predictions')
model = Model(input_tensor, net['predictions'])
return model
import tensorflow as tf
from nets.mobilenet import mobilenet
from tensorflow.python.training import saver as saver_lib
from tensorflow.python import pywrap_tensorflow
input_checkpoint = '/home/zehao/PycharmProjects/MobileNet/mobilenet-model/model.ckpt-439074'
# Where to save the modified graph
save_path = '/home/zehao/PycharmProjects/MobileNet/mobilenet-model/with_placeholder'
# TODO(shizehao): use graph editor library insead
with tf.Graph().as_default() as graph:
input_images = tf.placeholder(tf.float32, [None, 224, 224, 3],
'MobileNet/input_images')
logits, predictions = mobilenet(inputs=input_images,
num_classes=1001,
is_training=False)
saver = tf.train.Saver()
with tf.Session() as sess:
var_list = {}
reader = pywrap_tensorflow.NewCheckpointReader(input_checkpoint)
var_to_shape_map = reader.get_variable_to_shape_map()
for key in var_to_shape_map:
try:
tensor = sess.graph.get_tensor_by_name(key + ":0")
except KeyError:
# This tensor doesn't exist in the graph (for example it's
# 'global_step' or a similar housekeeping element) so skip it.
continue
var_list[key] = tensor
saver = saver_lib.Saver(var_list=var_list)
def mobilenet(input_tensor,
num_classes=1001,
depth_multiplier=1.0,
scope='MobilenetV2',
conv_defs=None,
finegrain_classification_mode=False,
min_depth=None,
divisible_by=None,
**kwargs):
"""Creates mobilenet V2 network.
Inference mode is created by default. To create training use training_scope
below.
with tf.contrib.slim.arg_scope(mobilenet_v2.training_scope()):
logits, endpoints = mobilenet_v2.mobilenet(input_tensor)
Args:
input_tensor: The input tensor
num_classes: number of classes
depth_multiplier: The multiplier applied to scale number of
channels in each layer. Note: this is called depth multiplier in the
paper but the name is kept for consistency with slim's model builder.
scope: Scope of the operator
conv_defs: Allows to override default conv def.
finegrain_classification_mode: When set to True, the model
will keep the last layer large even for small multipliers. Following
https://arxiv.org/abs/1801.04381
suggests that it improves performance for ImageNet-type of problems.
*Note* ignored if final_endpoint makes the builder exit earlier.
min_depth: If provided, will ensure that all layers will have that
many channels after application of depth multiplier.
divisible_by: If provided will ensure that all layers # channels
will be divisible by this number.
**kwargs: passed directly to mobilenet.mobilenet:
prediction_fn- what prediction function to use.
reuse-: whether to reuse variables (if reuse set to true, scope
must be given).
Returns:
logits/endpoints pair
Raises:
ValueError: On invalid arguments
"""
if conv_defs is None:
conv_defs = V2_DEF
if 'multiplier' in kwargs:
raise ValueError(
'mobilenetv2 doesn\'t support generic '
'multiplier parameter use "depth_multiplier" instead.')
if finegrain_classification_mode:
conv_defs = copy.deepcopy(conv_defs)
if depth_multiplier < 1:
conv_defs['spec'][-1].params['num_outputs'] /= depth_multiplier
depth_args = {}
# NB: do not set depth_args unless they are provided to avoid overriding
# whatever default depth_multiplier might have thanks to arg_scope.
if min_depth is not None:
depth_args['min_depth'] = min_depth
if divisible_by is not None:
depth_args['divisible_by'] = divisible_by
with slim.arg_scope((lib.depth_multiplier, ), **depth_args):
return lib.mobilenet(input_tensor,
num_classes=num_classes,
conv_defs=conv_defs,
scope=scope,
multiplier=depth_multiplier,
**kwargs)
slim = tf.contrib.slim
IMAGENET_CLASSES = 1001
with tf.Session() as sess:
with open('final1.jpg', 'rb') as f:
image = f.read()
image = tf.image.decode_jpeg(image, channels=0)
image = tf.reshape(image, (1825, 2738, 3))
image = preprocess_for_eval(image, 224, 224)
image = tf.expand_dims(image, axis=0)
logits, _ = mobilenet(image,
num_classes=IMAGENET_CLASSES,
is_training=False)
softs = tf.nn.softmax(logits)
top_5 = tf.nn.top_k(softs, k=5)
tf.global_variables_initializer().run()
saver = tf.train.Saver()
print('restoring weights')
saver.restore(sess, 'weights/model.ckpt-906808')
_, logits_out, top_5_out = sess.run([image, logits, top_5])
values, indices = top_5_out.values, top_5_out.indices
import tensorflow as tf
from nets.mobilenet import mobilenet
from tensorflow.python.training import saver as saver_lib
from tensorflow.python import pywrap_tensorflow
input_checkpoint = '/home/zehao/PycharmProjects/MobileNet/mobilenet-model/model.ckpt-439074'
# Where to save the modified graph
save_path = '/home/zehao/PycharmProjects/MobileNet/mobilenet-model/with_placeholder'
# TODO(shizehao): use graph editor library insead
with tf.Graph().as_default() as graph:
input_images = tf.placeholder(tf.float32, [None, 224, 224, 3], 'MobileNet/input_images')
logits, predictions = mobilenet(inputs=input_images, num_classes=1001, is_training=False)
saver = tf.train.Saver()
with tf.Session() as sess:
var_list = {}
reader = pywrap_tensorflow.NewCheckpointReader(input_checkpoint)
var_to_shape_map = reader.get_variable_to_shape_map()
for key in var_to_shape_map:
try:
tensor = sess.graph.get_tensor_by_name(key + ":0")
except KeyError:
# This tensor doesn't exist in the graph (for example it's
# 'global_step' or a similar housekeeping element) so skip it.
continue
var_list[key] = tensor
saver = saver_lib.Saver(var_list=var_list)
# Restore variables
saver.restore(sess, input_checkpoint)
