1、AlexNet
from datetime import datetime
import math
import time
import tensorflow as tf
batch_size=32
num_batches=100
def print_activations(t):
print(t.op.name, ' ', t.get_shape().as_list())
def inference(images):
parameters = []
# conv1
with tf.name_scope('conv1') as scope:
kernel = tf.Variable(tf.truncated_normal([11, 11, 3, 64], dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(images, kernel, [1, 4, 4, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[64], dtype=tf.float32),
trainable=True, name='biases')
bias = tf.nn.bias_add(conv, biases)
conv1 = tf.nn.relu(bias, name=scope)
print_activations(conv1)
parameters += [kernel, biases]
# pool1
lrn1 = tf.nn.lrn(conv1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name='lrn1')
pool1 = tf.nn.max_pool(lrn1,
ksize=[1, 3, 3, 1],
strides=[1, 2, 2, 1],
padding='VALID',
name='pool1')
print_activations(pool1)
# conv2
with tf.name_scope('conv2') as scope:
kernel = tf.Variable(tf.truncated_normal([5, 5, 64, 192], dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(pool1, kernel, [1, 1, 1, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[192], dtype=tf.float32),
trainable=True, name='biases')
bias = tf.nn.bias_add(conv, biases)
conv2 = tf.nn.relu(bias, name=scope)
parameters += [kernel, biases]
print_activations(conv2)
# pool2
lrn2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name='lrn2')
pool2 = tf.nn.max_pool(lrn2,
ksize=[1, 3, 3, 1],
strides=[1, 2, 2, 1],
padding='VALID',
name='pool2')
print_activations(pool2)
# conv3
with tf.name_scope('conv3') as scope:
kernel = tf.Variable(tf.truncated_normal([3, 3, 192, 384],
dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(pool2, kernel, [1, 1, 1, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[384], dtype=tf.float32),
trainable=True, name='biases')
bias = tf.nn.bias_add(conv, biases)
conv3 = tf.nn.relu(bias, name=scope)
parameters += [kernel, biases]
print_activations(conv3)
# conv4
with tf.name_scope('conv4') as scope:
kernel = tf.Variable(tf.truncated_normal([3, 3, 384, 256],
dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(conv3, kernel, [1, 1, 1, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[256], dtype=tf.float32),
trainable=True, name='biases')
bias = tf.nn.bias_add(conv, biases)
conv4 = tf.nn.relu(bias, name=scope)
parameters += [kernel, biases]
print_activations(conv4)
# conv5
with tf.name_scope('conv5') as scope:
kernel = tf.Variable(tf.truncated_normal([3, 3, 256, 256],
dtype=tf.float32,
stddev=1e-1), name='weights')
conv = tf.nn.conv2d(conv4, kernel, [1, 1, 1, 1], padding='SAME')
biases = tf.Variable(tf.constant(0.0, shape=[256], dtype=tf.float32),
trainable=True, name='biases')
bias = tf.nn.bias_add(conv, biases)
conv5 = tf.nn.relu(bias, name=scope)
parameters += [kernel, biases]
print_activations(conv5)
# pool5
pool5 = tf.nn.max_pool(conv5,
ksize=[1, 3, 3, 1],
strides=[1, 2, 2, 1],
padding='VALID',
name='pool5')
print_activations(pool5)
return pool5, parameters
def time_tensorflow_run(session, target, info_string):
# """Run the computation to obtain the target tensor and print timing stats.
#
# Args:
# session: the TensorFlow session to run the computation under.
# target: the target Tensor that is passed to the session's run() function.
# info_string: a string summarizing this run, to be printed with the stats.
#
# Returns:
# None
# """
num_steps_burn_in = 10
total_duration = 0.0
total_duration_squared = 0.0
for i in range(num_batches + num_steps_burn_in):
start_time = time.time()
_ = session.run(target)
duration = time.time() - start_time
if i >= num_steps_burn_in:
if not i % 10:
print ('%s: step %d, duration = %.3f' %
(datetime.now(), i - num_steps_burn_in, duration))
total_duration += duration
total_duration_squared += duration * duration
mn = total_duration / num_batches
vr = total_duration_squared / num_batches - mn * mn
sd = math.sqrt(vr)
print ('%s: %s across %d steps, %.3f +/- %.3f sec / batch' %
(datetime.now(), info_string, num_batches, mn, sd))
def run_benchmark():
# """Run the benchmark on AlexNet."""
with tf.Graph().as_default():
# Generate some dummy images.
image_size = 224
# Note that our padding definition is slightly different the cuda-convnet.
# In order to force the model to start with the same activations sizes,
# we add 3 to the image_size and employ VALID padding above.
images = tf.Variable(tf.random_normal([batch_size,
image_size,
image_size, 3],
dtype=tf.float32,
stddev=1e-1))
# Build a Graph that computes the logits predictions from the
# inference model.
pool5, parameters = inference(images)
# Build an initialization operation.
init = tf.global_variables_initializer()
# Start running operations on the Graph.
config = tf.ConfigProto()
config.gpu_options.allocator_type = 'BFC'
sess = tf.Session(config=config)
sess.run(init)
# Run the forward benchmark.
time_tensorflow_run(sess, pool5, "Forward")
# Add a simple objective so we can calculate the backward pass.
objective = tf.nn.l2_loss(pool5)
# Compute the gradient with respect to all the parameters.
grad = tf.gradients(objective, parameters)
# Run the backward benchmark.
time_tensorflow_run(sess, grad, "Forward-backward")
run_benchmark()
2、VggNet
from datetime import datetime
import math
import time
import tensorflow as tf
def conv_op(input_op, name, kh, kw, n_out, dh, dw, p):
n_in = input_op.get_shape()[-1].value
with tf.name_scope(name) as scope:
kernel = tf.get_variable(scope+"w",
shape=[kh, kw, n_in, n_out],
dtype=tf.float32,
initializer=tf.contrib.layers.xavier_initializer_conv2d())
conv = tf.nn.conv2d(input_op, kernel, (1, dh, dw, 1), padding='SAME')
bias_init_val = tf.constant(0.0, shape=[n_out], dtype=tf.float32)
biases = tf.Variable(bias_init_val, trainable=True, name='b')
z = tf.nn.bias_add(conv, biases)
activation = tf.nn.relu(z, name=scope)
p += [kernel, biases]
return activation
def fc_op(input_op, name, n_out, p):
n_in = input_op.get_shape()[-1].value
with tf.name_scope(name) as scope:
kernel = tf.get_variable(scope+"w",
shape=[n_in, n_out],
dtype=tf.float32,
initializer=tf.contrib.layers.xavier_initializer())
biases = tf.Variable(tf.constant(0.1, shape=[n_out], dtype=tf.float32), name='b')
activation = tf.nn.relu_layer(input_op, kernel, biases, name=scope)
p += [kernel, biases]
return activation
def mpool_op(input_op, name, kh, kw, dh, dw):
return tf.nn.max_pool(input_op,
ksize=[1, kh, kw, 1],
strides=[1, dh, dw, 1],
padding='SAME',
name=name)
def inference_op(input_op, keep_prob):
p = []
# assume input_op shape is 224x224x3
# block 1 -- outputs 112x112x64
conv1_1 = conv_op(input_op, name="conv1_1", kh=3, kw=3, n_out=64, dh=1, dw=1, p=p)
conv1_2 = conv_op(conv1_1, name="conv1_2", kh=3, kw=3, n_out=64, dh=1, dw=1, p=p)
pool1 = mpool_op(conv1_2, name="pool1", kh=2, kw=2, dw=2, dh=2)
# block 2 -- outputs 56x56x128
conv2_1 = conv_op(pool1, name="conv2_1", kh=3, kw=3, n_out=128, dh=1, dw=1, p=p)
conv2_2 = conv_op(conv2_1, name="conv2_2", kh=3, kw=3, n_out=128, dh=1, dw=1, p=p)
pool2 = mpool_op(conv2_2, name="pool2", kh=2, kw=2, dh=2, dw=2)
# # block 3 -- outputs 28x28x256
conv3_1 = conv_op(pool2, name="conv3_1", kh=3, kw=3, n_out=256, dh=1, dw=1, p=p)
conv3_2 = conv_op(conv3_1, name="conv3_2", kh=3, kw=3, n_out=256, dh=1, dw=1, p=p)
conv3_3 = conv_op(conv3_2, name="conv3_3", kh=3, kw=3, n_out=256, dh=1, dw=1, p=p)
pool3 = mpool_op(conv3_3, name="pool3", kh=2, kw=2, dh=2, dw=2)
# block 4 -- outputs 14x14x512
conv4_1 = conv_op(pool3, name="conv4_1", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv4_2 = conv_op(conv4_1, name="conv4_2", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv4_3 = conv_op(conv4_2, name="conv4_3", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
pool4 = mpool_op(conv4_3, name="pool4", kh=2, kw=2, dh=2, dw=2)
# block 5 -- outputs 7x7x512
conv5_1 = conv_op(pool4, name="conv5_1", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv5_2 = conv_op(conv5_1, name="conv5_2", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
conv5_3 = conv_op(conv5_2, name="conv5_3", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p)
pool5 = mpool_op(conv5_3, name="pool5", kh=2, kw=2, dw=2, dh=2)
# flatten
shp = pool5.get_shape()
flattened_shape = shp[1].value * shp[2].value * shp[3].value
resh1 = tf.reshape(pool5, [-1, flattened_shape], name="resh1")
# fully connected
fc6 = fc_op(resh1, name="fc6", n_out=4096, p=p)
fc6_drop = tf.nn.dropout(fc6, keep_prob, name="fc6_drop")
fc7 = fc_op(fc6_drop, name="fc7", n_out=4096, p=p)
fc7_drop = tf.nn.dropout(fc7, keep_prob, name="fc7_drop")
fc8 = fc_op(fc7_drop, name="fc8", n_out=1000, p=p)
softmax = tf.nn.softmax(fc8)
predictions = tf.argmax(softmax, 1)
return predictions, softmax, fc8, p
def time_tensorflow_run(session, target, feed, info_string):
num_steps_burn_in = 10
total_duration = 0.0
total_duration_squared = 0.0
for i in range(num_batches + num_steps_burn_in):
start_time = time.time()
_ = session.run(target, feed_dict=feed)
duration = time.time() - start_time
if i >= num_steps_burn_in:
if not i % 10:
print ('%s: step %d, duration = %.3f' %
(datetime.now(), i - num_steps_burn_in, duration))
total_duration += duration
total_duration_squared += duration * duration
mn = total_duration / num_batches
vr = total_duration_squared / num_batches - mn * mn
sd = math.sqrt(vr)
print ('%s: %s across %d steps, %.3f +/- %.3f sec / batch' %
(datetime.now(), info_string, num_batches, mn, sd))
def run_benchmark():
with tf.Graph().as_default():
image_size = 224
images = tf.Variable(tf.random_normal([batch_size,
image_size,
image_size, 3],
dtype=tf.float32,
stddev=1e-1))
keep_prob = tf.placeholder(tf.float32)
predictions, softmax, fc8, p = inference_op(images, keep_prob)
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, predictions, {keep_prob:1.0}, "Forward")
objective = tf.nn.l2_loss(fc8)
grad = tf.gradients(objective, p)
time_tensorflow_run(sess, grad, {keep_prob:0.5}, "Forward-backward")
batch_size=32
num_batches=100
run_benchmark()
3、InceptionNet
import tensorflow as tf
slim = tf.contrib.slim
trunc_normal = lambda stddev: tf.truncated_normal_initializer(0.0, stddev)
def inception_v3_base(inputs, scope=None):
end_points = {}
with tf.variable_scope(scope, 'InceptionV3', [inputs]):
with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
stride=1, padding='VALID'):
# 299 x 299 x 3
net = slim.conv2d(inputs, 32, [3, 3], stride=2, scope='Conv2d_1a_3x3')
# 149 x 149 x 32
net = slim.conv2d(net, 32, [3, 3], scope='Conv2d_2a_3x3')
# 147 x 147 x 32
net = slim.conv2d(net, 64, [3, 3], padding='SAME', scope='Conv2d_2b_3x3')
# 147 x 147 x 64
net = slim.max_pool2d(net, [3, 3], stride=2, scope='MaxPool_3a_3x3')
# 73 x 73 x 64
net = slim.conv2d(net, 80, [1, 1], scope='Conv2d_3b_1x1')
# 73 x 73 x 80.
net = slim.conv2d(net, 192, [3, 3], scope='Conv2d_4a_3x3')
# 71 x 71 x 192.
net = slim.max_pool2d(net, [3, 3], stride=2, scope='MaxPool_5a_3x3')
# 35 x 35 x 192.
# Inception blocks
with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
stride=1, padding='SAME'):
# mixed: 35 x 35 x 256.
with tf.variable_scope('Mixed_5b'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net, 48, [1, 1], scope='Conv2d_0a_1x1')
branch_1 = slim.conv2d(branch_1, 64, [5, 5], scope='Conv2d_0b_5x5')
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1')
branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0b_3x3')
branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0c_3x3')
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = slim.conv2d(branch_3, 32, [1, 1], scope='Conv2d_0b_1x1')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# mixed_1: 35 x 35 x 288.
with tf.variable_scope('Mixed_5c'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net, 48, [1, 1], scope='Conv2d_0b_1x1')
branch_1 = slim.conv2d(branch_1, 64, [5, 5], scope='Conv_1_0c_5x5')
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1')
branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0b_3x3')
branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0c_3x3')
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# mixed_2: 35 x 35 x 288.
with tf.variable_scope('Mixed_5d'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net, 48, [1, 1], scope='Conv2d_0a_1x1')
branch_1 = slim.conv2d(branch_1, 64, [5, 5], scope='Conv2d_0b_5x5')
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1')
branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0b_3x3')
branch_2 = slim.conv2d(branch_2, 96, [3, 3], scope='Conv2d_0c_3x3')
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = slim.conv2d(branch_3, 64, [1, 1], scope='Conv2d_0b_1x1')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# mixed_3: 17 x 17 x 768.
with tf.variable_scope('Mixed_6a'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net, 384, [3, 3], stride=2,
padding='VALID', scope='Conv2d_1a_1x1')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net, 64, [1, 1], scope='Conv2d_0a_1x1')
branch_1 = slim.conv2d(branch_1, 96, [3, 3], scope='Conv2d_0b_3x3')
branch_1 = slim.conv2d(branch_1, 96, [3, 3], stride=2,
padding='VALID', scope='Conv2d_1a_1x1')
with tf.variable_scope('Branch_2'):
branch_2 = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID',
scope='MaxPool_1a_3x3')
net = tf.concat([branch_0, branch_1, branch_2], 3)
# mixed4: 17 x 17 x 768.
with tf.variable_scope('Mixed_6b'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net, 128, [1, 1], scope='Conv2d_0a_1x1')
branch_1 = slim.conv2d(branch_1, 128, [1, 7], scope='Conv2d_0b_1x7')
branch_1 = slim.conv2d(branch_1, 192, [7, 1], scope='Conv2d_0c_7x1')
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, 128, [1, 1], scope='Conv2d_0a_1x1')
branch_2 = slim.conv2d(branch_2, 128, [7, 1], scope='Conv2d_0b_7x1')
branch_2 = slim.conv2d(branch_2, 128, [1, 7], scope='Conv2d_0c_1x7')
branch_2 = slim.conv2d(branch_2, 128, [7, 1], scope='Conv2d_0d_7x1')
branch_2 = slim.conv2d(branch_2, 192, [1, 7], scope='Conv2d_0e_1x7')
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = slim.conv2d(branch_3, 192, [1, 1], scope='Conv2d_0b_1x1')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# mixed_5: 17 x 17 x 768.
with tf.variable_scope('Mixed_6c'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1x1')
branch_1 = slim.conv2d(branch_1, 160, [1, 7], scope='Conv2d_0b_1x7')
branch_1 = slim.conv2d(branch_1, 192, [7, 1], scope='Conv2d_0c_7x1')
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1x1')
branch_2 = slim.conv2d(branch_2, 160, [7, 1], scope='Conv2d_0b_7x1')
branch_2 = slim.conv2d(branch_2, 160, [1, 7], scope='Conv2d_0c_1x7')
branch_2 = slim.conv2d(branch_2, 160, [7, 1], scope='Conv2d_0d_7x1')
branch_2 = slim.conv2d(branch_2, 192, [1, 7], scope='Conv2d_0e_1x7')
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = slim.conv2d(branch_3, 192, [1, 1], scope='Conv2d_0b_1x1')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# mixed_6: 17 x 17 x 768.
with tf.variable_scope('Mixed_6d'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1x1')
branch_1 = slim.conv2d(branch_1, 160, [1, 7], scope='Conv2d_0b_1x7')
branch_1 = slim.conv2d(branch_1, 192, [7, 1], scope='Conv2d_0c_7x1')
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, 160, [1, 1], scope='Conv2d_0a_1x1')
branch_2 = slim.conv2d(branch_2, 160, [7, 1], scope='Conv2d_0b_7x1')
branch_2 = slim.conv2d(branch_2, 160, [1, 7], scope='Conv2d_0c_1x7')
branch_2 = slim.conv2d(branch_2, 160, [7, 1], scope='Conv2d_0d_7x1')
branch_2 = slim.conv2d(branch_2, 192, [1, 7], scope='Conv2d_0e_1x7')
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = slim.conv2d(branch_3, 192, [1, 1], scope='Conv2d_0b_1x1')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# mixed_7: 17 x 17 x 768.
with tf.variable_scope('Mixed_6e'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
branch_1 = slim.conv2d(branch_1, 192, [1, 7], scope='Conv2d_0b_1x7')
branch_1 = slim.conv2d(branch_1, 192, [7, 1], scope='Conv2d_0c_7x1')
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
branch_2 = slim.conv2d(branch_2, 192, [7, 1], scope='Conv2d_0b_7x1')
branch_2 = slim.conv2d(branch_2, 192, [1, 7], scope='Conv2d_0c_1x7')
branch_2 = slim.conv2d(branch_2, 192, [7, 1], scope='Conv2d_0d_7x1')
branch_2 = slim.conv2d(branch_2, 192, [1, 7], scope='Conv2d_0e_1x7')
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = slim.conv2d(branch_3, 192, [1, 1], scope='Conv2d_0b_1x1')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
end_points['Mixed_6e'] = net
# mixed_8: 8 x 8 x 1280.
with tf.variable_scope('Mixed_7a'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
branch_0 = slim.conv2d(branch_0, 320, [3, 3], stride=2,
padding='VALID', scope='Conv2d_1a_3x3')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net, 192, [1, 1], scope='Conv2d_0a_1x1')
branch_1 = slim.conv2d(branch_1, 192, [1, 7], scope='Conv2d_0b_1x7')
branch_1 = slim.conv2d(branch_1, 192, [7, 1], scope='Conv2d_0c_7x1')
branch_1 = slim.conv2d(branch_1, 192, [3, 3], stride=2,
padding='VALID', scope='Conv2d_1a_3x3')
with tf.variable_scope('Branch_2'):
branch_2 = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID',
scope='MaxPool_1a_3x3')
net = tf.concat([branch_0, branch_1, branch_2], 3)
# mixed_9: 8 x 8 x 2048.
with tf.variable_scope('Mixed_7b'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net, 320, [1, 1], scope='Conv2d_0a_1x1')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net, 384, [1, 1], scope='Conv2d_0a_1x1')
branch_1 = tf.concat([
slim.conv2d(branch_1, 384, [1, 3], scope='Conv2d_0b_1x3'),
slim.conv2d(branch_1, 384, [3, 1], scope='Conv2d_0b_3x1')], 3)
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, 448, [1, 1], scope='Conv2d_0a_1x1')
branch_2 = slim.conv2d(
branch_2, 384, [3, 3], scope='Conv2d_0b_3x3')
branch_2 = tf.concat([
slim.conv2d(branch_2, 384, [1, 3], scope='Conv2d_0c_1x3'),
slim.conv2d(branch_2, 384, [3, 1], scope='Conv2d_0d_3x1')], 3)
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = slim.conv2d(
branch_3, 192, [1, 1], scope='Conv2d_0b_1x1')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
# mixed_10: 8 x 8 x 2048.
with tf.variable_scope('Mixed_7c'):
with tf.variable_scope('Branch_0'):
branch_0 = slim.conv2d(net, 320, [1, 1], scope='Conv2d_0a_1x1')
with tf.variable_scope('Branch_1'):
branch_1 = slim.conv2d(net, 384, [1, 1], scope='Conv2d_0a_1x1')
branch_1 = tf.concat([
slim.conv2d(branch_1, 384, [1, 3], scope='Conv2d_0b_1x3'),
slim.conv2d(branch_1, 384, [3, 1], scope='Conv2d_0c_3x1')], 3)
with tf.variable_scope('Branch_2'):
branch_2 = slim.conv2d(net, 448, [1, 1], scope='Conv2d_0a_1x1')
branch_2 = slim.conv2d(
branch_2, 384, [3, 3], scope='Conv2d_0b_3x3')
branch_2 = tf.concat([
slim.conv2d(branch_2, 384, [1, 3], scope='Conv2d_0c_1x3'),
slim.conv2d(branch_2, 384, [3, 1], scope='Conv2d_0d_3x1')], 3)
with tf.variable_scope('Branch_3'):
branch_3 = slim.avg_pool2d(net, [3, 3], scope='AvgPool_0a_3x3')
branch_3 = slim.conv2d(
branch_3, 192, [1, 1], scope='Conv2d_0b_1x1')
net = tf.concat([branch_0, branch_1, branch_2, branch_3], 3)
return net, end_points
def inception_v3(inputs,
num_classes=1000,
is_training=True,
dropout_keep_prob=0.8,
prediction_fn=slim.softmax,
spatial_squeeze=True,
reuse=None,
scope='InceptionV3'):
with tf.variable_scope(scope, 'InceptionV3', [inputs, num_classes],
reuse=reuse) as scope:
with slim.arg_scope([slim.batch_norm, slim.dropout],
is_training=is_training):
net, end_points = inception_v3_base(inputs, scope=scope)
# Auxiliary Head logits
with slim.arg_scope([slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
stride=1, padding='SAME'):
aux_logits = end_points['Mixed_6e']
with tf.variable_scope('AuxLogits'):
aux_logits = slim.avg_pool2d(
aux_logits, [5, 5], stride=3, padding='VALID',
scope='AvgPool_1a_5x5')
aux_logits = slim.conv2d(aux_logits, 128, [1, 1],
scope='Conv2d_1b_1x1')
# Shape of feature map before the final layer.
aux_logits = slim.conv2d(
aux_logits, 768, [5,5],
weights_initializer=trunc_normal(0.01),
padding='VALID', scope='Conv2d_2a_5x5')
aux_logits = slim.conv2d(
aux_logits, num_classes, [1, 1], activation_fn=None,
normalizer_fn=None, weights_initializer=trunc_normal(0.001),
scope='Conv2d_2b_1x1')
if spatial_squeeze:
aux_logits = tf.squeeze(aux_logits, [1, 2], name='SpatialSqueeze')
end_points['AuxLogits'] = aux_logits
# Final pooling and prediction
with tf.variable_scope('Logits'):
net = slim.avg_pool2d(net, [8, 8], padding='VALID',
scope='AvgPool_1a_8x8')
# 1 x 1 x 2048
net = slim.dropout(net, keep_prob=dropout_keep_prob, scope='Dropout_1b')
end_points['PreLogits'] = net
# 2048
logits = slim.conv2d(net, num_classes, [1, 1], activation_fn=None,
normalizer_fn=None, scope='Conv2d_1c_1x1')
if spatial_squeeze:
logits = tf.squeeze(logits, [1, 2], name='SpatialSqueeze')
# 1000
end_points['Logits'] = logits
end_points['Predictions'] = prediction_fn(logits, scope='Predictions')
return logits, end_points
def inception_v3_arg_scope(weight_decay=0.00004,
stddev=0.1,
batch_norm_var_collection='moving_vars'):
batch_norm_params = {
'decay': 0.9997,
'epsilon': 0.001,
'updates_collections': tf.GraphKeys.UPDATE_OPS,
'variables_collections': {
'beta': None,
'gamma': None,
'moving_mean': [batch_norm_var_collection],
'moving_variance': [batch_norm_var_collection],
}
}
with slim.arg_scope([slim.conv2d, slim.fully_connected],
weights_regularizer=slim.l2_regularizer(weight_decay)):
with slim.arg_scope(
[slim.conv2d],
weights_initializer=trunc_normal(stddev),
activation_fn=tf.nn.relu,
normalizer_fn=slim.batch_norm,
normalizer_params=batch_norm_params) as sc:
return sc
from datetime import datetime
import math
import time
def time_tensorflow_run(session, target, info_string):
num_steps_burn_in = 10
total_duration = 0.0
total_duration_squared = 0.0
for i in range(num_batches + num_steps_burn_in):
start_time = time.time()
_ = session.run(target)
duration = time.time() - start_time
if i >= num_steps_burn_in:
if not i % 10:
print ('%s: step %d, duration = %.3f' %
(datetime.now(), i - num_steps_burn_in, duration))
total_duration += duration
total_duration_squared += duration * duration
mn = total_duration / num_batches
vr = total_duration_squared / num_batches - mn * mn
sd = math.sqrt(vr)
print ('%s: %s across %d steps, %.3f +/- %.3f sec / batch' %
(datetime.now(), info_string, num_batches, mn, sd))
batch_size = 32
height, width = 299, 299
inputs = tf.random_uniform((batch_size, height, width, 3))
with slim.arg_scope(inception_v3_arg_scope()):
logits, end_points = inception_v3(inputs, is_training=False)
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
num_batches=100
time_tensorflow_run(sess, logits, "Forward")
4、ResNet
"""
Typical use:
from tensorflow.contrib.slim.nets import resnet_v2
ResNet-101 for image classification into 1000 classes:
# inputs has shape [batch, 224, 224, 3]
with slim.arg_scope(resnet_v2.resnet_arg_scope(is_training)):
net, end_points = resnet_v2.resnet_v2_101(inputs, 1000)
ResNet-101 for semantic segmentation into 21 classes:
# inputs has shape [batch, 513, 513, 3]
with slim.arg_scope(resnet_v2.resnet_arg_scope(is_training)):
net, end_points = resnet_v2.resnet_v2_101(inputs,
21,
global_pool=False,
output_stride=16)
"""
import collections
import tensorflow as tf
slim = tf.contrib.slim
class Block(collections.namedtuple('Block', ['scope', 'unit_fn', 'args'])):
"""A named tuple describing a ResNet block.
Its parts are:
scope: The scope of the `Block`.
unit_fn: The ResNet unit function which takes as input a `Tensor` and
returns another `Tensor` with the output of the ResNet unit.
args: A list of length equal to the number of units in the `Block`. The list
contains one (depth, depth_bottleneck, stride) tuple for each unit in the
block to serve as argument to unit_fn.
"""
def subsample(inputs, factor, scope=None):
"""Subsamples the input along the spatial dimensions.
Args:
inputs: A `Tensor` of size [batch, height_in, width_in, channels].
factor: The subsampling factor.
scope: Optional variable_scope.
Returns:
output: A `Tensor` of size [batch, height_out, width_out, channels] with the
input, either intact (if factor == 1) or subsampled (if factor > 1).
"""
if factor == 1:
return inputs
else:
return slim.max_pool2d(inputs, [1, 1], stride=factor, scope=scope)
def conv2d_same(inputs, num_outputs, kernel_size, stride, scope=None):
"""Strided 2-D convolution with 'SAME' padding.
When stride > 1, then we do explicit zero-padding, followed by conv2d with
'VALID' padding.
Note that
net = conv2d_same(inputs, num_outputs, 3, stride=stride)
is equivalent to
net = slim.conv2d(inputs, num_outputs, 3, stride=1, padding='SAME')
net = subsample(net, factor=stride)
whereas
net = slim.conv2d(inputs, num_outputs, 3, stride=stride, padding='SAME')
is different when the input's height or width is even, which is why we add the
current function. For more details, see ResnetUtilsTest.testConv2DSameEven().
Args:
inputs: A 4-D tensor of size [batch, height_in, width_in, channels].
num_outputs: An integer, the number of output filters.
kernel_size: An int with the kernel_size of the filters.
stride: An integer, the output stride.
rate: An integer, rate for atrous convolution.
scope: Scope.
Returns:
output: A 4-D tensor of size [batch, height_out, width_out, channels] with
the convolution output.
"""
if stride == 1:
return slim.conv2d(inputs, num_outputs, kernel_size, stride=1,
padding='SAME', scope=scope)
else:
#kernel_size_effective = kernel_size + (kernel_size - 1) * (rate - 1)
pad_total = kernel_size - 1
pad_beg = pad_total // 2
pad_end = pad_total - pad_beg
inputs = tf.pad(inputs,
[[0, 0], [pad_beg, pad_end], [pad_beg, pad_end], [0, 0]])
return slim.conv2d(inputs, num_outputs, kernel_size, stride=stride,
padding='VALID', scope=scope)
@slim.add_arg_scope
def stack_blocks_dense(net, blocks,
outputs_collections=None):
"""Stacks ResNet `Blocks` and controls output feature density.
First, this function creates scopes for the ResNet in the form of
'block_name/unit_1', 'block_name/unit_2', etc.
Args:
net: A `Tensor` of size [batch, height, width, channels].
blocks: A list of length equal to the number of ResNet `Blocks`. Each
element is a ResNet `Block` object describing the units in the `Block`.
outputs_collections: Collection to add the ResNet block outputs.
Returns:
net: Output tensor
"""
for block in blocks:
with tf.variable_scope(block.scope, 'block', [net]) as sc:
for i, unit in enumerate(block.args):
with tf.variable_scope('unit_%d' % (i + 1), values=[net]):
unit_depth, unit_depth_bottleneck, unit_stride = unit
net = block.unit_fn(net,
depth=unit_depth,
depth_bottleneck=unit_depth_bottleneck,
stride=unit_stride)
net = slim.utils.collect_named_outputs(outputs_collections, sc.name, net)
return net
def resnet_arg_scope(is_training=True,
weight_decay=0.0001,
batch_norm_decay=0.997,
batch_norm_epsilon=1e-5,
batch_norm_scale=True):
"""Defines the default ResNet arg scope.
TODO(gpapan): The batch-normalization related default values above are
appropriate for use in conjunction with the reference ResNet models
released at https://github.com/KaimingHe/deep-residual-networks. When
training ResNets from scratch, they might need to be tuned.
Args:
is_training: Whether or not we are training the parameters in the batch
normalization layers of the model.
weight_decay: The weight decay to use for regularizing the model.
batch_norm_decay: The moving average decay when estimating layer activation
statistics in batch normalization.
batch_norm_epsilon: Small constant to prevent division by zero when
normalizing activations by their variance in batch normalization.
batch_norm_scale: If True, uses an explicit `gamma` multiplier to scale the
activations in the batch normalization layer.
Returns:
An `arg_scope` to use for the resnet models.
"""
batch_norm_params = {
'is_training': is_training,
'decay': batch_norm_decay,
'epsilon': batch_norm_epsilon,
'scale': batch_norm_scale,
'updates_collections': tf.GraphKeys.UPDATE_OPS,
}
with slim.arg_scope(
[slim.conv2d],
weights_regularizer=slim.l2_regularizer(weight_decay),
weights_initializer=slim.variance_scaling_initializer(),
activation_fn=tf.nn.relu,
normalizer_fn=slim.batch_norm,
normalizer_params=batch_norm_params):
with slim.arg_scope([slim.batch_norm], **batch_norm_params):
# The following implies padding='SAME' for pool1, which makes feature
# alignment easier for dense prediction tasks. This is also used in
# https://github.com/facebook/fb.resnet.torch. However the accompanying
# code of 'Deep Residual Learning for Image Recognition' uses
# padding='VALID' for pool1. You can switch to that choice by setting
# slim.arg_scope([slim.max_pool2d], padding='VALID').
with slim.arg_scope([slim.max_pool2d], padding='SAME') as arg_sc:
return arg_sc
@slim.add_arg_scope
def bottleneck(inputs, depth, depth_bottleneck, stride,
outputs_collections=None, scope=None):
"""Bottleneck residual unit variant with BN before convolutions.
This is the full preactivation residual unit variant proposed in [2]. See
Fig. 1(b) of [2] for its definition. Note that we use here the bottleneck
variant which has an extra bottleneck layer.
When putting together two consecutive ResNet blocks that use this unit, one
should use stride = 2 in the last unit of the first block.
Args:
inputs: A tensor of size [batch, height, width, channels].
depth: The depth of the ResNet unit output.
depth_bottleneck: The depth of the bottleneck layers.
stride: The ResNet unit's stride. Determines the amount of downsampling of
the units output compared to its input.
rate: An integer, rate for atrous convolution.
outputs_collections: Collection to add the ResNet unit output.
scope: Optional variable_scope.
Returns:
The ResNet unit's output.
"""
with tf.variable_scope(scope, 'bottleneck_v2', [inputs]) as sc:
depth_in = slim.utils.last_dimension(inputs.get_shape(), min_rank=4)
preact = slim.batch_norm(inputs, activation_fn=tf.nn.relu, scope='preact')
if depth == depth_in:
shortcut = subsample(inputs, stride, 'shortcut')
else:
shortcut = slim.conv2d(preact, depth, [1, 1], stride=stride,
normalizer_fn=None, activation_fn=None,
scope='shortcut')
residual = slim.conv2d(preact, depth_bottleneck, [1, 1], stride=1,
scope='conv1')
residual = conv2d_same(residual, depth_bottleneck, 3, stride,
scope='conv2')
residual = slim.conv2d(residual, depth, [1, 1], stride=1,
normalizer_fn=None, activation_fn=None,
scope='conv3')
output = shortcut + residual
return slim.utils.collect_named_outputs(outputs_collections,
sc.name,
output)
def resnet_v2(inputs,
blocks,
num_classes=None,
global_pool=True,
include_root_block=True,
reuse=None,
scope=None):
"""Generator for v2 (preactivation) ResNet models.
This function generates a family of ResNet v2 models. See the resnet_v2_*()
methods for specific model instantiations, obtained by selecting different
block instantiations that produce ResNets of various depths.
Args:
inputs: A tensor of size [batch, height_in, width_in, channels].
blocks: A list of length equal to the number of ResNet blocks. Each element
is a resnet_utils.Block object describing the units in the block.
num_classes: Number of predicted classes for classification tasks. If None
we return the features before the logit layer.
include_root_block: If True, include the initial convolution followed by
max-pooling, if False excludes it. If excluded, `inputs` should be the
results of an activation-less convolution.
reuse: whether or not the network and its variables should be reused. To be
able to reuse 'scope' must be given.
scope: Optional variable_scope.
Returns:
net: A rank-4 tensor of size [batch, height_out, width_out, channels_out].
If global_pool is False, then height_out and width_out are reduced by a
factor of output_stride compared to the respective height_in and width_in,
else both height_out and width_out equal one. If num_classes is None, then
net is the output of the last ResNet block, potentially after global
average pooling. If num_classes is not None, net contains the pre-softmax
activations.
end_points: A dictionary from components of the network to the corresponding
activation.
Raises:
ValueError: If the target output_stride is not valid.
"""
with tf.variable_scope(scope, 'resnet_v2', [inputs], reuse=reuse) as sc:
end_points_collection = sc.original_name_scope + '_end_points'
with slim.arg_scope([slim.conv2d, bottleneck,
stack_blocks_dense],
outputs_collections=end_points_collection):
net = inputs
if include_root_block:
# We do not include batch normalization or activation functions in conv1
# because the first ResNet unit will perform these. Cf. Appendix of [2].
with slim.arg_scope([slim.conv2d],
activation_fn=None, normalizer_fn=None):
net = conv2d_same(net, 64, 7, stride=2, scope='conv1')
net = slim.max_pool2d(net, [3, 3], stride=2, scope='pool1')
net = stack_blocks_dense(net, blocks)
# This is needed because the pre-activation variant does not have batch
# normalization or activation functions in the residual unit output. See
# Appendix of [2].
net = slim.batch_norm(net, activation_fn=tf.nn.relu, scope='postnorm')
if global_pool:
# Global average pooling.
net = tf.reduce_mean(net, [1, 2], name='pool5', keep_dims=True)
if num_classes is not None:
net = slim.conv2d(net, num_classes, [1, 1], activation_fn=None,
normalizer_fn=None, scope='logits')
# Convert end_points_collection into a dictionary of end_points.
end_points = slim.utils.convert_collection_to_dict(end_points_collection)
if num_classes is not None:
end_points['predictions'] = slim.softmax(net, scope='predictions')
return net, end_points
def resnet_v2_50(inputs,
num_classes=None,
global_pool=True,
reuse=None,
scope='resnet_v2_50'):
"""ResNet-50 model of [1]. See resnet_v2() for arg and return description."""
blocks = [
Block('block1', bottleneck, [(256, 64, 1)] * 2 + [(256, 64, 2)]),
Block(
'block2', bottleneck, [(512, 128, 1)] * 3 + [(512, 128, 2)]),
Block(
'block3', bottleneck, [(1024, 256, 1)] * 5 + [(1024, 256, 2)]),
Block(
'block4', bottleneck, [(2048, 512, 1)] * 3)]
return resnet_v2(inputs, blocks, num_classes, global_pool,
include_root_block=True, reuse=reuse, scope=scope)
def resnet_v2_101(inputs,
num_classes=None,
global_pool=True,
reuse=None,
scope='resnet_v2_101'):
"""ResNet-101 model of [1]. See resnet_v2() for arg and return description."""
blocks = [
Block(
'block1', bottleneck, [(256, 64, 1)] * 2 + [(256, 64, 2)]),
Block(
'block2', bottleneck, [(512, 128, 1)] * 3 + [(512, 128, 2)]),
Block(
'block3', bottleneck, [(1024, 256, 1)] * 22 + [(1024, 256, 2)]),
Block(
'block4', bottleneck, [(2048, 512, 1)] * 3)]
return resnet_v2(inputs, blocks, num_classes, global_pool,
include_root_block=True, reuse=reuse, scope=scope)
def resnet_v2_152(inputs,
num_classes=None,
global_pool=True,
reuse=None,
scope='resnet_v2_152'):
"""ResNet-152 model of [1]. See resnet_v2() for arg and return description."""
blocks = [
Block(
'block1', bottleneck, [(256, 64, 1)] * 2 + [(256, 64, 2)]),
Block(
'block2', bottleneck, [(512, 128, 1)] * 7 + [(512, 128, 2)]),
Block(
'block3', bottleneck, [(1024, 256, 1)] * 35 + [(1024, 256, 2)]),
Block(
'block4', bottleneck, [(2048, 512, 1)] * 3)]
return resnet_v2(inputs, blocks, num_classes, global_pool,
include_root_block=True, reuse=reuse, scope=scope)
def resnet_v2_200(inputs,
num_classes=None,
global_pool=True,
reuse=None,
scope='resnet_v2_200'):
"""ResNet-200 model of [2]. See resnet_v2() for arg and return description."""
blocks = [
Block(
'block1', bottleneck, [(256, 64, 1)] * 2 + [(256, 64, 2)]),
Block(
'block2', bottleneck, [(512, 128, 1)] * 23 + [(512, 128, 2)]),
Block(
'block3', bottleneck, [(1024, 256, 1)] * 35 + [(1024, 256, 2)]),
Block(
'block4', bottleneck, [(2048, 512, 1)] * 3)]
return resnet_v2(inputs, blocks, num_classes, global_pool,
include_root_block=True, reuse=reuse, scope=scope)
from datetime import datetime
import math
import time
def time_tensorflow_run(session, target, info_string):
num_steps_burn_in = 10
total_duration = 0.0
total_duration_squared = 0.0
for i in range(num_batches + num_steps_burn_in):
start_time = time.time()
_ = session.run(target)
duration = time.time() - start_time
if i >= num_steps_burn_in:
if not i % 10:
print ('%s: step %d, duration = %.3f' %
(datetime.now(), i - num_steps_burn_in, duration))
total_duration += duration
total_duration_squared += duration * duration
mn = total_duration / num_batches
vr = total_duration_squared / num_batches - mn * mn
sd = math.sqrt(vr)
print ('%s: %s across %d steps, %.3f +/- %.3f sec / batch' %
(datetime.now(), info_string, num_batches, mn, sd))
batch_size = 32
height, width = 224, 224
inputs = tf.random_uniform((batch_size, height, width, 3))
with slim.arg_scope(resnet_arg_scope(is_training=False)):
net, end_points = resnet_v2_152(inputs, 1000)
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
num_batches=100
time_tensorflow_run(sess, net, "Forward")
209
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
