def Linear(data,
num_filter=1,
kernel=(1, 1),
stride=(1, 1),
pad=(0, 0),
num_group=1,
name=None,
suffix=''):
conv = sym.Convolution(data=data,
num_filter=num_filter,
kernel=kernel,
num_group=num_group,
stride=stride,
pad=pad,
no_bias=True,
name='%s%s_conv2d' % (name, suffix))
bn = sym.BatchNorm(data=conv,
name='%s%s_batchnorm' % (name, suffix),
fix_gamma=False,
momentum=config.bn_mom)
return bn
def ConvFactory(data,
num_filter,
kernel,
stride=(1, 1),
pad=(0, 0),
name=None,
suffix='',
attr={}):
conv = mxy.Convolution(data=data,
num_filter=num_filter,
kernel=kernel,
stride=stride,
pad=pad,
name='conv_%s%s' % (name, suffix))
bn = mxy.BatchNorm(data=conv,
fix_gamma=fix_gamma,
eps=eps,
momentum=bn_mom,
name='bn_%s%s' % (name, suffix))
act = mxy.Activation(data=bn,
act_type='relu',
name='relu_%s%s' % (name, suffix),
attr=attr)
return act
def conv_bn_relu_pool_siamese(input_a,
input_b,
kernel,
num_filter,
pad,
stride,
name_postfix,
use_pooling=False,
p_kernel=None,
p_stride=None,
use_batch_norm=True):
conv_weight = mxs.Variable(name='conv' + name_postfix + '_weight')
conv_bias = mxs.Variable(name='conv' + name_postfix + '_bias')
conv_a = mxs.Convolution(data=input_a,
kernel=kernel,
num_filter=num_filter,
pad=pad,
stride=stride,
name='conv' + name_postfix + "_a",
weight=conv_weight,
bias=conv_bias)
conv_b = mxs.Convolution(data=input_b,
kernel=kernel,
num_filter=num_filter,
pad=pad,
stride=stride,
name='conv' + name_postfix + "_b",
weight=conv_weight,
bias=conv_bias)
if use_batch_norm:
bn_gamma = mxs.Variable(name='bn' + name_postfix + '_gamma')
bn_beta = mxs.Variable(name='bn' + name_postfix + '_beta')
bn_moving_mean = mxs.Variable(name='bn' + name_postfix +
'_moving_mean')
bn_moving_var = mxs.Variable(name='bn' + name_postfix +
'_moving_var')
batch_norm_a = mxs.BatchNorm(data=conv_a,
name='bn' + name_postfix + '_a',
gamma=bn_gamma,
beta=bn_beta,
moving_mean=bn_moving_mean,
moving_var=bn_moving_var)
batch_norm_b = mxs.BatchNorm(data=conv_b,
name='bn' + name_postfix + '_b',
gamma=bn_gamma,
beta=bn_beta,
moving_mean=bn_moving_mean,
moving_var=bn_moving_var)
else:
batch_norm_a = conv_a
batch_norm_b = conv_b
relu_a = mxs.relu(data=batch_norm_a, name='relu' + name_postfix + '_a')
relu_b = mxs.relu(data=batch_norm_b, name='relu' + name_postfix + '_b')
if use_pooling:
out_a = mxs.Pooling(data=relu_a,
kernel=p_kernel,
pool_type='max',
stride=p_stride,
name='pool' + name_postfix + '_a')
out_b = mxs.Pooling(data=relu_b,
kernel=p_kernel,
pool_type='max',
stride=p_stride,
name='pool' + name_postfix + '_b')
else:
out_a = relu_a
out_b = relu_b
return out_a, out_b
def siamese_simp_net():
def conv_bn_relu_pool_siamese(input_a,
input_b,
kernel,
num_filter,
pad,
stride,
name_postfix,
use_pooling=False,
p_kernel=None,
p_stride=None,
use_batch_norm=True):
conv_weight = mxs.Variable(name='conv' + name_postfix + '_weight')
conv_bias = mxs.Variable(name='conv' + name_postfix + '_bias')
conv_a = mxs.Convolution(data=input_a,
kernel=kernel,
num_filter=num_filter,
pad=pad,
stride=stride,
name='conv' + name_postfix + "_a",
weight=conv_weight,
bias=conv_bias)
conv_b = mxs.Convolution(data=input_b,
kernel=kernel,
num_filter=num_filter,
pad=pad,
stride=stride,
name='conv' + name_postfix + "_b",
weight=conv_weight,
bias=conv_bias)
if use_batch_norm:
bn_gamma = mxs.Variable(name='bn' + name_postfix + '_gamma')
bn_beta = mxs.Variable(name='bn' + name_postfix + '_beta')
bn_moving_mean = mxs.Variable(name='bn' + name_postfix +
'_moving_mean')
bn_moving_var = mxs.Variable(name='bn' + name_postfix +
'_moving_var')
batch_norm_a = mxs.BatchNorm(data=conv_a,
name='bn' + name_postfix + '_a',
gamma=bn_gamma,
beta=bn_beta,
moving_mean=bn_moving_mean,
moving_var=bn_moving_var)
batch_norm_b = mxs.BatchNorm(data=conv_b,
name='bn' + name_postfix + '_b',
gamma=bn_gamma,
beta=bn_beta,
moving_mean=bn_moving_mean,
moving_var=bn_moving_var)
else:
batch_norm_a = conv_a
batch_norm_b = conv_b
relu_a = mxs.relu(data=batch_norm_a, name='relu' + name_postfix + '_a')
relu_b = mxs.relu(data=batch_norm_b, name='relu' + name_postfix + '_b')
if use_pooling:
out_a = mxs.Pooling(data=relu_a,
kernel=p_kernel,
pool_type='max',
stride=p_stride,
name='pool' + name_postfix + '_a')
out_b = mxs.Pooling(data=relu_b,
kernel=p_kernel,
pool_type='max',
stride=p_stride,
name='pool' + name_postfix + '_b')
else:
out_a = relu_a
out_b = relu_b
return out_a, out_b
data_a = mxs.Variable('data_a')
data_b = mxs.Variable('data_b')
c1_a, c1_b = conv_bn_relu_pool_siamese(data_a,
data_b,
kernel=(3, 3),
num_filter=64,
pad=(1, 1),
stride=(1, 1),
name_postfix='1',
use_pooling=False)
c1_0_a, c1_0_b = conv_bn_relu_pool_siamese(c1_a,
c1_b,
kernel=(3, 3),
num_filter=32,
pad=(1, 1),
stride=(1, 1),
name_postfix='1_0',
use_pooling=False)
c2_a, c2_b = conv_bn_relu_pool_siamese(c1_0_a,
c1_0_b,
kernel=(3, 3),
num_filter=32,
pad=(1, 1),
stride=(1, 1),
name_postfix='2',
use_pooling=False)
c2_1_a, c2_1_b = conv_bn_relu_pool_siamese(c2_a,
c2_b,
kernel=(3, 3),
num_filter=32,
pad=(1, 1),
stride=(1, 1),
name_postfix='2_1',
use_pooling=True,
p_kernel=(2, 2),
p_stride=(2, 2))
c2_2_a, c2_2_b = conv_bn_relu_pool_siamese(c2_1_a,
c2_1_b,
kernel=(3, 3),
num_filter=32,
pad=(1, 1),
stride=(1, 1),
name_postfix='2_2',
use_pooling=False)
c3_a, c3_b = conv_bn_relu_pool_siamese(c2_2_a,
c2_2_b,
kernel=(3, 3),
num_filter=32,
pad=(1, 1),
stride=(1, 1),
name_postfix='3',
use_pooling=False)
# conv4
conv4_weight = mxs.Variable(name='conv4_weight')
conv4_bias = mxs.Variable(name='conv4_bias')
conv4_a = mxs.Convolution(data=c3_a,
kernel=(3, 3),
num_filter=64,
pad=(1, 1),
stride=(1, 1),
name='conv4_a',
weight=conv4_weight,
bias=conv4_bias) # xavier
conv4_b = mxs.Convolution(data=c3_b,
kernel=(3, 3),
num_filter=64,
pad=(1, 1),
stride=(1, 1),
name='conv4_b',
weight=conv4_weight,
bias=conv4_bias) # xavier
maxp4_a = mxs.Pooling(data=conv4_a,
kernel=(2, 2),
pool_type='max',
stride=(2, 2),
name='pool4_a')
maxp4_b = mxs.Pooling(data=conv4_b,
kernel=(2, 2),
pool_type='max',
stride=(2, 2),
name='pool4_b')
bn4_gamma = mxs.Variable(name='bn4_gamma')
bn4_beta = mxs.Variable(name='bn4_beta')
bn4_moving_mean = mxs.Variable(name='bn4_moving_mean')
bn4_moving_var = mxs.Variable(name='bn4_moving_var')
batch_norm_4_a = mxs.BatchNorm(data=maxp4_a,
name='bn4_a',
gamma=bn4_gamma,
beta=bn4_beta,
moving_mean=bn4_moving_mean,
moving_var=bn4_moving_var)
batch_norm_4_b = mxs.BatchNorm(data=maxp4_b,
name='bn4_b',
gamma=bn4_gamma,
beta=bn4_beta,
moving_mean=bn4_moving_mean,
moving_var=bn4_moving_var)
relu4_a = mxs.relu(data=batch_norm_4_a, name='relu4')
relu4_b = mxs.relu(data=batch_norm_4_b, name='relu4')
c4_1_a, c4_1_b = conv_bn_relu_pool_siamese(relu4_a,
relu4_b,
kernel=(3, 3),
num_filter=64,
pad=(1, 1),
stride=(1, 1),
name_postfix='4_1',
use_pooling=False)
c4_2_a, c4_2_b = conv_bn_relu_pool_siamese(c4_1_a,
c4_1_b,
kernel=(3, 3),
num_filter=64,
pad=(1, 1),
stride=(1, 1),
name_postfix='4_2',
use_pooling=True,
p_kernel=(2, 2),
p_stride=(2, 2))
c4_0_a, c4_0_b = conv_bn_relu_pool_siamese(c4_2_a,
c4_2_b,
kernel=(3, 3),
num_filter=128,
pad=(1, 1),
stride=(1, 1),
name_postfix='4_0',
use_pooling=False)
cccp4_a, cccp4_b = conv_bn_relu_pool_siamese(c4_0_a,
c4_0_b,
kernel=(1, 1),
num_filter=256,
pad=[],
stride=(1, 1),
name_postfix='_cccp4',
use_pooling=False,
use_batch_norm=False)
cccp5_a, cccp5_b = conv_bn_relu_pool_siamese(cccp4_a,
cccp4_b,
kernel=(1, 1),
num_filter=64,
pad=[],
stride=(1, 1),
name_postfix='_cccp5',
use_pooling=True,
p_kernel=(2, 2),
p_stride=(2, 2),
use_batch_norm=False)
cccp6_a, cccp6_b = conv_bn_relu_pool_siamese(cccp5_a,
cccp5_b,
kernel=(3, 3),
num_filter=64,
pad=(2, 2),
stride=(1, 1),
name_postfix='_cccp6',
use_pooling=False,
use_batch_norm=False)
flat_a = mxs.flatten(cccp6_a)
flat_b = mxs.flatten(cccp6_b)
return flat_a, flat_b