def densenet_backbone(image, qw=1):
with argscope(Conv2DQuant,
nl=tf.identity,
use_bias=False,
W_init=variance_scaling_initializer(mode='FAN_IN'),
data_format=get_arg_scope()['Conv2D']['data_format'],
nbit=qw,
is_quant=True if qw > 0 else False):
logits = (
LinearWrap(image).Conv2DQuant('conv1',
2 * GROWTH_RATE,
7,
stride=2,
nl=BNReLU,
is_quant=False).MaxPooling(
'pool1',
shape=3,
stride=2,
padding='SAME')
# 56
.apply(add_dense_block, 'block0', 6)
# 28
.apply(add_dense_block, 'block1', 12)
# 14
.apply(add_dense_block, 'block2', 24)
# 7
.apply(add_dense_block, 'block3', 16, last=True).BNReLU(
'bnrelu_last').GlobalAvgPooling('gap').FullyConnected(
'linear',
out_dim=1000,
nl=tf.identity,
W_init=variance_scaling_initializer(mode='FAN_IN'))())
return logits
def vgg_backbone(image, qw=1):
with argscope(Conv2DQuant, nl=tf.identity, use_bias=False,
W_init=variance_scaling_initializer(mode='FAN_IN'),
data_format=get_arg_scope()['Conv2D']['data_format'],
nbit=qw):
logits = (LinearWrap(image)
.Conv2DQuant('conv1', 96, 7, stride=2, nl=tf.nn.relu, is_quant=False)
.MaxPooling('pool1', shape=2, stride=2, padding='VALID')
# 56
.BNReLUQuant('bnquant2_0')
.Conv2DQuant('conv2_1', 256, 3, nl=getBNReLUQuant)
.Conv2DQuant('conv2_2', 256, 3, nl=getBNReLUQuant)
.Conv2DQuant('conv2_3', 256, 3)
.MaxPooling('pool2', shape=2, stride=2, padding='VALID')
# 28
.BNReLUQuant('bnquant3_0')
.Conv2DQuant('conv3_1', 512, 3, nl=getBNReLUQuant)
.Conv2DQuant('conv3_2', 512, 3, nl=getBNReLUQuant)
.Conv2DQuant('conv3_3', 512, 3)
.MaxPooling('pool3', shape=2, stride=2, padding='VALID')
# 14
.BNReLUQuant('bnquant4_0')
.Conv2DQuant('conv4_1', 512, 3, nl=getBNReLUQuant)
.Conv2DQuant('conv4_2', 512, 3, nl=getBNReLUQuant)
.Conv2DQuant('conv4_3', 512, 3)
.MaxPooling('pool4', shape=2, stride=2, padding='VALID')
# 7
.BNReLUQuant('bnquant5')
.Conv2DQuant('fc5', 4096, 7, nl=getfcBNReLUQuant, padding='VALID', use_bias=True)
.Conv2DQuant('fc6', 4096, 1, nl=getfcBNReLU, padding='VALID', use_bias=True)
.FullyConnected('fc7', out_dim=1000, nl=tf.identity, W_init=variance_scaling_initializer(mode='FAN_IN'))())
return logits
def inception_block(l, name, ch_1x1, ch_3x3, ch_5x5, is_last_block=False, is_last=False):
data_format = get_arg_scope()['Conv2DQuant']['data_format']
with tf.variable_scope(name):
conv1x1 = Conv2DQuant('1x1', l, ch_1x1, 1, nl=getBNReLUQuant if not is_last_block else tf.identity)
conv3x3_reduce = Conv2DQuant('3x3_reduce', l, ch_3x3, 1, nl=getBNReLUQuant)
conv3x3 = Conv2DQuant('3x3', conv3x3_reduce, ch_3x3, 3, nl=getBNReLUQuant if not is_last_block else tf.identity)
conv5x5_reduce = Conv2DQuant('5x5_reduce', l, ch_5x5, 1, nl=getBNReLUQuant)
conv5x5 = Conv2DQuant('5x5', conv5x5_reduce, ch_5x5, 5, nl=getBNReLUQuant if not is_last_block else tf.identity)
if is_last_block and not is_last:
conv1x1 = MaxPooling('pool_1x1', conv1x1, shape=3, stride=2, padding='SAME')
conv1x1 = BNReLU('conv1x1_bn', conv1x1)
conv1x1 = QuantizedActiv('conv1x1_quant', conv1x1)
conv3x3 = MaxPooling('pool_3x3', conv3x3, shape=3, stride=2, padding='SAME')
conv3x3 = BNReLU('conv3x3_bn', conv3x3)
conv3x3 = QuantizedActiv('conv3x3_quant', conv3x3)
conv5x5 = MaxPooling('pool_5x5', conv5x5, shape=3, stride=2, padding='SAME')
conv5x5 = BNReLU('conv5x5_bn', conv5x5)
conv5x5 = QuantizedActiv('conv5x5_quant', conv5x5)
l = tf.concat([
conv1x1,
conv3x3,
conv5x5], 1 if data_format == 'NCHW' else 3, name='concat')
if is_last:
l = BNReLU('output_bn', l)
return l
def googlenet_backbone(image, qw=1):
with argscope(Conv2DQuant, nl=tf.identity, use_bias=False,
W_init=variance_scaling_initializer(mode='FAN_IN'),
data_format=get_arg_scope()['Conv2D']['data_format'],
nbit=qw,
is_quant=True if qw > 0 else False):
logits = (LinearWrap(image)
.Conv2DQuant('conv1', 64, 7, stride=2, is_quant=False)
.MaxPooling('pool1', shape=3, stride=2, padding='SAME')
.BNReLUQuant('pool1/out')
.Conv2DQuant('conv2/3x3_reduce', 192, 1, nl=getBNReLUQuant)
.Conv2DQuant('conv2/3x3', 192, 3)
.MaxPooling('pool2', shape=3, stride=2, padding='SAME')
.BNReLUQuant('pool2/out')
.apply(inception_block, 'incpetion_3a', 96, 128, 32)
.apply(inception_block, 'incpetion_3b', 192, 192, 96, is_last_block=True)
.apply(inception_block, 'incpetion_4a', 256, 208, 48)
.apply(inception_block, 'incpetion_4b', 224, 224, 64)
.apply(inception_block, 'incpetion_4c', 192, 256, 64)
.apply(inception_block, 'incpetion_4d', 176, 288, 64)
.apply(inception_block, 'incpetion_4e', 384, 320, 128, is_last_block=True)
.apply(inception_block, 'incpetion_5a', 384, 320, 128)
.apply(inception_block, 'incpetion_5b', 512, 384, 128, is_last_block=True, is_last=True)
.GlobalAvgPooling('pool5')
.FullyConnected('linear', out_dim=1000, nl=tf.identity)())
return logits
def resnet_shortcut(l: tf.Tensor,
n_out: int,
stride: int,
isDownsampling: bool,
activation=tf.identity):
data_format = get_arg_scope()["Conv2D"]["data_format"]
n_in = l.get_shape().as_list()[1 if data_format in
["NCHW", "channels_first"] else 3]
if n_in != n_out or stride != 1: # change dimension when channel is not the same
if isDownsampling:
return Conv2D("convshortcut",
l,
n_out,
1,
strides=stride,
activation=activation)
else:
return Conv2DTranspose("convshortcut",
l,
n_out,
1,
strides=stride,
activation=activation)
else:
return l
def resnet_shortcut(l, n_out, stride):
data_format = get_arg_scope()['Conv2D']['data_format']
n_in = l.get_shape().as_list()[1 if data_format == 'NCHW' else 3]
if n_in != n_out: # change dimension when channel is not the same
return Conv2D('convshortcut', l, n_out, 1, stride=stride)
else:
return l
def resnet_backbone(image, num_blocks, group_func, block_func, qw=1):
with argscope(Conv2DQuant,
nl=tf.identity,
use_bias=False,
W_init=variance_scaling_initializer(mode='FAN_OUT'),
data_format=get_arg_scope()['Conv2D']['data_format'],
nbit=qw):
logits = (LinearWrap(image).Conv2DQuant(
'conv0', 64, 7, stride=2, nl=BNReLU, is_quant=False).MaxPooling(
'pool0', shape=3, stride=2, padding='SAME').apply(
group_func, 'group0', block_func, 64, num_blocks[0],
1).apply(group_func, 'group1', block_func, 128,
num_blocks[1],
2).apply(group_func, 'group2', block_func, 256,
num_blocks[2],
2).apply(group_func,
'group3',
block_func,
512,
num_blocks[3],
2,
is_last=True).GlobalAvgPooling(
'gap').FullyConnected(
'linear',
1000,
nl=tf.identity)())
return logits
def se_resnet_bottleneck(l, ch_out, stride, rate):
shortcut = l
l = Conv2D('conv1', l, ch_out, 1, dilation_rate=rate, nl=BNReLU)
l = Conv2D('conv2',
l,
ch_out,
3,
stride=stride,
dilation_rate=rate,
nl=BNReLU)
l = Conv2D('conv3',
l,
ch_out * 4,
1,
dilation_rate=rate,
nl=get_bn(zero_init=True))
squeeze = GlobalAvgPooling('gap', l)
squeeze = FullyConnected('fc1', squeeze, ch_out // 4, nl=tf.nn.relu)
squeeze = FullyConnected('fc2', squeeze, ch_out * 4, nl=tf.nn.sigmoid)
data_format = get_arg_scope()['Conv2D']['data_format']
ch_ax = 1 if data_format == 'NCHW' else 3
shape = [-1, 1, 1, 1]
shape[ch_ax] = ch_out * 4
l = l * tf.reshape(squeeze, shape)
return l + resnet_shortcut(
shortcut, ch_out * 4, stride, rate, nl=get_bn(zero_init=False))
def resnet_shortcut(l, n_out, stride, activation=tf.identity):
data_format = get_arg_scope()['mpusim_conv2d']['data_format']
n_in = l.get_shape().as_list()[1 if data_format in ['NCHW', 'channels_first'] else 3]
if n_in != n_out: # change dimension when channel is not the same
return mpusim_conv2d('convshortcut', l, n_out, 1, strides=stride, activation=activation)
else:
return l
def resnet_shortcut(l, n_out, stride, nl=tf.identity):
data_format = get_arg_scope()['Conv2D']['data_format']
n_in = l.get_shape().as_list()[1 if data_format == 'NCHW' else 3]
if n_in != n_out: # change dimension when channel is not the same
return Conv2D('convshortcut', l, n_out, 1, stride=stride, nl=nl)
else:
return l
def resnet_shortcut(l, n_out, stride, activation=tf.identity):
data_format = get_arg_scope()['Conv2D']['data_format']
n_in = l.get_shape().as_list()[1 if data_format in ['NCHW', 'channels_first'] else 3]
if n_in != n_out: # change dimension when channel is not the same
return Conv2D('convshortcut', l, n_out, 1, strides=stride, activation=activation)
else:
return l
def resnet_shortcut(l, n_out, stride, nl=tf.identity):
data_format = get_arg_scope()['Conv2D']['data_format']
n_in = l.get_shape().as_list()[1 if data_format == 'NCHW' else 3]
if n_in != n_out: # change dimension when channel is not the same
if stride == 2:
l = l[:, :, :-1, :-1]
return Conv2D('convshortcut', l, n_out, 1,
stride=stride, padding='VALID', nl=nl)
else:
return Conv2D('convshortcut', l, n_out, 1,
stride=stride, nl=nl)
else:
return l
def resnet_shortcut(l, n_out, stride, activation=tf.identity):
data_format = get_arg_scope()['Conv2D']['data_format']
n_in = l.get_shape().as_list()[1 if data_format in ['NCHW', 'channels_first'] else 3]
if n_in != n_out: # change dimension when channel is not the same
# TF's SAME mode output ceil(x/stride), which is NOT what we want when x is odd and stride is 2
if not cfg.MODE_FPN and stride == 2:
l = l[:, :, :-1, :-1]
return Conv2D('convshortcut', l, n_out, 1,
strides=stride, padding='VALID', activation=activation)
else:
return Conv2D('convshortcut', l, n_out, 1,
strides=stride, activation=activation)
else:
return l
def googlenet_backbone(image, qw=1):
with argscope(Conv2DQuant,
nl=tf.identity,
use_bias=False,
W_init=variance_scaling_initializer(mode='FAN_IN'),
data_format=get_arg_scope()['Conv2D']['data_format'],
nbit=qw,
is_quant=True if qw > 0 else False):
logits = (LinearWrap(image).Conv2DQuant(
'conv1', 64, 7, stride=2, is_quant=False).MaxPooling(
'pool1', shape=3, stride=2,
padding='SAME').BNReLUQuant('pool1/out').Conv2DQuant(
'conv2/3x3_reduce', 192, 1, nl=getBNReLUQuant).Conv2DQuant(
'conv2/3x3', 192, 3).MaxPooling(
'pool2', shape=3, stride=2,
padding='SAME').BNReLUQuant('pool2/out').apply(
inception_block, 'incpetion_3a', 96, 128,
32).apply(inception_block,
'incpetion_3b',
192,
192,
96,
is_last_block=True).apply(
inception_block, 'incpetion_4a',
256, 208, 48).apply(
inception_block,
'incpetion_4b', 224, 224,
64).
apply(inception_block, 'incpetion_4c', 192, 256,
64).apply(inception_block, 'incpetion_4d', 176, 288,
64).apply(inception_block,
'incpetion_4e',
384,
320,
128,
is_last_block=True).apply(
inception_block,
'incpetion_5a', 384, 320,
128).apply(inception_block,
'incpetion_5b',
512,
384,
128,
is_last_block=True,
is_last=True).
GlobalAvgPooling('pool5').FullyConnected('linear',
out_dim=1000,
nl=tf.identity)())
return logits
def se_resnet_bottleneck(l, ch_out, stride):
shortcut = l
l = Conv2D('conv1', l, ch_out, 1, nl=BNReLU)
l = Conv2D('conv2', l, ch_out, 3, stride=stride, nl=BNReLU)
l = Conv2D('conv3', l, ch_out * 4, 1, nl=get_bn(zero_init=True))
squeeze = GlobalAvgPooling('gap', l)
squeeze = FullyConnected('fc1', squeeze, ch_out // 4, nl=tf.nn.relu)
squeeze = FullyConnected('fc2', squeeze, ch_out * 4, nl=tf.nn.sigmoid)
data_format = get_arg_scope()['Conv2D']['data_format']
ch_ax = 1 if data_format == 'NCHW' else 3
shape = [-1, 1, 1, 1]
shape[ch_ax] = ch_out * 4
l = l * tf.reshape(squeeze, shape)
return l + resnet_shortcut(shortcut, ch_out * 4, stride, nl=get_bn(zero_init=False))
def resnet_backbone(image, num_blocks, group_func, block_func, qw=1):
with argscope(Conv2DQuant, nl=tf.identity, use_bias=False,
W_init=variance_scaling_initializer(mode='FAN_OUT'),
data_format=get_arg_scope()['Conv2D']['data_format'],
nbit=qw):
logits = (LinearWrap(image)
.Conv2DQuant('conv0', 64, 7, stride=2, nl=BNReLU, is_quant=False)
.MaxPooling('pool0', shape=3, stride=2, padding='SAME')
.apply(group_func, 'group0', block_func, 64, num_blocks[0], 1)
.apply(group_func, 'group1', block_func, 128, num_blocks[1], 2)
.apply(group_func, 'group2', block_func, 256, num_blocks[2], 2)
.apply(group_func, 'group3', block_func, 512, num_blocks[3], 2, is_last=True)
.GlobalAvgPooling('gap')
.FullyConnected('linear', 1000, nl=tf.identity)())
return logits
def se_bottleneck(l, ch_out, stride):
shortcut = l
l = mpusim_conv2d('conv1', l, ch_out, 1, activation=BNReLU)
l = mpusim_conv2d('conv2', l, ch_out, 3, strides=stride, activation=BNReLU)
l = mpusim_conv2d('conv3', l, ch_out * 4, 1, activation=get_bn(zero_init=True))
squeeze = GlobalAvgPooling('gap', l)
squeeze = mpusim_fully_connected('fc1', squeeze, ch_out // 4, activation=tf.nn.relu)
squeeze = mpusim_fully_connected('fc2', squeeze, ch_out * 4, activation=tf.nn.sigmoid)
data_format = get_arg_scope()['mpusim_conv2d']['data_format']
ch_ax = 1 if data_format in ['NCHW', 'channels_first'] else 3
shape = [-1, 1, 1, 1]
shape[ch_ax] = ch_out * 4
l = l * tf.reshape(squeeze, shape)
out = l + resnet_shortcut(shortcut, ch_out * 4, stride, activation=get_bn(zero_init=False))
return tf.nn.relu(out)
def resnet_shortcut(l, n_out, stride, nl=tf.identity, block_type='B'):
data_format = get_arg_scope()['Conv2DQuant']['data_format']
n_in = l.get_shape().as_list()[1 if data_format == 'NCHW' else 3]
if n_in != n_out: # change dimension when channel is not the same
if block_type == 'B':
return Conv2DQuant('convshortcut', l, n_out, 1, stride=stride, nl=nl)
else:
l = AvgPooling('poolshortcut', l, stride, stride, padding='VALID')
if data_format == 'NCHW':
paddings = [[0, 0], [0, n_out - n_in], [0, 0], [0, 0]]
else:
paddings = [[0, 0], [0, 0], [0, 0], [0, n_out - n_in]]
l = tf.pad(l, paddings, 'CONSTANT')
return l
else:
return l
def se_resnet_bottleneck(l, ch_out, stride):
shortcut = l
if config.RESNET == 'ResXt':
baseWidth = 4
D = int(math.floor(ch_out * (baseWidth / 64.0)))
C = 32
l = Conv2D('conv1', l, D * C, 1, activation=BNReLU)
l = Conv2D('conv2',
l,
D * C,
3,
stride=stride,
split=C,
activation=BNReLU)
l = Conv2D('conv3',
l,
ch_out * 4,
1,
stride=1,
activation=get_bn(zero_init=True))
else:
l = Conv2D('conv1', l, ch_out, 1, activation=BNReLU)
l = Conv2D('conv2', l, ch_out, 3, strides=stride, activation=BNReLU)
l = Conv2D('conv3',
l,
ch_out * 4,
1,
activation=get_bn(zero_init=True))
squeeze = GlobalAvgPooling('gap', l)
squeeze = FullyConnected('fc1',
squeeze,
ch_out // 4,
activation=tf.nn.relu)
squeeze = FullyConnected('fc2',
squeeze,
ch_out * 4,
activation=tf.nn.sigmoid)
data_format = get_arg_scope()['Conv2D']['data_format']
ch_ax = 1 if data_format in ['NCHW', 'channels_first'] else 3
shape = [-1, 1, 1, 1]
shape[ch_ax] = ch_out * 4
l = l * tf.reshape(squeeze, shape)
out = l + resnet_shortcut(
shortcut, ch_out * 4, stride, activation=get_bn(zero_init=False))
return tf.nn.relu(out)
def alexnet_backbone(image, qw=1):
with argscope(Conv2DQuant,
nl=tf.identity,
use_bias=False,
W_init=tf.random_normal_initializer(stddev=0.01),
data_format=get_arg_scope()['Conv2D']['data_format'],
nbit=qw):
logits = (LinearWrap(image).Conv2DQuant(
'conv1', 96, 11, stride=4, is_quant=False,
padding='VALID').MaxPooling(
'pool1', shape=3, stride=2,
padding='VALID').BNReLUQuant('bnquant2').Conv2DQuant(
'conv2', 256, 5).MaxPooling(
'pool2', shape=3, stride=2,
padding='VALID').BNReLUQuant('bnquant3').Conv2DQuant(
'conv3', 384, 3, nl=getBNReLUQuant).Conv2DQuant(
'conv4', 384, 3,
nl=getBNReLUQuant).Conv2DQuant(
'conv5', 256,
3).MaxPooling('pool5',
shape=3,
stride=2,
padding='VALID').
BNReLUQuant('bnquant6').Conv2DQuant(
'fc6',
4096,
6,
nl=getfcBNReLUQuant,
padding='VALID',
W_init=tf.random_normal_initializer(stddev=0.005),
use_bias=True).Conv2DQuant(
'fc7',
4096,
1,
nl=getfcBNReLU,
padding='VALID',
W_init=tf.random_normal_initializer(stddev=0.005),
use_bias=True).FullyConnected(
'fc8',
out_dim=1000,
nl=tf.identity,
W_init=tf.random_normal_initializer(
stddev=0.01))())
return logits
def resnet_shortcut(
l,
n_out,
stride,
activation=tf.identity
): # tf.identity 返回一个和输入的 tensor 大小和数值都一样的 tensor ,类似于 y=x 操作
data_format = get_arg_scope()['Conv2D']['data_format']
# 下面这个式子主要是为了提取出l的通道数
n_in = l.get_shape().as_list()[1 if data_format in [
'NCHW', 'channels_first'
] else 3] # NCHW即 N,channel,height,width,也就是channels_first
if n_in != n_out: # 通道不同时改变尺寸，使之与n_out相同
return Conv2D('convshortcut',
l,
n_out,
1,
strides=stride,
activation=activation)
else:
return l
def alexnet_backbone(image, qw=1):
with argscope(Conv2DQuant, nl=tf.identity, use_bias=False,
W_init=tf.random_normal_initializer(stddev=0.01),
data_format=get_arg_scope()['Conv2D']['data_format'],
nbit=qw):
logits = (LinearWrap(image)
.Conv2DQuant('conv1', 96, 11, stride=4, is_quant=False, padding='VALID')
.MaxPooling('pool1', shape=3, stride=2, padding='VALID')
.BNReLUQuant('bnquant2')
.Conv2DQuant('conv2', 256, 5)
.MaxPooling('pool2', shape=3, stride=2, padding='VALID')
.BNReLUQuant('bnquant3')
.Conv2DQuant('conv3', 384, 3, nl=getBNReLUQuant)
.Conv2DQuant('conv4', 384, 3, nl=getBNReLUQuant)
.Conv2DQuant('conv5', 256, 3)
.MaxPooling('pool5', shape=3, stride=2, padding='VALID')
.BNReLUQuant('bnquant6')
.Conv2DQuant('fc6', 4096, 6, nl=getfcBNReLUQuant, padding='VALID', W_init=tf.random_normal_initializer(stddev=0.005), use_bias=True)
.Conv2DQuant('fc7', 4096, 1, nl=getfcBNReLU, padding='VALID', W_init=tf.random_normal_initializer(stddev=0.005), use_bias=True)
.FullyConnected('fc8', out_dim=1000, nl=tf.identity, W_init=tf.random_normal_initializer(stddev=0.01))())
return logits
def resnet_shortcut(l, n_out, stride, nl=tf.identity, block_type='B'):
data_format = get_arg_scope()['Conv2DQuant']['data_format']
n_in = l.get_shape().as_list()[1 if data_format == 'NCHW' else 3]
if n_in != n_out: # change dimension when channel is not the same
if block_type == 'B':
return Conv2DQuant('convshortcut',
l,
n_out,
1,
stride=stride,
nl=nl)
else:
l = AvgPooling('poolshortcut', l, stride, stride, padding='VALID')
if data_format == 'NCHW':
paddings = [[0, 0], [0, n_out - n_in], [0, 0], [0, 0]]
else:
paddings = [[0, 0], [0, 0], [0, 0], [0, n_out - n_in]]
l = tf.pad(l, paddings, 'CONSTANT')
return l
else:
return l
def densenet_backbone(image, qw=1):
with argscope(Conv2DQuant, nl=tf.identity, use_bias=False,
W_init=variance_scaling_initializer(mode='FAN_IN'),
data_format=get_arg_scope()['Conv2D']['data_format'],
nbit=qw,
is_quant=True if qw > 0 else False):
logits = (LinearWrap(image)
.Conv2DQuant('conv1', 2 * GROWTH_RATE, 7, stride=2, nl=BNReLU, is_quant=False)
.MaxPooling('pool1', shape=3, stride=2, padding='SAME')
# 56
.apply(add_dense_block, 'block0', 6)
# 28
.apply(add_dense_block, 'block1', 12)
# 14
.apply(add_dense_block, 'block2', 24)
# 7
.apply(add_dense_block, 'block3', 16, last=True)
.BNReLU('bnrelu_last')
.GlobalAvgPooling('gap')
.FullyConnected('linear', out_dim=1000, nl=tf.identity, W_init=variance_scaling_initializer(mode='FAN_IN'))())
return logits
def se_resnet_bottleneck(option,
l,
ch_out,
stride,
ADL_Flag=False,
count=None):
shortcut = l
l = Conv2D('conv1', l, ch_out, 1, activation=BNReLU)
l = Conv2D('conv2', l, ch_out, 3, strides=stride, activation=BNReLU)
l = Conv2D('conv3',
l,
ch_out * 4,
1,
activation=get_bn(option, zero_init=True))
squeeze = GlobalAvgPooling('gap', l)
squeeze = FullyConnected('fc1',
squeeze,
ch_out // 4,
activation=tf.nn.relu)
squeeze = FullyConnected('fc2',
squeeze,
ch_out * 4,
activation=tf.nn.sigmoid)
data_format = get_arg_scope()['Conv2D']['data_format']
ch_ax = 1 if data_format in ['NCHW', 'channels_first'] else 3
shape = [-1, 1, 1, 1]
shape[ch_ax] = ch_out * 4
l = l * tf.reshape(squeeze, shape)
out = l + resnet_shortcut(shortcut,
ch_out * 4,
stride,
activation=get_bn(option, zero_init=False))
out = tf.nn.relu(out)
if option.attdrop[count]: out = ADL(count, out, option)
return out
def se_resnet_bottleneck(l, ch_out, stride):
shortcut = l
l = Conv2D('conv1', l, ch_out, 1, activation=BNReLU)
l = Conv2D('conv2', l, ch_out, 3, strides=stride, activation=BNReLU)
l = Conv2D('conv3', l, ch_out * 4, 1, activation=get_bn(zero_init=True))
squeeze = GlobalAvgPooling('gap', l)
squeeze = FullyConnected('fc1',
squeeze,
ch_out // 4,
activation=tf.nn.relu)
squeeze = FullyConnected('fc2',
squeeze,
ch_out * 4,
activation=tf.nn.sigmoid)
data_format = get_arg_scope()['Conv2D']['data_format']
ch_ax = 1 if data_format in ['NCHW', 'channels_first'
] else 3 # ch_ax是data_format中表示通道数的索引值
shape = [-1, 1, 1, 1]
shape[ch_ax] = ch_out * 4 # 改变shape中通道数的值
l = l * tf.reshape(squeeze, shape)
return l + resnet_shortcut(
shortcut, ch_out * 4, stride, activation=get_bn(zero_init=False))
def vgg_backbone(image, qw=1):
with argscope(Conv2DQuant,
nl=tf.identity,
use_bias=False,
W_init=variance_scaling_initializer(mode='FAN_IN'),
data_format=get_arg_scope()['Conv2D']['data_format'],
nbit=qw):
logits = (
LinearWrap(image).Conv2DQuant('conv1',
96,
7,
stride=2,
nl=tf.nn.relu,
is_quant=False).MaxPooling(
'pool1',
shape=2,
stride=2,
padding='VALID')
# 56
.BNReLUQuant('bnquant2_0').Conv2DQuant(
'conv2_1', 256, 3, nl=getBNReLUQuant).Conv2DQuant(
'conv2_2', 256, 3, nl=getBNReLUQuant).Conv2DQuant(
'conv2_3', 256, 3).MaxPooling('pool2',
shape=2,
stride=2,
padding='VALID')
# 28
.BNReLUQuant('bnquant3_0').Conv2DQuant(
'conv3_1', 512, 3, nl=getBNReLUQuant).Conv2DQuant(
'conv3_2', 512, 3, nl=getBNReLUQuant).Conv2DQuant(
'conv3_3', 512, 3).MaxPooling('pool3',
shape=2,
stride=2,
padding='VALID')
# 14
.BNReLUQuant('bnquant4_0').Conv2DQuant(
'conv4_1', 512, 3, nl=getBNReLUQuant).Conv2DQuant(
'conv4_2', 512, 3, nl=getBNReLUQuant).Conv2DQuant(
'conv4_3', 512, 3).MaxPooling('pool4',
shape=2,
stride=2,
padding='VALID')
# 7
.BNReLUQuant('bnquant5').Conv2DQuant(
'fc5',
4096,
7,
nl=getfcBNReLUQuant,
padding='VALID',
use_bias=True).Conv2DQuant(
'fc6',
4096,
1,
nl=getfcBNReLU,
padding='VALID',
use_bias=True).FullyConnected(
'fc7',
out_dim=1000,
nl=tf.identity,
W_init=variance_scaling_initializer(mode='FAN_IN'))())
return logits
def is_data_format_nchw():
data_format = get_arg_scope()['Conv2D']['data_format']
return data_format in ['NCHW', 'channels_first']
def inception_block(l,
name,
ch_1x1,
ch_3x3,
ch_5x5,
is_last_block=False,
is_last=False):
data_format = get_arg_scope()['Conv2DQuant']['data_format']
with tf.variable_scope(name):
conv1x1 = Conv2DQuant(
'1x1',
l,
ch_1x1,
1,
nl=getBNReLUQuant if not is_last_block else tf.identity)
conv3x3_reduce = Conv2DQuant('3x3_reduce',
l,
ch_3x3,
1,
nl=getBNReLUQuant)
conv3x3 = Conv2DQuant(
'3x3',
conv3x3_reduce,
ch_3x3,
3,
nl=getBNReLUQuant if not is_last_block else tf.identity)
conv5x5_reduce = Conv2DQuant('5x5_reduce',
l,
ch_5x5,
1,
nl=getBNReLUQuant)
conv5x5 = Conv2DQuant(
'5x5',
conv5x5_reduce,
ch_5x5,
5,
nl=getBNReLUQuant if not is_last_block else tf.identity)
if is_last_block and not is_last:
conv1x1 = MaxPooling('pool_1x1',
conv1x1,
shape=3,
stride=2,
padding='SAME')
conv1x1 = BNReLU('conv1x1_bn', conv1x1)
conv1x1 = QuantizedActiv('conv1x1_quant', conv1x1)
conv3x3 = MaxPooling('pool_3x3',
conv3x3,
shape=3,
stride=2,
padding='SAME')
conv3x3 = BNReLU('conv3x3_bn', conv3x3)
conv3x3 = QuantizedActiv('conv3x3_quant', conv3x3)
conv5x5 = MaxPooling('pool_5x5',
conv5x5,
shape=3,
stride=2,
padding='SAME')
conv5x5 = BNReLU('conv5x5_bn', conv5x5)
conv5x5 = QuantizedActiv('conv5x5_quant', conv5x5)
l = tf.concat([conv1x1, conv3x3, conv5x5],
1 if data_format == 'NCHW' else 3,
name='concat')
if is_last:
l = BNReLU('output_bn', l)
return l