Python tensorpack.tfutils.argscope.argscope() Examples
The following are 20
code examples of tensorpack.tfutils.argscope.argscope().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
tensorpack.tfutils.argscope
, or try the search function
.
.
Example #1
| Source File: basemodel.py From PReMVOS with MIT License | 6 votes |
|
def pretrained_resnet_conv4(image, num_blocks):
assert len(num_blocks) == 3
with argscope([Conv2D, MaxPooling, BatchNorm], data_format='NCHW'), \
argscope(Conv2D, nl=tf.identity, use_bias=False), \
argscope(BatchNorm, use_local_stat=False):
l = tf.pad(image, [[0, 0], [0, 0], [2, 3], [2, 3]])
l = Conv2D('conv0', l, 64, 7, stride=2, nl=BNReLU, padding='VALID')
l = tf.pad(l, [[0, 0], [0, 0], [0, 1], [0, 1]])
l = MaxPooling('pool0', l, shape=3, stride=2, padding='VALID')
l = resnet_group(l, 'group0', resnet_bottleneck, 64, num_blocks[0], 1)
# TODO replace var by const to enable folding
l = tf.stop_gradient(l)
l = resnet_group(l, 'group1', resnet_bottleneck, 128, num_blocks[1], 2)
l = resnet_group(l, 'group2', resnet_bottleneck, 256, num_blocks[2], 2)
# 16x downsampling up to now
return l
Example #2
| Source File: model_rpn.py From tensorpack with Apache License 2.0 | 6 votes |
|
def rpn_head(featuremap, channel, num_anchors):
"""
Returns:
label_logits: fHxfWxNA
box_logits: fHxfWxNAx4
"""
with argscope(Conv2D, data_format='channels_first',
kernel_initializer=tf.random_normal_initializer(stddev=0.01)):
hidden = Conv2D('conv0', featuremap, channel, 3, activation=tf.nn.relu)
label_logits = Conv2D('class', hidden, num_anchors, 1)
box_logits = Conv2D('box', hidden, 4 * num_anchors, 1)
# 1, NA(*4), im/16, im/16 (NCHW)
label_logits = tf.transpose(label_logits, [0, 2, 3, 1]) # 1xfHxfWxNA
label_logits = tf.squeeze(label_logits, 0) # fHxfWxNA
shp = tf.shape(box_logits) # 1x(NAx4)xfHxfW
box_logits = tf.transpose(box_logits, [0, 2, 3, 1]) # 1xfHxfWx(NAx4)
box_logits = tf.reshape(box_logits, tf.stack([shp[2], shp[3], num_anchors, 4])) # fHxfWxNAx4
return label_logits, box_logits
Example #3
| Source File: model_mrcnn.py From tensorpack with Apache License 2.0 | 6 votes |
|
def maskrcnn_upXconv_head(feature, num_category, num_convs, norm=None):
"""
Args:
feature (NxCx s x s): size is 7 in C4 models and 14 in FPN models.
num_category(int):
num_convs (int): number of convolution layers
norm (str or None): either None or 'GN'
Returns:
mask_logits (N x num_category x 2s x 2s):
"""
assert norm in [None, 'GN'], norm
l = feature
with argscope([Conv2D, Conv2DTranspose], data_format='channels_first',
kernel_initializer=tf.variance_scaling_initializer(
scale=2.0, mode='fan_out',
distribution='untruncated_normal' if get_tf_version_tuple() >= (1, 12) else 'normal')):
# c2's MSRAFill is fan_out
for k in range(num_convs):
l = Conv2D('fcn{}'.format(k), l, cfg.MRCNN.HEAD_DIM, 3, activation=tf.nn.relu)
if norm is not None:
l = GroupNorm('gn{}'.format(k), l)
l = Conv2DTranspose('deconv', l, cfg.MRCNN.HEAD_DIM, 2, strides=2, activation=tf.nn.relu)
l = Conv2D('conv', l, num_category, 1, kernel_initializer=tf.random_normal_initializer(stddev=0.001))
return l
Example #4
| Source File: model_frcnn.py From tensorpack with Apache License 2.0 | 6 votes |
|
def fastrcnn_Xconv1fc_head(feature, num_convs, norm=None):
"""
Args:
feature (NCHW):
num_classes(int): num_category + 1
num_convs (int): number of conv layers
norm (str or None): either None or 'GN'
Returns:
2D head feature
"""
assert norm in [None, 'GN'], norm
l = feature
with argscope(Conv2D, data_format='channels_first',
kernel_initializer=tf.variance_scaling_initializer(
scale=2.0, mode='fan_out',
distribution='untruncated_normal' if get_tf_version_tuple() >= (1, 12) else 'normal')):
for k in range(num_convs):
l = Conv2D('conv{}'.format(k), l, cfg.FPN.FRCNN_CONV_HEAD_DIM, 3, activation=tf.nn.relu)
if norm is not None:
l = GroupNorm('gn{}'.format(k), l)
l = FullyConnected('fc', l, cfg.FPN.FRCNN_FC_HEAD_DIM,
kernel_initializer=tf.variance_scaling_initializer(), activation=tf.nn.relu)
return l
Example #5
| Source File: model.py From PReMVOS with MIT License | 6 votes |
|
def rpn_head(featuremap, channel, num_anchors):
"""
Returns:
label_logits: fHxfWxNA
box_logits: fHxfWxNAx4
"""
with argscope(Conv2D, data_format='NCHW',
W_init=tf.random_normal_initializer(stddev=0.01)):
hidden = Conv2D('conv0', featuremap, channel, 3, nl=tf.nn.relu)
label_logits = Conv2D('class', hidden, num_anchors, 1)
box_logits = Conv2D('box', hidden, 4 * num_anchors, 1)
# 1, NA(*4), im/16, im/16 (NCHW)
label_logits = tf.transpose(label_logits, [0, 2, 3, 1]) # 1xfHxfWxNA
label_logits = tf.squeeze(label_logits, 0) # fHxfWxNA
shp = tf.shape(box_logits) # 1x(NAx4)xfHxfW
box_logits = tf.transpose(box_logits, [0, 2, 3, 1]) # 1xfHxfWx(NAx4)
box_logits = tf.reshape(box_logits, tf.stack([shp[2], shp[3], num_anchors, 4])) # fHxfWxNAx4
return label_logits, box_logits
Example #6
| Source File: resnet_model.py From benchmarks with The Unlicense | 6 votes |
|
def resnet_backbone(image, num_blocks, group_func, block_func):
"""
Sec 5.1: We adopt the initialization of [15] for all convolutional layers.
TensorFlow does not have the true "MSRA init". We use variance_scaling as an approximation.
"""
with argscope(Conv2D, use_bias=False,
kernel_initializer=tf.variance_scaling_initializer(scale=2.0, mode='fan_out')):
l = Conv2D('conv0', image, 64, 7, strides=2, activation=BNReLU)
l = MaxPooling('pool0', l, pool_size=3, strides=2, padding='SAME')
l = group_func('group0', l, block_func, 64, num_blocks[0], 1)
l = group_func('group1', l, block_func, 128, num_blocks[1], 2)
l = group_func('group2', l, block_func, 256, num_blocks[2], 2)
l = group_func('group3', l, block_func, 512, num_blocks[3], 2)
l = GlobalAvgPooling('gap', l)
logits = FullyConnected('linear', l, 1000,
kernel_initializer=tf.random_normal_initializer(stddev=0.01))
"""
Sec 5.1:
The 1000-way fully-connected layer is initialized by
drawing weights from a zero-mean Gaussian with standard
deviation of 0.01.
"""
return logits
Example #7
| Source File: resnet_model.py From GroupNorm-reproduce with Apache License 2.0 | 6 votes |
|
def resnet_backbone(image, num_blocks, group_func, block_func):
with argscope(Conv2D, use_bias=False,
kernel_initializer=tf.variance_scaling_initializer(
scale=2.0, mode='fan_out', distribution='untruncated_normal')):
logits = (LinearWrap(image)
.tf.pad([[0, 0], [0, 0], [3, 3], [3, 3]])
.Conv2D('conv0', 64, 7, strides=2, activation=GNReLU, padding='VALID')
.tf.pad([[0, 0], [0, 0], [1, 1], [1, 1]])
.MaxPooling('pool0', shape=3, stride=2, padding='VALID')
.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)
.GlobalAvgPooling('gap')
.FullyConnected('linear', 1000,
kernel_initializer=tf.random_normal_initializer(stddev=0.01))())
return logits
Example #8
| Source File: densenet_model.py From LQ-Nets with MIT License | 6 votes |
|
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
Example #9
| Source File: alexnet_model.py From LQ-Nets with MIT License | 6 votes |
|
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
Example #10
| Source File: resnet.py From ADL with MIT License | 5 votes |
|
def resnet(input_, option):
mode = option.mode
DEPTH = option.depth
bottleneck = {'se': se_resnet_bottleneck}[mode]
cfg = {
50: ([3, 4, 6, 3], bottleneck),
}
defs, block_func = cfg[DEPTH]
group_func = resnet_group
with argscope(Conv2D, use_bias=False, kernel_initializer= \
tf.variance_scaling_initializer(scale=2.0, mode='fan_out')), \
argscope([Conv2D, MaxPooling, GlobalAvgPooling, BatchNorm],
data_format='channels_first'):
l = Conv2D('conv0', input_, 64, 7, strides=2, activation=BNReLU)
if option.gating_position[0]: l = gating_op(l, option)
l = MaxPooling('pool0', l, 3, strides=2, padding='SAME')
if option.gating_position[1]: l = gating_op(l, option)
l = group_func('group0', l, block_func, 64, defs[0], 1, option)
if option.gating_position[2]: l = gating_op(l, option)
l = group_func('group1', l, block_func, 128, defs[1], 2, option)
if option.gating_position[3]: l = gating_op(l, option)
l = group_func('group2', l, block_func, 256, defs[2], 2, option)
if option.gating_position[4]: l = gating_op(l, option)
l = group_func('group3', l, block_func, 512, defs[3],
1, option)
if option.gating_position[5]: l = gating_op(l, option)
p_logits = GlobalAvgPooling('gap', l)
logits = FullyConnected('linearnew', p_logits, option.number_of_class)
return logits, l
Example #11
| Source File: resnet_model.py From LQ-Nets with MIT License | 5 votes |
|
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
Example #12
| Source File: vgg_model.py From LQ-Nets with MIT License | 5 votes |
|
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
Example #13
| Source File: basemodel.py From PReMVOS with MIT License | 5 votes |
|
def resnet_conv5(image, num_block):
with argscope([Conv2D, BatchNorm], data_format='NCHW'), \
argscope(Conv2D, nl=tf.identity, use_bias=False), \
argscope(BatchNorm, use_local_stat=False):
# 14x14:
l = resnet_group(image, 'group3', resnet_bottleneck, 512, num_block, stride=2)
return l
Example #14
| Source File: googlenet_model.py From LQ-Nets with MIT License | 5 votes |
|
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
Example #15
| Source File: model.py From PReMVOS with MIT License | 5 votes |
|
def maskrcnn_head(feature, num_class):
"""
Args:
feature (NxCx7x7):
num_classes(int): num_category + 1
Returns:
mask_logits (N x num_category x 14 x 14):
"""
with argscope([Conv2D, Deconv2D], data_format='NCHW',
W_init=tf.variance_scaling_initializer(
scale=2.0, mode='fan_in', distribution='normal')):
l = Deconv2D('deconv', feature, 256, 2, stride=2, nl=tf.nn.relu)
l = Conv2D('conv', l, num_class - 1, 1)
return l
Example #16
| Source File: resnet_model.py From adanet with MIT License | 5 votes |
|
def resnet_backbone(image, num_blocks, group_func, block_func):
with argscope(Conv2D, use_bias=False,
kernel_initializer=tf.variance_scaling_initializer(scale=2.0, mode='fan_out')):
# Note that this pads the image by [2, 3] instead of [3, 2].
# Similar things happen in later stride=2 layers as well.
l = Conv2D('conv0', image, 64, 7, strides=2, activation=BNReLU)
l = MaxPooling('pool0', l, pool_size=3, strides=2, padding='SAME')
l = group_func('group0', l, block_func, 64, num_blocks[0], 1)
l = group_func('group1', l, block_func, 128, num_blocks[1], 2)
l = group_func('group2', l, block_func, 256, num_blocks[2], 2)
l = group_func('group3', l, block_func, 512, num_blocks[3], 2)
l = GlobalAvgPooling('gap', l)
logits = FullyConnected('linear', l, 1000,
kernel_initializer=tf.random_normal_initializer(stddev=0.01))
return logits, l
Example #17
| Source File: resnet_model.py From tensorpack with Apache License 2.0 | 5 votes |
|
def resnet_backbone(image, num_blocks, group_func, block_func):
with argscope(Conv2D, use_bias=False,
kernel_initializer=tf.variance_scaling_initializer(scale=2.0, mode='fan_out')):
# Note that TF pads the image by [2, 3] instead of [3, 2].
# Similar things happen in later stride=2 layers as well.
l = Conv2D('conv0', image, 64, 7, strides=2, activation=BNReLU)
l = MaxPooling('pool0', l, pool_size=3, strides=2, padding='SAME')
l = group_func('group0', l, block_func, 64, num_blocks[0], 1)
l = group_func('group1', l, block_func, 128, num_blocks[1], 2)
l = group_func('group2', l, block_func, 256, num_blocks[2], 2)
l = group_func('group3', l, block_func, 512, num_blocks[3], 2)
l = GlobalAvgPooling('gap', l)
logits = FullyConnected('linear', l, 1000,
kernel_initializer=tf.random_normal_initializer(stddev=0.01))
return logits
Example #18
| Source File: resnet_model.py From tensorpack with Apache License 2.0 | 5 votes |
|
def resnet_backbone(image, num_blocks, group_func, block_func):
with argscope(Conv2D, use_bias=False,
kernel_initializer=tf.variance_scaling_initializer(scale=2.0, mode='fan_out')):
# Note that TF pads the image by [2, 3] instead of [3, 2].
# Similar things happen in later stride=2 layers as well.
l = Conv2D('conv0', image, 64, 7, strides=2, activation=BNReLU)
l = MaxPooling('pool0', l, pool_size=3, strides=2, padding='SAME')
l = group_func('group0', l, block_func, 64, num_blocks[0], 1)
l = group_func('group1', l, block_func, 128, num_blocks[1], 2)
l = group_func('group2', l, block_func, 256, num_blocks[2], 2)
l = group_func('group3', l, block_func, 512, num_blocks[3], 2)
l = GlobalAvgPooling('gap', l)
logits = FullyConnected('linear', l, 1000,
kernel_initializer=tf.random_normal_initializer(stddev=0.01))
return logits
Example #19
| Source File: resnet_model.py From webvision-2.0-benchmarks with Apache License 2.0 | 5 votes |
|
def resnet_backbone(image, num_blocks, group_func, block_func):
with argscope(Conv2D, nl=tf.identity, use_bias=False,
W_init=tf.variance_scaling_initializer(scale=2.0, mode='fan_out')):
logits = (LinearWrap(image)
.Conv2D('conv0', 64, 7, stride=2, nl=BNReLU)
.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)
.GlobalAvgPooling('gap')
.FullyConnected('linear', NUM_CLASSES, nl=tf.identity)())
return logits
Example #20
| Source File: vgg.py From ADL with MIT License | 4 votes |
|
def vgg_gap(image, option):
with argscope(Conv2D, use_bias=True,
kernel_initializer=tf.variance_scaling_initializer(scale=2.)), \
argscope([Conv2D, MaxPooling, BatchNorm, GlobalAvgPooling],
data_format='channels_first'):
l = convnormrelu(image, 'conv1_1', 64)
if option.gating_position[11]: l = gating_op(l, option)
l = convnormrelu(l, 'conv1_2', 64)
if option.gating_position[12]: l = gating_op(l, option)
l = MaxPooling('pool1', l, 2)
if option.gating_position[1]: l = gating_op(l, option)
l = convnormrelu(l, 'conv2_1', 128)
if option.gating_position[21]: l = gating_op(l, option)
l = convnormrelu(l, 'conv2_2', 128)
if option.gating_position[22]: l = gating_op(l, option)
l = MaxPooling('pool2', l, 2)
if option.gating_position[2]: l = gating_op(l, option)
l = convnormrelu(l, 'conv3_1', 256)
if option.gating_position[31]: l = gating_op(l, option)
l = convnormrelu(l, 'conv3_2', 256)
if option.gating_position[32]: l = gating_op(l, option)
l = convnormrelu(l, 'conv3_3', 256)
if option.gating_position[33]: l = gating_op(l, option)
l = MaxPooling('pool3', l, 2)
if option.gating_position[3]: l = gating_op(l, option)
l = convnormrelu(l, 'conv4_1', 512)
if option.gating_position[41]: l = gating_op(l, option)
l = convnormrelu(l, 'conv4_2', 512)
if option.gating_position[42]: l = gating_op(l, option)
l = convnormrelu(l, 'conv4_3', 512)
if option.gating_position[43]: l = gating_op(l, option)
l = MaxPooling('pool4', l, 2)
if option.gating_position[4]: l = gating_op(l, option)
l = convnormrelu(l, 'conv5_1', 512)
if option.gating_position[51]: l = gating_op(l, option)
l = convnormrelu(l, 'conv5_2', 512)
if option.gating_position[52]: l = gating_op(l, option)
l = convnormrelu(l, 'conv5_3', 512)
if option.gating_position[53]: l = gating_op(l, option)
convmaps = convnormrelu(l, 'new', 1024)
if option.gating_position[6]: convmaps = gating_op(l, option)
p_logits = GlobalAvgPooling('gap', convmaps)
logits = FullyConnected('linear',
p_logits, option.number_of_class,
kernel_initializer=tf.random_normal_initializer(
stddev=0.01))
return logits, convmaps
