def small_vgg(input_image, num_channels, num_classes):
def __vgg__(ipt, num_filter, times, dropouts, num_channels_=None):
return img_conv_group(input=ipt,
num_channels=num_channels_,
pool_size=2,
pool_stride=2,
conv_num_filter=[num_filter] * times,
conv_filter_size=3,
conv_act=ReluActivation(),
conv_with_batchnorm=True,
conv_batchnorm_drop_rate=dropouts,
pool_type=MaxPooling())
tmp = __vgg__(input_image, 64, 2, [0.3, 0], num_channels)
tmp = __vgg__(tmp, 128, 2, [0.4, 0])
tmp = __vgg__(tmp, 256, 3, [0.4, 0.4, 0])
tmp = __vgg__(tmp, 512, 3, [0.4, 0.4, 0])
tmp = img_pool_layer(input=tmp,
stride=2,
pool_size=2,
pool_type=MaxPooling())
tmp = dropout_layer(input=tmp, dropout_rate=0.5)
tmp = fc_layer(input=tmp,
size=512,
layer_attr=ExtraAttr(drop_rate=0.5),
act=LinearActivation())
tmp = batch_norm_layer(input=tmp, act=ReluActivation())
return fc_layer(input=tmp, size=num_classes, act=SoftmaxActivation())
def __vgg__(ipt, num_filter, times, dropouts, num_channels_=None):
return img_conv_group(input=ipt, num_channels=num_channels_,
pool_size=2,
pool_stride=2,
conv_num_filter=[num_filter] * times,
conv_filter_size=3,
conv_act=ReluActivation(),
conv_with_batchnorm=True,
conv_batchnorm_drop_rate=dropouts,
pool_type=MaxPooling())
def vgg_16_network(input_image, num_channels, num_classes=1000):
"""
Same model from https://gist.github.com/ksimonyan/211839e770f7b538e2d8
:param num_classes:
:param input_image:
:type input_image: LayerOutput
:param num_channels:
:type num_channels: int
:return:
"""
tmp = img_conv_group(input=input_image, num_channels=num_channels,
conv_padding=1, conv_num_filter=[64, 64],
conv_filter_size=3,
conv_act=ReluActivation(), pool_size=2,
pool_stride=2,
pool_type=MaxPooling())
tmp = img_conv_group(input=tmp, conv_num_filter=[128, 128], conv_padding=1,
conv_filter_size=3, conv_act=ReluActivation(),
pool_stride=2, pool_type=MaxPooling(),
pool_size=2)
tmp = img_conv_group(input=tmp, conv_num_filter=[256, 256, 256],
conv_padding=1,
conv_filter_size=3, conv_act=ReluActivation(),
pool_stride=2, pool_type=MaxPooling(), pool_size=2)
tmp = img_conv_group(input=tmp, conv_num_filter=[512, 512, 512],
conv_padding=1,
conv_filter_size=3, conv_act=ReluActivation(),
pool_stride=2, pool_type=MaxPooling(), pool_size=2)
tmp = img_conv_group(input=tmp, conv_num_filter=[512, 512, 512],
conv_padding=1,
conv_filter_size=3, conv_act=ReluActivation(),
pool_stride=2, pool_type=MaxPooling(), pool_size=2)
tmp = fc_layer(input=tmp, size=4096, act=ReluActivation(),
layer_attr=ExtraAttr(drop_rate=0.5))
tmp = fc_layer(input=tmp, size=4096, act=ReluActivation(),
layer_attr=ExtraAttr(drop_rate=0.5))
return fc_layer(input=tmp, size=num_classes, act=SoftmaxActivation())
__bn__ = batch_norm_layer(name="%s_bn" % name,
input=__conv__,
act=act,
bias_attr=bn_bias_attr,
param_attr=bn_param_attr,
layer_attr=bn_layer_attr)
return img_pool_layer(name="%s_pool" % name,
input=__bn__,
pool_type=pool_type,
pool_size=pool_size,
stride=pool_stride,
padding=pool_padding,
layer_attr=pool_layer_attr)
@wrap_act_default(param_names=['conv_act'], act=ReluActivation())
@wrap_param_default(param_names=['pool_type'],
default_factory=lambda _: MaxPooling())
def img_conv_group(input,
conv_num_filter,
pool_size,
num_channels=None,
conv_padding=1,
conv_filter_size=3,
conv_act=None,
conv_with_batchnorm=False,
conv_batchnorm_drop_rate=0,
pool_stride=1,
pool_type=None):
"""
Image Convolution Group, Used for vgg net.
param_attr=conv_param_attr,
shared_biases=shared_bias,
layer_attr=conv_layer_attr)
__bn__ = batch_norm_layer(name="%s_bn" % name,
input=__conv__, act=act,
bias_attr=bn_bias_attr, param_attr=bn_param_attr,
layer_attr=bn_layer_attr)
return img_pool_layer(name="%s_pool" % name,
input=__bn__, pool_type=pool_type,
pool_size=pool_size, stride=pool_stride,
start=pool_start, padding=pool_padding,
layer_attr=pool_layer_attr)
@wrap_act_default(param_names=['conv_act'],
act=ReluActivation())
@wrap_param_default(param_names=['pool_type'],
default_factory=lambda _: MaxPooling())
def img_conv_group(input, conv_num_filter,
pool_size,
num_channels=None,
conv_padding=1,
conv_filter_size=3,
conv_act=None,
conv_with_batchnorm=False,
conv_batchnorm_drop_rate=0,
pool_stride=1,
pool_type=None):
"""
Image Convolution Group, Used for vgg net.