def decoder(encode_data, decode_shortcut):
# 解码器配置
# encode_data：编码器输出
# decode_shortcut: 从backbone引出的分支, resize后与encode_data concat
# DECODER_USE_SEP_CONV: 默认为真，则concat后连接两个可分离卷积，否则为普通卷积
param_attr = fluid.ParamAttr(name=name_scope + 'weights',
regularizer=None,
initializer=fluid.initializer.TruncatedNormal(
loc=0.0, scale=0.06))
with scope('decoder'):
with scope('concat'):
decode_shortcut = bn_relu(
conv(decode_shortcut,
48,
1,
1,
groups=1,
padding=0,
param_attr=param_attr))
encode_data = fluid.layers.resize_bilinear(
encode_data, decode_shortcut.shape[2:])
encode_data = fluid.layers.concat([encode_data, decode_shortcut],
axis=1)
if cfg.MODEL.DEEPLAB.DECODER_USE_SEP_CONV:
with scope("separable_conv1"):
encode_data = separate_conv(encode_data,
256,
1,
3,
dilation=1,
act=relu)
with scope("separable_conv2"):
encode_data = separate_conv(encode_data,
256,
1,
3,
dilation=1,
act=relu)
else:
with scope("decoder_conv1"):
encode_data = bn_relu(
conv(encode_data,
256,
stride=1,
filter_size=3,
dilation=1,
padding=1,
param_attr=param_attr))
with scope("decoder_conv2"):
encode_data = bn_relu(
conv(encode_data,
256,
stride=1,
filter_size=3,
dilation=1,
padding=1,
param_attr=param_attr))
return encode_data
def _decoder_with_concat(encode_data, decode_shortcut, param_attr):
with scope('concat'):
decode_shortcut = bn_relu(
conv(
decode_shortcut,
48,
1,
1,
groups=1,
padding=0,
param_attr=param_attr))
encode_data = fluid.layers.resize_bilinear(encode_data,
decode_shortcut.shape[2:])
encode_data = fluid.layers.concat([encode_data, decode_shortcut],
axis=1)
if cfg.MODEL.DEEPLAB.DECODER_USE_SEP_CONV:
with scope("separable_conv1"):
encode_data = separate_conv(
encode_data,
cfg.MODEL.DEEPLAB.DECODER.CONV_FILTERS,
1,
3,
dilation=1,
act=relu)
with scope("separable_conv2"):
encode_data = separate_conv(
encode_data,
cfg.MODEL.DEEPLAB.DECODER.CONV_FILTERS,
1,
3,
dilation=1,
act=relu)
else:
with scope("decoder_conv1"):
encode_data = bn_relu(
conv(
encode_data,
cfg.MODEL.DEEPLAB.DECODER.CONV_FILTERS,
stride=1,
filter_size=3,
dilation=1,
padding=1,
param_attr=param_attr))
with scope("decoder_conv2"):
encode_data = bn_relu(
conv(
encode_data,
cfg.MODEL.DEEPLAB.DECODER.CONV_FILTERS,
stride=1,
filter_size=3,
dilation=1,
padding=1,
param_attr=param_attr))
return encode_data
def xception_block(self,
input,
channels,
strides=1,
filters=3,
dilation=1,
skip_conv=True,
has_skip=True,
activation_fn_in_separable_conv=False):
repeat_number = 3
channels = check_data(channels, repeat_number)
filters = check_data(filters, repeat_number)
strides = check_data(strides, repeat_number)
data = input
results = []
for i in range(repeat_number):
with scope('separable_conv' + str(i + 1)):
if not activation_fn_in_separable_conv:
data = relu(data)
data = separate_conv(
data,
channels[i],
strides[i],
filters[i],
dilation=dilation)
else:
data = separate_conv(
data,
channels[i],
strides[i],
filters[i],
dilation=dilation,
act=relu)
results.append(data)
if not has_skip:
return data, results
if skip_conv:
param_attr = fluid.ParamAttr(
name=name_scope + 'weights',
regularizer=None,
initializer=fluid.initializer.TruncatedNormal(
loc=0.0, scale=0.09))
with scope('shortcut'):
skip = bn(
conv(
input,
channels[-1],
1,
strides[-1],
groups=1,
padding=0,
param_attr=param_attr))
else:
skip = input
return data + skip, results
def net(self, x):
with scope('dsconv1'):
x = separate_conv(x,
self.dw_channels,
stride=self.stride,
filter=3,
act=fluid.layers.relu)
with scope('dsconv2'):
x = separate_conv(x,
self.dw_channels,
stride=self.stride,
filter=3,
act=fluid.layers.relu)
x = dropout2d(x, 0.1, is_train=cfg.PHASE == 'train')
x = conv(x, self.num_classes, 1, bias_attr=True)
return x
def learning_to_downsample(x,
dw_channels1=32,
dw_channels2=48,
out_channels=64):
x = relu(bn(conv(x, dw_channels1, 3, 2)))
with scope('dsconv1'):
x = separate_conv(x,
dw_channels2,
stride=2,
filter=3,
act=fluid.layers.relu)
with scope('dsconv2'):
x = separate_conv(x,
out_channels,
stride=2,
filter=3,
act=fluid.layers.relu)
return x
def encoder(input):
#优化方向：可考虑ASPP_WITH_SE模块
# 编码器配置，采用ASPP架构，pooling + 1x1_conv + 三个不同尺度的空洞卷积并行, concat后1x1conv
# ASPP_WITH_SEP_CONV：默认为真，使用depthwise可分离卷积，否则使用普通卷积
# OUTPUT_STRIDE: 下采样倍数，8或16，决定aspp_ratios大小
# aspp_ratios：ASPP模块空洞卷积的采样率
aspp_ratios = [6, 12, 18]
param_attr = fluid.ParamAttr(
name=name_scope + 'weights',
regularizer=None,
initializer=fluid.initializer.TruncatedNormal(loc=0.0, scale=0.06))
concat_logits = []
with scope('encoder'):
#channel = cfg.MODEL.DEEPLAB.ENCODER.ASPP_CONVS_FILTERS
channel = 256
with scope("image_pool"):
#if not cfg.MODEL.DEEPLAB.ENCODER.POOLING_CROP_SIZE:
image_avg = fluid.layers.reduce_mean(
input, [2, 3], keep_dim=True)
#else:
# pool_w = int((cfg.MODEL.DEEPLAB.ENCODER.POOLING_CROP_SIZE[0] -
# 1.0) / cfg.MODEL.DEEPLAB.OUTPUT_STRIDE + 1.0)
# pool_h = int((cfg.MODEL.DEEPLAB.ENCODER.POOLING_CROP_SIZE[1] -
# 1.0) / cfg.MODEL.DEEPLAB.OUTPUT_STRIDE + 1.0)
# image_avg = fluid.layers.pool2d(
# input,
# pool_size=(pool_h, pool_w),
# pool_stride=cfg.MODEL.DEEPLAB.ENCODER.POOLING_STRIDE,
# pool_type='avg',
# pool_padding='VALID')
#act = qsigmoid if cfg.MODEL.DEEPLAB.ENCODER.SE_USE_QSIGMOID else bn_relu
act = bn_relu
image_avg = act(
conv(
image_avg,
channel,
1,
1,
groups=1,
padding=0,
param_attr=param_attr))
image_avg = fluid.layers.resize_bilinear(image_avg, input.shape[2:])
#if cfg.MODEL.DEEPLAB.ENCODER.ADD_IMAGE_LEVEL_FEATURE:
concat_logits.append(image_avg)
with scope("aspp0"):
aspp0 = bn_relu(
conv(
input,
channel,
1,
1,
groups=1,
padding=0,
param_attr=param_attr))
concat_logits.append(aspp0)
if aspp_ratios:
with scope("aspp1"):
#if cfg.MODEL.DEEPLAB.ASPP_WITH_SEP_CONV:
aspp1 = separate_conv(
input, channel, 1, 3, dilation=aspp_ratios[0], act=relu)
# else:
# aspp1 = bn_relu(
# conv(
# input,
# channel,
# stride=1,
# filter_size=3,
# dilation=aspp_ratios[0],
# padding=aspp_ratios[0],
# param_attr=param_attr))
concat_logits.append(aspp1)
with scope("aspp2"):
#if cfg.MODEL.DEEPLAB.ASPP_WITH_SEP_CONV:
aspp2 = separate_conv(
input, channel, 1, 3, dilation=aspp_ratios[1], act=relu)
# else:
# aspp2 = bn_relu(
# conv(
# input,
# channel,
# stride=1,
# filter_size=3,
# dilation=aspp_ratios[1],
# padding=aspp_ratios[1],
# param_attr=param_attr))
concat_logits.append(aspp2)
with scope("aspp3"):
#if cfg.MODEL.DEEPLAB.ASPP_WITH_SEP_CONV:
aspp3 = separate_conv(
input, channel, 1, 3, dilation=aspp_ratios[2], act=relu)
# else:
# aspp3 = bn_relu(
# conv(
# input,
# channel,
# stride=1,
# filter_size=3,
# dilation=aspp_ratios[2],
# padding=aspp_ratios[2],
# param_attr=param_attr))
concat_logits.append(aspp3)
with scope("concat"):
data = fluid.layers.concat(concat_logits, axis=1)
#if cfg.MODEL.DEEPLAB.ENCODER.ASPP_WITH_CONCAT_PROJECTION:
data = bn_relu(
conv(
data,
channel,
1,
1,
groups=1,
padding=0,
param_attr=param_attr))
data = fluid.layers.dropout(data, 0.9)
#if cfg.MODEL.DEEPLAB.ENCODER.ASPP_WITH_SE:
# data = data * image_avg
return data
def encoder(input):
# 编码器配置，采用ASPP架构，pooling + 1x1_conv + 三个不同尺度的空洞卷积并行, concat后1x1conv
# ASPP_WITH_SEP_CONV：默认为真，使用depthwise可分离卷积，否则使用普通卷积
# OUTPUT_STRIDE: 下采样倍数，8或16，决定aspp_ratios大小
# aspp_ratios：ASPP模块空洞卷积的采样率
if cfg.MODEL.DEEPLAB.OUTPUT_STRIDE == 16:
aspp_ratios = [6, 12, 18]
elif cfg.MODEL.DEEPLAB.OUTPUT_STRIDE == 8:
aspp_ratios = [12, 24, 36]
else:
raise Exception("deeplab only support stride 8 or 16")
param_attr = fluid.ParamAttr(
name=name_scope + 'weights',
regularizer=None,
initializer=fluid.initializer.TruncatedNormal(loc=0.0, scale=0.06))
with scope('encoder'):
channel = 256
with scope("image_pool"):
if cfg.MODEL.FP16:
image_avg = fluid.layers.reduce_mean(
fluid.layers.cast(input, 'float32'), [2, 3], keep_dim=True)
image_avg = fluid.layers.cast(image_avg, 'float16')
else:
image_avg = fluid.layers.reduce_mean(
input, [2, 3], keep_dim=True)
image_avg = bn_relu(
conv(
image_avg,
channel,
1,
1,
groups=1,
padding=0,
param_attr=param_attr))
if cfg.MODEL.FP16:
image_avg = fluid.layers.cast(image_avg, 'float32')
image_avg = fluid.layers.resize_bilinear(image_avg, input.shape[2:])
if cfg.MODEL.FP16:
image_avg = fluid.layers.cast(image_avg, 'float16')
with scope("aspp0"):
aspp0 = bn_relu(
conv(
input,
channel,
1,
1,
groups=1,
padding=0,
param_attr=param_attr))
with scope("aspp1"):
if cfg.MODEL.DEEPLAB.ASPP_WITH_SEP_CONV:
aspp1 = separate_conv(
input, channel, 1, 3, dilation=aspp_ratios[0], act=relu)
else:
aspp1 = bn_relu(
conv(
input,
channel,
stride=1,
filter_size=3,
dilation=aspp_ratios[0],
padding=aspp_ratios[0],
param_attr=param_attr))
with scope("aspp2"):
if cfg.MODEL.DEEPLAB.ASPP_WITH_SEP_CONV:
aspp2 = separate_conv(
input, channel, 1, 3, dilation=aspp_ratios[1], act=relu)
else:
aspp2 = bn_relu(
conv(
input,
channel,
stride=1,
filter_size=3,
dilation=aspp_ratios[1],
padding=aspp_ratios[1],
param_attr=param_attr))
with scope("aspp3"):
if cfg.MODEL.DEEPLAB.ASPP_WITH_SEP_CONV:
aspp3 = separate_conv(
input, channel, 1, 3, dilation=aspp_ratios[2], act=relu)
else:
aspp3 = bn_relu(
conv(
input,
channel,
stride=1,
filter_size=3,
dilation=aspp_ratios[2],
padding=aspp_ratios[2],
param_attr=param_attr))
with scope("concat"):
data = fluid.layers.concat([image_avg, aspp0, aspp1, aspp2, aspp3],
axis=1)
data = bn_relu(
conv(
data,
channel,
1,
1,
groups=1,
padding=0,
param_attr=param_attr))
data = fluid.layers.dropout(data, 0.9)
return data
