def __stage(self, x, stage=2, repeat=3):
if 2 <= stage <= 4:
stage_layer = shufflenet_unit(
'stage' + str(stage) + '_0',
x=x,
w=None,
num_groups=self.args.num_groups,
group_conv_bottleneck=not (stage == 2),
num_filters=self.output_channels[str(
self.args.num_groups)][stage - 2],
stride=(2, 2),
fusion='concat',
l2_strength=self.args.l2_strength,
bias=self.args.bias,
batchnorm_enabled=self.args.batchnorm_enabled,
is_training=self.is_training)
for i in range(1, repeat + 1):
stage_layer = shufflenet_unit(
'stage' + str(stage) + '_' + str(i),
x=stage_layer,
w=None,
num_groups=self.args.num_groups,
group_conv_bottleneck=True,
num_filters=self.output_channels[str(
self.args.num_groups)][stage - 2],
stride=(1, 1),
fusion='add',
l2_strength=self.args.l2_strength,
bias=self.args.bias,
batchnorm_enabled=self.args.batchnorm_enabled,
is_training=self.is_training)
return stage_layer
else:
raise ValueError("Stage should be from 2 -> 4")
def __stage(self, x, stage=2, repeat=3):
if 2 <= stage <= 4:
stage_layer = shufflenet_unit('stage' + str(stage) + '_0', x=x, w=None,
num_groups=self.args.num_groups,
group_conv_bottleneck=not (stage == 2),# stage = 2 时 先不进行分组点卷积
num_filters=
self.output_channels[str(self.args.num_groups)][
stage - 2],
stride=(2, 2),# concate通道扩展合并
fusion='concat', l2_strength=self.args.l2_strength,
bias=self.args.bias,
batchnorm_enabled=self.args.batchnorm_enabled,
is_training=self.is_training)
for i in range(1, repeat + 1):
stage_layer = shufflenet_unit('stage' + str(stage) + '_' + str(i),
x=stage_layer, w=None,
num_groups=self.args.num_groups,
group_conv_bottleneck=True,# 分组点卷积
num_filters=self.output_channels[
str(self.args.num_groups)][stage - 2],
stride=(1, 1),#ADD 通道叠加
fusion='add',
l2_strength=self.args.l2_strength,
bias=self.args.bias,
batchnorm_enabled=self.args.batchnorm_enabled,
is_training=self.is_training)
return stage_layer
else:
raise ValueError("Stage should be from 2 -> 4")