Created by: mensaochun

给模型加上namespace之后

namespace的名字变成两份：

可复现的代码

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import paddle.fluid as fluid
from paddle.fluid.initializer import MSRA
from paddle.fluid.param_attr import ParamAttr
from paddle.fluid.transpiler.details.program_utils import program_to_code

class MobileNetV2():
    def __init__(self, scale=1.0, emb_dim=512, fix_net=False, emb_bn=False):
        self.scale = scale
        self.fix_net = fix_net  # FIXME: not use!
        self.emb_dim = emb_dim
        self.emb_bn = emb_bn

    def net(self, input):
        scale = self.scale
        bottleneck_params_list = [
            (1, 16, 1, 1),
            (6, 24, 2, 2),
            (6, 32, 3, 2),
            (6, 64, 4, 2),
            (6, 96, 3, 1),
            (6, 160, 3, 2),
            (6, 320, 1, 1),
        ]

        # conv1
        input = self.conv_bn_layer(
            input,
            num_filters=int(32 * scale),
            filter_size=3,
            stride=2,
            padding=1,
            if_act=True,
            name='conv1_1')

        # bottleneck sequences
        i = 1
        in_c = int(32 * scale)
        for layer_setting in bottleneck_params_list:
            t, c, n, s = layer_setting
            i += 1
            input = self.invresi_blocks(
                input=input,
                in_c=in_c,
                t=t,
                c=int(c * scale),
                n=n,
                s=s,
                name='conv' + str(i))
            in_c = int(c * scale)
        # last_conv
        input = self.conv_bn_layer(
            input=input,
            num_filters=int(1280 * scale) if scale > 1.0 else 1280,
            filter_size=1,
            stride=1,
            padding=0,
            if_act=True,
            name='conv9')

        emb = fluid.layers.fc(
            input=input,
            size=self.emb_dim,
            act=None,
            name='fc_0',
            param_attr=fluid.param_attr.ParamAttr(
                initializer=fluid.initializer.NormalInitializer(0.0, 0.01)),
            bias_attr=fluid.param_attr.ParamAttr(
                initializer=fluid.initializer.ConstantInitializer()))
        if self.emb_bn:
            print('Add bn after embedding...')
            emb = fluid.layers.batch_norm(input=emb, act=None, use_global_stats=False, name='last_bn')

        return emb

    def conv_bn_layer(self,
                      input,
                      filter_size,
                      num_filters,
                      stride,
                      padding,
                      channels=None,
                      num_groups=1,
                      if_act=True,
                      name=None,
                      use_cudnn=True):
        conv = fluid.layers.conv2d(
            input=input,
            num_filters=num_filters,
            filter_size=filter_size,
            stride=stride,
            padding=padding,
            groups=num_groups,
            act=None,
            use_cudnn=use_cudnn,
            param_attr=ParamAttr(name=name + '_weights'),
            bias_attr=False)
        bn_name = name + '_bn'
        bn = fluid.layers.batch_norm(
            input=conv,
            param_attr=ParamAttr(name=bn_name + "_scale"),
            bias_attr=ParamAttr(name=bn_name + "_offset"),
            moving_mean_name=bn_name + '_mean',
            moving_variance_name=bn_name + '_variance')
        if if_act:
            return fluid.layers.relu6(bn)
        else:
            return bn

    def shortcut(self, input, data_residual):
        return fluid.layers.elementwise_add(input, data_residual)

    def inverted_residual_unit(self,
                               input,
                               num_in_filter,
                               num_filters,
                               ifshortcut,
                               stride,
                               filter_size,
                               padding,
                               expansion_factor,
                               name=None):
        num_expfilter = int(round(num_in_filter * expansion_factor))

        channel_expand = self.conv_bn_layer(
            input=input,
            num_filters=num_expfilter,
            filter_size=1,
            stride=1,
            padding=0,
            num_groups=1,
            if_act=True,
            name=name + '_expand')

        bottleneck_conv = self.conv_bn_layer(
            input=channel_expand,
            num_filters=num_expfilter,
            filter_size=filter_size,
            stride=stride,
            padding=padding,
            num_groups=num_expfilter,
            if_act=True,
            name=name + '_dwise',
            use_cudnn=False)

        linear_out = self.conv_bn_layer(
            input=bottleneck_conv,
            num_filters=num_filters,
            filter_size=1,
            stride=1,
            padding=0,
            num_groups=1,
            if_act=False,
            name=name + '_linear')
        if ifshortcut:
            out = self.shortcut(input=input, data_residual=linear_out)
            return out
        else:
            return linear_out

    def invresi_blocks(self, input, in_c, t, c, n, s, name=None):
        first_block = self.inverted_residual_unit(
            input=input,
            num_in_filter=in_c,
            num_filters=c,
            ifshortcut=False,
            stride=s,
            filter_size=3,
            padding=1,
            expansion_factor=t,
            name=name + '_1')

        last_residual_block = first_block
        last_c = c

        for i in range(1, n):
            last_residual_block = self.inverted_residual_unit(
                input=last_residual_block,
                num_in_filter=last_c,
                num_filters=c,
                ifshortcut=True,
                stride=1,
                filter_size=3,
                padding=1,
                expansion_factor=t,
                name=name + '_' + str(i + 1))
        return last_residual_block


def MobileNetV2_x0_25(emb_dim=512, fix_net=False, emb_bn=False):
    model = MobileNetV2(scale=0.25, emb_dim=emb_dim, fix_net=fix_net, emb_bn=emb_bn)
    return model


def MobileNetV2_x0_5(emb_dim=512, fix_net=False, emb_bn=False):
    model = MobileNetV2(scale=0.5, emb_dim=emb_dim, fix_net=fix_net, emb_bn=emb_bn)
    return model


def MobileNetV2_x0_75(emb_dim=512, fix_net=False, emb_bn=False):
    model = MobileNetV2(scale=0.75, emb_dim=emb_dim, fix_net=fix_net, emb_bn=emb_bn)
    return model


def MobileNetV2_x1_0(emb_dim=512, fix_net=False, emb_bn=False):
    model = MobileNetV2(scale=1.0, emb_dim=emb_dim, fix_net=fix_net, emb_bn=emb_bn)
    return model


def MobileNetV2_x1_5(emb_dim=512, fix_net=False, emb_bn=False):
    model = MobileNetV2(scale=1.5, emb_dim=emb_dim, fix_net=fix_net, emb_bn=emb_bn)
    return model


def MobileNetV2_x2_0(emb_dim=512, fix_net=False, emb_bn=False):
    model = MobileNetV2(scale=2.0, emb_dim=emb_dim, fix_net=fix_net, emb_bn=emb_bn)
    return model


if __name__ == '__main__':
    image = fluid.layers.data(name='image', shape=[3, 112, 112], dtype='float32')
    label = fluid.layers.data(name='label', shape=[1], dtype='int64')
    model = MobileNetV2_x1_0(emb_dim=128, fix_net=0, emb_bn=1)
    with fluid.unique_name.guard('MobileNetV2_x1_'):
        emb = model.net(image)
    main_prog = fluid.default_main_program()
    with open('main.program', 'w') as fout:
        program_to_code(main_prog, fout, True)