mobilenet_v1.py

#copyright (c) 2020 PaddlePaddle Authors. All Rights Reserve.
#
#Licensed under the Apache License, Version 2.0 (the "License");
#you may not use this file except in compliance with the License.
#You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
#Unless required by applicable law or agreed to in writing, software
#distributed under the License is distributed on an "AS IS" BASIS,
#WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
#See the License for the specific language governing permissions and
#limitations under the License.

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

__all__ = [
    'MobileNetV1', 'MobileNetV1_x0_25', 'MobileNetV1_x0_5', 'MobileNetV1_x1_0',
    'MobileNetV1_x0_75'
]


class MobileNetV1():
    def __init__(self, scale=1.0):
        self.scale = scale

    def net(self, input, class_dim=1000):
        scale = self.scale
        # conv1: 112x112
        input = self.conv_bn_layer(
            input,
            filter_size=3,
            channels=3,
            num_filters=int(32 * scale),
            stride=2,
            padding=1,
            name="conv1")

        # 56x56
        input = self.depthwise_separable(
            input,
            num_filters1=32,
            num_filters2=64,
            num_groups=32,
            stride=1,
            scale=scale,
            name="conv2_1")

        input = self.depthwise_separable(
            input,
            num_filters1=64,
            num_filters2=128,
            num_groups=64,
            stride=2,
            scale=scale,
            name="conv2_2")

        # 28x28
        input = self.depthwise_separable(
            input,
            num_filters1=128,
            num_filters2=128,
            num_groups=128,
            stride=1,
            scale=scale,
            name="conv3_1")

        input = self.depthwise_separable(
            input,
            num_filters1=128,
            num_filters2=256,
            num_groups=128,
            stride=2,
            scale=scale,
            name="conv3_2")

        # 14x14
        input = self.depthwise_separable(
            input,
            num_filters1=256,
            num_filters2=256,
            num_groups=256,
            stride=1,
            scale=scale,
            name="conv4_1")

        input = self.depthwise_separable(
            input,
            num_filters1=256,
            num_filters2=512,
            num_groups=256,
            stride=2,
            scale=scale,
            name="conv4_2")

        # 14x14
        for i in range(5):
            input = self.depthwise_separable(
                input,
                num_filters1=512,
                num_filters2=512,
                num_groups=512,
                stride=1,
                scale=scale,
                name="conv5" + "_" + str(i + 1))
        # 7x7
        input = self.depthwise_separable(
            input,
            num_filters1=512,
            num_filters2=1024,
            num_groups=512,
            stride=2,
            scale=scale,
            name="conv5_6")

        input = self.depthwise_separable(
            input,
            num_filters1=1024,
            num_filters2=1024,
            num_groups=1024,
            stride=1,
            scale=scale,
            name="conv6")

        input = fluid.layers.pool2d(
            input=input, pool_type='avg', global_pooling=True)

        output = fluid.layers.fc(input=input,
                                 size=class_dim,
                                 param_attr=ParamAttr(
                                     initializer=MSRA(), name="fc7_weights"),
                                 bias_attr=ParamAttr(name="fc7_offset"))
        return output

    def conv_bn_layer(self,
                      input,
                      filter_size,
                      num_filters,
                      stride,
                      padding,
                      channels=None,
                      num_groups=1,
                      act='relu',
                      use_cudnn=True,
                      name=None):
        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(
                initializer=MSRA(), name=name + "_weights"),
            bias_attr=False)
        bn_name = name + "_bn"
        return fluid.layers.batch_norm(
            input=conv,
            act=act,
            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')

    def depthwise_separable(self,
                            input,
                            num_filters1,
                            num_filters2,
                            num_groups,
                            stride,
                            scale,
                            name=None):
        depthwise_conv = self.conv_bn_layer(
            input=input,
            filter_size=3,
            num_filters=int(num_filters1 * scale),
            stride=stride,
            padding=1,
            num_groups=int(num_groups * scale),
            use_cudnn=False,
            name=name + "_dw")

        pointwise_conv = self.conv_bn_layer(
            input=depthwise_conv,
            filter_size=1,
            num_filters=int(num_filters2 * scale),
            stride=1,
            padding=0,
            name=name + "_sep")
        return pointwise_conv


def MobileNetV1_x0_25():
    model = MobileNetV1(scale=0.25)
    return model


def MobileNetV1_x0_5():
    model = MobileNetV1(scale=0.5)
    return model


def MobileNetV1_x1_0():
    model = MobileNetV1(scale=1.0)
    return model


def MobileNetV1_x0_75():
    model = MobileNetV1(scale=0.75)
    return model