resnet_vd.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 numpy as np
import paddle
from paddle import ParamAttr
import paddle.nn as nn
from paddle.nn import Conv2d, BatchNorm, Linear, Dropout
from paddle.nn import AdaptiveAvgPool2d, MaxPool2d, AvgPool2d
from paddle.nn.initializer import Uniform

import math

__all__ = [
    "ResNet18_vd", "ResNet34_vd", "ResNet50_vd", "ResNet101_vd", "ResNet152_vd"
]


class ConvBNLayer(nn.Layer):
    def __init__(self,
                 num_channels,
                 num_filters,
                 filter_size,
                 stride=1,
                 groups=1,
                 is_vd_mode=False,
                 act=None,
                 lr_mult=1.0,
                 name=None):
        super(ConvBNLayer, self).__init__()
        self.is_vd_mode = is_vd_mode
        self._pool2d_avg = AvgPool2d(
            kernel_size=2, stride=2, padding=0, ceil_mode=True)
        self._conv = Conv2d(
            in_channels=num_channels,
            out_channels=num_filters,
            kernel_size=filter_size,
            stride=stride,
            padding=(filter_size - 1) // 2,
            groups=groups,
            weight_attr=ParamAttr(
                name=name + "_weights", learning_rate=lr_mult),
            bias_attr=False)
        if name == "conv1":
            bn_name = "bn_" + name
        else:
            bn_name = "bn" + name[3:]
        self._batch_norm = BatchNorm(
            num_filters,
            act=act,
            param_attr=ParamAttr(name=bn_name + '_scale'),
            bias_attr=ParamAttr(bn_name + '_offset'),
            moving_mean_name=bn_name + '_mean',
            moving_variance_name=bn_name + '_variance')

    def forward(self, inputs):
        if self.is_vd_mode:
            inputs = self._pool2d_avg(inputs)
        y = self._conv(inputs)
        y = self._batch_norm(y)
        return y


class BottleneckBlock(nn.Layer):
    def __init__(self,
                 num_channels,
                 num_filters,
                 stride,
                 shortcut=True,
                 if_first=False,
                 lr_mult=1.0,
                 name=None):
        super(BottleneckBlock, self).__init__()

        self.conv0 = ConvBNLayer(
            num_channels=num_channels,
            num_filters=num_filters,
            filter_size=1,
            act='relu',
            lr_mult=lr_mult,
            name=name + "_branch2a")
        self.conv1 = ConvBNLayer(
            num_channels=num_filters,
            num_filters=num_filters,
            filter_size=3,
            stride=stride,
            act='relu',
            lr_mult=lr_mult,
            name=name + "_branch2b")
        self.conv2 = ConvBNLayer(
            num_channels=num_filters,
            num_filters=num_filters * 4,
            filter_size=1,
            act=None,
            lr_mult=lr_mult,
            name=name + "_branch2c")

        if not shortcut:
            self.short = ConvBNLayer(
                num_channels=num_channels,
                num_filters=num_filters * 4,
                filter_size=1,
                stride=1,
                is_vd_mode=False if if_first else True,
                name=name + "_branch1")

        self.shortcut = shortcut

    def forward(self, inputs):
        y = self.conv0(inputs)
        conv1 = self.conv1(y)
        conv2 = self.conv2(conv1)

        if self.shortcut:
            short = inputs
        else:
            short = self.short(inputs)
        y = paddle.elementwise_add(x=short, y=conv2, act='relu')
        return y


class BasicBlock(nn.Layer):
    def __init__(self,
                 num_channels,
                 num_filters,
                 stride,
                 shortcut=True,
                 if_first=False,
                 lr_mult=1.0,
                 name=None):
        super(BasicBlock, self).__init__()
        self.stride = stride
        self.conv0 = ConvBNLayer(
            num_channels=num_channels,
            num_filters=num_filters,
            filter_size=3,
            stride=stride,
            act='relu',
            name=name + "_branch2a")
        self.conv1 = ConvBNLayer(
            num_channels=num_filters,
            num_filters=num_filters,
            filter_size=3,
            act=None,
            name=name + "_branch2b")

        if not shortcut:
            self.short = ConvBNLayer(
                num_channels=num_channels,
                num_filters=num_filters,
                filter_size=1,
                stride=1,
                is_vd_mode=False if if_first else True,
                name=name + "_branch1")

        self.shortcut = shortcut

    def forward(self, inputs):
        y = self.conv0(inputs)
        conv1 = self.conv1(y)

        if self.shortcut:
            short = inputs
        else:
            short = self.short(inputs)
        y = paddle.elementwise_add(x=short, y=conv1, act='relu')
        return y


class ResNet_vd(nn.Layer):
    def __init__(self,
                 layers=50,
                 class_dim=1000,
                 lr_mult_list=[1.0, 1.0, 1.0, 1.0, 1.0]):
        super(ResNet_vd, self).__init__()

        self.layers = layers
        supported_layers = [18, 34, 50, 101, 152, 200]
        assert layers in supported_layers, \
            "supported layers are {} but input layer is {}".format(
                supported_layers, layers)

        self.lr_mult_list = lr_mult_list
        assert isinstance(self.lr_mult_list, (
            list, tuple
        )), "lr_mult_list should be in (list, tuple) but got {}".format(
            type(self.lr_mult_list))
        assert len(
            self.lr_mult_list
        ) == 5, "lr_mult_list length should should be 5 but got {}".format(
            len(self.lr_mult_list))

        if layers == 18:
            depth = [2, 2, 2, 2]
        elif layers == 34 or layers == 50:
            depth = [3, 4, 6, 3]
        elif layers == 101:
            depth = [3, 4, 23, 3]
        elif layers == 152:
            depth = [3, 8, 36, 3]
        elif layers == 200:
            depth = [3, 12, 48, 3]
        num_channels = [64, 256, 512,
                        1024] if layers >= 50 else [64, 64, 128, 256]
        num_filters = [64, 128, 256, 512]

        self.conv1_1 = ConvBNLayer(
            num_channels=3,
            num_filters=32,
            filter_size=3,
            stride=2,
            act='relu',
            lr_mult=self.lr_mult_list[0],
            name="conv1_1")
        self.conv1_2 = ConvBNLayer(
            num_channels=32,
            num_filters=32,
            filter_size=3,
            stride=1,
            act='relu',
            lr_mult=self.lr_mult_list[0],
            name="conv1_2")
        self.conv1_3 = ConvBNLayer(
            num_channels=32,
            num_filters=64,
            filter_size=3,
            stride=1,
            act='relu',
            lr_mult=self.lr_mult_list[0],
            name="conv1_3")
        self.pool2d_max = MaxPool2d(kernel_size=3, stride=2, padding=1)

        self.block_list = []
        if layers >= 50:
            for block in range(len(depth)):
                shortcut = False
                for i in range(depth[block]):
                    if layers in [101, 152] and block == 2:
                        if i == 0:
                            conv_name = "res" + str(block + 2) + "a"
                        else:
                            conv_name = "res" + str(block + 2) + "b" + str(i)
                    else:
                        conv_name = "res" + str(block + 2) + chr(97 + i)
                    bottleneck_block = self.add_sublayer(
                        'bb_%d_%d' % (block, i),
                        BottleneckBlock(
                            num_channels=num_channels[block]
                            if i == 0 else num_filters[block] * 4,
                            num_filters=num_filters[block],
                            stride=2 if i == 0 and block != 0 else 1,
                            shortcut=shortcut,
                            if_first=block == i == 0,
                            lr_mult=self.lr_mult_list[block + 1],
                            name=conv_name))
                    self.block_list.append(bottleneck_block)
                    shortcut = True
        else:
            for block in range(len(depth)):
                shortcut = False
                for i in range(depth[block]):
                    conv_name = "res" + str(block + 2) + chr(97 + i)
                    basic_block = self.add_sublayer(
                        'bb_%d_%d' % (block, i),
                        BasicBlock(
                            num_channels=num_channels[block]
                            if i == 0 else num_filters[block],
                            num_filters=num_filters[block],
                            stride=2 if i == 0 and block != 0 else 1,
                            shortcut=shortcut,
                            if_first=block == i == 0,
                            name=conv_name,
                            lr_mult=lr_mult))
                    self.block_list.append(basic_block)
                    shortcut = True

        self.pool2d_avg = AdaptiveAvgPool2d(1)

        self.pool2d_avg_channels = num_channels[-1] * 2

        stdv = 1.0 / math.sqrt(self.pool2d_avg_channels * 1.0)

        self.out = Linear(
            self.pool2d_avg_channels,
            class_dim,
            weight_attr=ParamAttr(
                initializer=Uniform(-stdv, stdv), name="fc_0.w_0"),
            bias_attr=ParamAttr(name="fc_0.b_0"))

    def forward(self, inputs):
        y = self.conv1_1(inputs)
        y = self.conv1_2(y)
        y = self.conv1_3(y)
        y = self.pool2d_max(y)
        for block in self.block_list:
            y = block(y)
        y = self.pool2d_avg(y)
        y = paddle.reshape(y, shape=[-1, self.pool2d_avg_channels])
        y = self.out(y)
        return y


def ResNet18_vd(**args):
    model = ResNet_vd(layers=18, **args)
    return model


def ResNet34_vd(**args):
    model = ResNet_vd(layers=34, **args)
    return model


def ResNet50_vd(**args):
    model = ResNet_vd(layers=50, **args)
    return model


def ResNet101_vd(**args):
    model = ResNet_vd(layers=101, **args)
    return model


def ResNet152_vd(**args):
    model = ResNet_vd(layers=152, **args)
    return model


def ResNet200_vd(**args):
    model = ResNet_vd(layers=200, **args)
    return model