resnet.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.

import paddle.fluid as fluid
from paddle.fluid.layer_helper import LayerHelper
from paddle.fluid.dygraph.nn import Conv2D, Pool2D, BatchNorm, Linear

import math

__all__ = [
    "ResNet18",
    "ResNet34",
    "ResNet50",
    "ResNet101",
    "ResNet152",
]


class ConvBNLayer(fluid.dygraph.Layer):
    def __init__(self,
                 num_channels,
                 num_filters,
                 filter_size,
                 stride=1,
                 groups=1,
                 act=None):
        super(ConvBNLayer, self).__init__()

        self._conv = Conv2D(
            num_channels=num_channels,
            num_filters=num_filters,
            filter_size=filter_size,
            stride=stride,
            padding=(filter_size - 1) // 2,
            groups=groups,
            act=None,
            bias_attr=False)

        self._batch_norm = BatchNorm(num_filters, act=act)

    def forward(self, inputs):
        y = self._conv(inputs)
        y = self._batch_norm(y)

        return y


class BottleneckBlock(fluid.dygraph.Layer):
    def __init__(self, num_channels, num_filters, stride, shortcut=True):
        super(BottleneckBlock, self).__init__()

        self.conv0 = ConvBNLayer(
            num_channels=num_channels,
            num_filters=num_filters,
            filter_size=1,
            act='relu')
        self.conv1 = ConvBNLayer(
            num_channels=num_filters,
            num_filters=num_filters,
            filter_size=3,
            stride=stride,
            act='relu')
        self.conv2 = ConvBNLayer(
            num_channels=num_filters,
            num_filters=num_filters * 4,
            filter_size=1,
            act=None)

        if not shortcut:
            self.short = ConvBNLayer(
                num_channels=num_channels,
                num_filters=num_filters * 4,
                filter_size=1,
                stride=stride)

        self.shortcut = shortcut

        self._num_channels_out = num_filters * 4

    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 = fluid.layers.elementwise_add(x=short, y=conv2)

        layer_helper = LayerHelper(self.full_name(), act='relu')
        return layer_helper.append_activation(y)


class ResNet(fluid.dygraph.Layer):
    def __init__(self, layers=50, class_dim=1000):
        super(ResNet, self).__init__()

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

        if layers == 50:
            depth = [3, 4, 6, 3]
        elif layers == 101:
            depth = [3, 4, 23, 3]
        elif layers == 152:
            depth = [3, 8, 36, 3]
        num_channels = [64, 256, 512, 1024]
        num_filters = [64, 128, 256, 512]

        self.conv = ConvBNLayer(
            num_channels=3,
            num_filters=64,
            filter_size=7,
            stride=2,
            act='relu')
        self.pool2d_max = Pool2D(
            pool_size=3, pool_stride=2, pool_padding=1, pool_type='max')

        self.bottleneck_block_list = []
        for block in range(len(depth)):
            shortcut = False
            for i in range(depth[block]):
                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))
                self.bottleneck_block_list.append(bottleneck_block)
                shortcut = True

        self.pool2d_avg = Pool2D(
            pool_size=7, pool_type='avg', global_pooling=True)

        self.pool2d_avg_output = num_filters[len(num_filters) - 1] * 4 * 1 * 1

        stdv = 1.0 / math.sqrt(2048 * 1.0)

        self.out = Linear(
            self.pool2d_avg_output,
            class_dim,
            param_attr=fluid.param_attr.ParamAttr(
                initializer=fluid.initializer.Uniform(-stdv, stdv)))

    def forward(self, inputs):
        y = self.conv(inputs)
        y = self.pool2d_max(y)
        for bottleneck_block in self.bottleneck_block_list:
            y = bottleneck_block(y)
        y = self.pool2d_avg(y)
        y = fluid.layers.reshape(y, shape=[-1, self.pool2d_avg_output])
        y = self.out(y)
        return y


def ResNet18(**kwargs):
    model = ResNet(layers=18, **kwargs)
    return model


def ResNet34(**kwargs):
    model = ResNet(layers=34, **kwargs)
    return model


def ResNet50(**kwargs):
    model = ResNet(layers=50, **kwargs)
    return model


def ResNet101(**kwargs):
    model = ResNet(layers=101, **kwargs)
    return model


def ResNet152(class_dim=1000):
    model = ResNet(layers=152, class_dim=class_dim)
    return model