mindspore/model_zoo/resnet50_quant/models/resnet_quant.py

# Copyright 2020 Huawei Technologies Co., Ltd
#
# 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.
# ============================================================================
"""ResNet."""
import mindspore.nn as nn
from mindspore.ops import operations as P


class ConvBNReLU(nn.Cell):
    """
    Convolution/Depthwise fused with Batchnorm and ReLU block definition.

    Args:
        in_planes (int): Input channel.
        out_planes (int): Output channel.
        kernel_size (int): Input kernel size.
        stride (int): Stride size for the first convolutional layer. Default: 1.
        groups (int): channel group. Convolution is 1 while Depthiwse is input channel. Default: 1.

    Returns:
        Tensor, output tensor.

    Examples:
        >>> ConvBNReLU(16, 256, kernel_size=1, stride=1, groups=1)
    """

    def __init__(self, in_planes, out_planes, kernel_size=3, stride=1, groups=1):
        super(ConvBNReLU, self).__init__()
        padding = (kernel_size - 1) // 2
        conv = nn.Conv2dBnAct(in_planes, out_planes, kernel_size, stride, pad_mode='pad', padding=padding,
                              group=groups, has_bn=True, activation='relu')
        self.features = conv

    def construct(self, x):
        output = self.features(x)
        return output


class ResidualBlock(nn.Cell):
    """
    ResNet V1 residual block definition.

    Args:
        in_channel (int): Input channel.
        out_channel (int): Output channel.
        stride (int): Stride size for the first convolutional layer. Default: 1.

    Returns:
        Tensor, output tensor.

    Examples:
        >>> ResidualBlock(3, 256, stride=2)
    """
    expansion = 4

    def __init__(self,
                 in_channel,
                 out_channel,
                 stride=1):
        super(ResidualBlock, self).__init__()

        channel = out_channel // self.expansion
        self.conv1 = ConvBNReLU(in_channel, channel, kernel_size=1, stride=1)
        self.conv2 = ConvBNReLU(channel, channel, kernel_size=3, stride=stride)
        self.conv3 = nn.Conv2dBnAct(channel, out_channel, kernel_size=1, stride=1, pad_mode='same', padding=0,
                                    has_bn=True, activation='relu')

        self.down_sample = False
        if stride != 1 or in_channel != out_channel:
            self.down_sample = True
        self.down_sample_layer = None

        if self.down_sample:
            self.down_sample_layer = nn.Conv2dBnAct(in_channel, out_channel,
                                                    kernel_size=1, stride=stride,
                                                    pad_mode='same', padding=0, has_bn=True, activation='relu')
        self.add = P.TensorAdd()
        self.relu = P.ReLU()

    def construct(self, x):
        identity = x
        out = self.conv1(x)
        out = self.conv2(out)
        out = self.conv3(out)

        if self.down_sample:
            identity = self.down_sample_layer(identity)

        out = self.add(out, identity)
        out = self.relu(out)

        return out


class ResNet(nn.Cell):
    """
    ResNet architecture.

    Args:
        block (Cell): Block for network.
        layer_nums (list): Numbers of block in different layers.
        in_channels (list): Input channel in each layer.
        out_channels (list): Output channel in each layer.
        strides (list):  Stride size in each layer.
        num_classes (int): The number of classes that the training images are belonging to.
    Returns:
        Tensor, output tensor.

    Examples:
        >>> ResNet(ResidualBlock,
        >>>        [3, 4, 6, 3],
        >>>        [64, 256, 512, 1024],
        >>>        [256, 512, 1024, 2048],
        >>>        [1, 2, 2, 2],
        >>>        10)
    """

    def __init__(self,
                 block,
                 layer_nums,
                 in_channels,
                 out_channels,
                 strides,
                 num_classes):
        super(ResNet, self).__init__()

        if not len(layer_nums) == len(in_channels) == len(out_channels) == 4:
            raise ValueError("the length of layer_num, in_channels, out_channels list must be 4!")

        self.conv1 = ConvBNReLU(3, 64, kernel_size=7, stride=2)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, pad_mode="same")

        self.layer1 = self._make_layer(block,
                                       layer_nums[0],
                                       in_channel=in_channels[0],
                                       out_channel=out_channels[0],
                                       stride=strides[0])
        self.layer2 = self._make_layer(block,
                                       layer_nums[1],
                                       in_channel=in_channels[1],
                                       out_channel=out_channels[1],
                                       stride=strides[1])
        self.layer3 = self._make_layer(block,
                                       layer_nums[2],
                                       in_channel=in_channels[2],
                                       out_channel=out_channels[2],
                                       stride=strides[2])
        self.layer4 = self._make_layer(block,
                                       layer_nums[3],
                                       in_channel=in_channels[3],
                                       out_channel=out_channels[3],
                                       stride=strides[3])

        self.mean = P.ReduceMean(keep_dims=True)
        self.flatten = nn.Flatten()
        self.end_point = nn.DenseBnAct(out_channels[3], num_classes, has_bias=True, has_bn=False)

    def _make_layer(self, block, layer_num, in_channel, out_channel, stride):
        """
        Make stage network of ResNet.

        Args:
            block (Cell): Resnet block.
            layer_num (int): Layer number.
            in_channel (int): Input channel.
            out_channel (int): Output channel.
            stride (int): Stride size for the first convolutional layer.

        Returns:
            SequentialCell, the output layer.

        Examples:
            >>> _make_layer(ResidualBlock, 3, 128, 256, 2)
        """
        layers = []

        resnet_block = block(in_channel, out_channel, stride=stride)
        layers.append(resnet_block)

        for _ in range(1, layer_num):
            resnet_block = block(out_channel, out_channel, stride=1)
            layers.append(resnet_block)

        return nn.SequentialCell(layers)

    def construct(self, x):
        x = self.conv1(x)
        c1 = self.maxpool(x)

        c2 = self.layer1(c1)
        c3 = self.layer2(c2)
        c4 = self.layer3(c3)
        c5 = self.layer4(c4)

        out = self.mean(c5, (2, 3))
        out = self.flatten(out)
        out = self.end_point(out)
        return out


def resnet50_quant(class_num=10001):
    """
    Get ResNet50 neural network.

    Args:
        class_num (int): Class number.

    Returns:
        Cell, cell instance of ResNet50 neural network.

    Examples:
        >>> net = resnet50_quant(10)
    """
    return ResNet(ResidualBlock,
                  [3, 4, 6, 3],
                  [64, 256, 512, 1024],
                  [256, 512, 1024, 2048],
                  [1, 2, 2, 2],
                  class_num)


def resnet101_quant(class_num=1001):
    """
    Get ResNet101 neural network.

    Args:
        class_num (int): Class number.

    Returns:
        Cell, cell instance of ResNet101 neural network.

    Examples:
        >>> net = resnet101(1001)
    """
    return ResNet(ResidualBlock,
                  [3, 4, 23, 3],
                  [64, 256, 512, 1024],
                  [256, 512, 1024, 2048],
                  [1, 2, 2, 2],
                  class_num)