evaluation/tiny_benchmark/maskrcnn_benchmark/modeling/backbone/resnet.py

# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
"""
Variant of the resnet module that takes cfg as an argument.
Example usage. Strings may be specified in the config file.
    model = ResNet(
        "StemWithFixedBatchNorm",
        "BottleneckWithFixedBatchNorm",
        "ResNet50StagesTo4",
    )
OR:
    model = ResNet(
        "StemWithGN",
        "BottleneckWithGN",
        "ResNet50StagesTo4",
    )
Custom implementations may be written in user code and hooked in via the
`register_*` functions.
"""
from collections import namedtuple

import torch
import torch.nn.functional as F
from torch import nn

from maskrcnn_benchmark.layers import FrozenBatchNorm2d
from maskrcnn_benchmark.layers import Conv2d
from maskrcnn_benchmark.modeling.make_layers import group_norm
from maskrcnn_benchmark.utils.registry import Registry


# ResNet stage specification
StageSpec = namedtuple(
    "StageSpec",
    [
        "index",  # Index of the stage, eg 1, 2, ..,. 5
        "block_count",  # Numer of residual blocks in the stage
        "return_features",  # True => return the last feature map from this stage
    ],
)

# -----------------------------------------------------------------------------
# Standard ResNet models
# -----------------------------------------------------------------------------
# ResNet-50 (including all stages)
ResNet50StagesTo5 = tuple(
    StageSpec(index=i, block_count=c, return_features=r)
    for (i, c, r) in ((1, 3, False), (2, 4, False), (3, 6, False), (4, 3, True))
)
# ResNet-50 up to stage 4 (excludes stage 5)
ResNet50StagesTo4 = tuple(
    StageSpec(index=i, block_count=c, return_features=r)
    for (i, c, r) in ((1, 3, False), (2, 4, False), (3, 6, True))
)
# add by hui ResNet-50 up to stage 3 (excludes stage 4, 5)
ResNet50StagesTo3 = tuple(
    StageSpec(index=i, block_count=c, return_features=r)
    for (i, c, r) in ((1, 3, False), (2, 4, True))
)
# add by hui ResNet-50 up to stage 2 (excludes stage 3, 4, 5)
ResNet50StagesTo2 = tuple(
    StageSpec(index=i, block_count=c, return_features=r)
    for (i, c, r) in ((1, 3, True),)
)
# ResNet-101 (including all stages)
ResNet101StagesTo5 = tuple(
    StageSpec(index=i, block_count=c, return_features=r)
    for (i, c, r) in ((1, 3, False), (2, 4, False), (3, 23, False), (4, 3, True))
)
# ResNet-101 up to stage 4 (excludes stage 5)
ResNet101StagesTo4 = tuple(
    StageSpec(index=i, block_count=c, return_features=r)
    for (i, c, r) in ((1, 3, False), (2, 4, False), (3, 23, True))
)
# ResNet-18-FPN (including all stages), add by hui
ResNet18FPNStagesTo5 = tuple(
    StageSpec(index=i, block_count=c, return_features=r)
    for (i, c, r) in ((1, 2, True), (2, 2, True), (3, 2, True), (4, 2, True))
)
# ResNet-50-FPN (including all stages)
ResNet50FPNStagesTo5 = tuple(
    StageSpec(index=i, block_count=c, return_features=r)
    for (i, c, r) in ((1, 3, True), (2, 4, True), (3, 6, True), (4, 3, True))
)
# ResNet-101-FPN (including all stages)
ResNet101FPNStagesTo5 = tuple(
    StageSpec(index=i, block_count=c, return_features=r)
    for (i, c, r) in ((1, 3, True), (2, 4, True), (3, 23, True), (4, 3, True))
)
# ResNet-152-FPN (including all stages)
ResNet152FPNStagesTo5 = tuple(
    StageSpec(index=i, block_count=c, return_features=r)
    for (i, c, r) in ((1, 3, True), (2, 8, True), (3, 36, True), (4, 3, True))
)


class ResNet(nn.Module):
    def __init__(self, cfg):
        super(ResNet, self).__init__()

        # If we want to use the cfg in forward(), then we should make a copy
        # of it and store it for later use:
        # self.cfg = cfg.clone()

        # Translate string names to implementations
        stem_module = _STEM_MODULES[cfg.MODEL.RESNETS.STEM_FUNC]
        stage_specs = _STAGE_SPECS[cfg.MODEL.BACKBONE.CONV_BODY]
        transformation_module = _TRANSFORMATION_MODULES[cfg.MODEL.RESNETS.TRANS_FUNC]

        # Construct the stem module
        self.stem = stem_module(cfg)

        # Constuct the specified ResNet stages
        num_groups = cfg.MODEL.RESNETS.NUM_GROUPS
        width_per_group = cfg.MODEL.RESNETS.WIDTH_PER_GROUP
        in_channels = cfg.MODEL.RESNETS.STEM_OUT_CHANNELS
        stage2_bottleneck_channels = num_groups * width_per_group
        stage2_out_channels = cfg.MODEL.RESNETS.RES2_OUT_CHANNELS
        self.stages = []
        self.return_features = {}
        for i, stage_spec in enumerate(stage_specs):
            name = "layer" + str(stage_spec.index)
            stage2_relative_factor = 2 ** (stage_spec.index - 1)
            bottleneck_channels = stage2_bottleneck_channels * stage2_relative_factor
            out_channels = stage2_out_channels * stage2_relative_factor
            # ################# add by hui # ########################################################
            if len(cfg.MODEL.RESNETS.RESNET_STAGE_FIRST_STRIDE) == 0:
                stride = int(stage_spec.index > 1) + 1
            else:
                stride = cfg.MODEL.RESNETS.RESNET_STAGE_FIRST_STRIDE[i]
            if cfg.MODEL.RESNETS.TRANS_FUNC.startswith('BasicBlock'):
                module = _make_basic_stage(
                    transformation_module,
                    in_channels,
                    out_channels,
                    stage_spec.block_count,
                    num_groups,
                    first_stride=stride
                )
            else:
            # ########################################################################################
                module = _make_stage(
                    transformation_module,
                    in_channels,
                    bottleneck_channels,
                    out_channels,
                    stage_spec.block_count,
                    num_groups,
                    cfg.MODEL.RESNETS.STRIDE_IN_1X1,
                    first_stride=stride,  # changed by hui
                )
            in_channels = out_channels
            self.add_module(name, module)
            self.stages.append(name)
            self.return_features[name] = stage_spec.return_features

        # Optionally freeze (requires_grad=False) parts of the backbone
        self._freeze_backbone(cfg.MODEL.BACKBONE.FREEZE_CONV_BODY_AT)

    def _freeze_backbone(self, freeze_at):
        if freeze_at < 0:
            return
        for stage_index in range(freeze_at):
            if stage_index == 0:
                m = self.stem  # stage 0 is the stem
            else:
                m = getattr(self, "layer" + str(stage_index))
            for p in m.parameters():
                p.requires_grad = False

    def forward(self, x):
        outputs = []
        x = self.stem(x)
        for stage_name in self.stages:
            x = getattr(self, stage_name)(x)
            if self.return_features[stage_name]:
                outputs.append(x)
        return outputs


class ResNetHead(nn.Module):
    def __init__(
        self,
        block_module,
        stages,
        num_groups=1,
        width_per_group=64,
        stride_in_1x1=True,
        stride_init=None,
        res2_out_channels=256,
        dilation=1
    ):
        super(ResNetHead, self).__init__()

        stage2_relative_factor = 2 ** (stages[0].index - 1)
        stage2_bottleneck_channels = num_groups * width_per_group
        out_channels = res2_out_channels * stage2_relative_factor
        in_channels = out_channels // 2
        bottleneck_channels = stage2_bottleneck_channels * stage2_relative_factor

        block_module = _TRANSFORMATION_MODULES[block_module]

        self.stages = []
        stride = stride_init
        for stage in stages:
            name = "layer" + str(stage.index)
            if not stride:
                stride = int(stage.index > 1) + 1
            module = _make_stage(
                block_module,
                in_channels,
                bottleneck_channels,
                out_channels,
                stage.block_count,
                num_groups,
                stride_in_1x1,
                first_stride=stride,
                dilation=dilation
            )
            stride = None
            self.add_module(name, module)
            self.stages.append(name)
        self.out_channels = out_channels

    def forward(self, x):
        for stage in self.stages:
            x = getattr(self, stage)(x)
        return x


def _make_stage(
    transformation_module,
    in_channels,
    bottleneck_channels,
    out_channels,
    block_count,
    num_groups,
    stride_in_1x1,
    first_stride,
    dilation=1
):
    blocks = []
    stride = first_stride
    for _ in range(block_count):
        blocks.append(
            transformation_module(
                in_channels,
                bottleneck_channels,
                out_channels,
                num_groups,
                stride_in_1x1,
                stride,
                dilation=dilation
            )
        )
        stride = 1
        in_channels = out_channels
    return nn.Sequential(*blocks)


class Bottleneck(nn.Module):
    def __init__(
        self,
        in_channels,
        bottleneck_channels,
        out_channels,
        num_groups,
        stride_in_1x1,
        stride,
        dilation,
        norm_func
    ):
        super(Bottleneck, self).__init__()

        self.downsample = None
        if in_channels != out_channels:
            down_stride = stride if dilation == 1 else 1
            self.downsample = nn.Sequential(
                Conv2d(
                    in_channels, out_channels,
                    kernel_size=1, stride=down_stride, bias=False
                ),
                norm_func(out_channels),
            )
            for modules in [self.downsample,]:
                for l in modules.modules():
                    if isinstance(l, Conv2d):
                        nn.init.kaiming_uniform_(l.weight, a=1)

        if dilation > 1:
            stride = 1  # reset to be 1

        # The original MSRA ResNet models have stride in the first 1x1 conv
        # The subsequent fb.torch.resnet and Caffe2 ResNe[X]t implementations have
        # stride in the 3x3 conv
        stride_1x1, stride_3x3 = (stride, 1) if stride_in_1x1 else (1, stride)

        self.conv1 = Conv2d(
            in_channels,
            bottleneck_channels,
            kernel_size=1,
            stride=stride_1x1,
            bias=False,
        )
        self.bn1 = norm_func(bottleneck_channels)
        # TODO: specify init for the above

        self.conv2 = Conv2d(
            bottleneck_channels,
            bottleneck_channels,
            kernel_size=3,
            stride=stride_3x3,
            padding=dilation,
            bias=False,
            groups=num_groups,
            dilation=dilation
        )
        self.bn2 = norm_func(bottleneck_channels)

        self.conv3 = Conv2d(
            bottleneck_channels, out_channels, kernel_size=1, bias=False
        )
        self.bn3 = norm_func(out_channels)

        for l in [self.conv1, self.conv2, self.conv3,]:
            nn.init.kaiming_uniform_(l.weight, a=1)

    def forward(self, x):
        identity = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = F.relu_(out)

        out = self.conv2(out)
        out = self.bn2(out)
        out = F.relu_(out)

        out0 = self.conv3(out)
        out = self.bn3(out0)

        if self.downsample is not None:
            identity = self.downsample(x)

        out += identity
        out = F.relu_(out)

        return out


class BaseStem(nn.Module):
    def __init__(self, cfg, norm_func):
        super(BaseStem, self).__init__()

        out_channels = cfg.MODEL.RESNETS.STEM_OUT_CHANNELS
        stride = cfg.MODEL.RESNETS.STEM_STRIDE

        self.conv1 = Conv2d(
            3, out_channels, kernel_size=7, stride=stride, padding=3, bias=False
        )
        self.bn1 = norm_func(out_channels)

        for l in [self.conv1,]:
            nn.init.kaiming_uniform_(l.weight, a=1)

        self.remove_max_pooling = cfg.MODEL.RESNETS.REMOVE_STEM_POOL  # add by hui

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = F.relu_(x)
        if not self.remove_max_pooling:  # changed by hui
            x = F.max_pool2d(x, kernel_size=3, stride=2, padding=1)
        return x


class BottleneckWithFixedBatchNorm(Bottleneck):
    def __init__(
        self,
        in_channels,
        bottleneck_channels,
        out_channels,
        num_groups=1,
        stride_in_1x1=True,
        stride=1,
        dilation=1
    ):
        super(BottleneckWithFixedBatchNorm, self).__init__(
            in_channels=in_channels,
            bottleneck_channels=bottleneck_channels,
            out_channels=out_channels,
            num_groups=num_groups,
            stride_in_1x1=stride_in_1x1,
            stride=stride,
            dilation=dilation,
            norm_func=FrozenBatchNorm2d
        )


class StemWithFixedBatchNorm(BaseStem):
    def __init__(self, cfg):
        super(StemWithFixedBatchNorm, self).__init__(
            cfg, norm_func=FrozenBatchNorm2d
        )


class BottleneckWithGN(Bottleneck):
    def __init__(
        self,
        in_channels,
        bottleneck_channels,
        out_channels,
        num_groups=1,
        stride_in_1x1=True,
        stride=1,
        dilation=1
    ):
        super(BottleneckWithGN, self).__init__(
            in_channels=in_channels,
            bottleneck_channels=bottleneck_channels,
            out_channels=out_channels,
            num_groups=num_groups,
            stride_in_1x1=stride_in_1x1,
            stride=stride,
            dilation=dilation,
            norm_func=group_norm
        )


class StemWithGN(BaseStem):
    def __init__(self, cfg):
        super(StemWithGN, self).__init__(cfg, norm_func=group_norm)


# add by hui copy from https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py ####################
def conv1x1(in_planes, out_planes, stride=1):
    """1x1 convolution"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)


def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=dilation, groups=groups, bias=False, dilation=dilation)


def _make_basic_stage(
    transformation_module,
    in_channels,
    out_channels,
    block_count,
    num_groups,
    first_stride,
    dilation=1
):
    blocks = []
    stride = first_stride
    for _ in range(block_count):
        blocks.append(
            transformation_module(
                in_channels,
                out_channels,
                num_groups,
                stride,
                dilation=dilation
            )
        )
        stride = 1
        in_channels = out_channels
    return nn.Sequential(*blocks)


class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,
                 base_width=64, dilation=1, norm_layer=None):
        super(BasicBlock, self).__init__()
        if norm_layer is None:
            norm_layer = nn.BatchNorm2d
        if groups != 1 or base_width != 64:
            raise ValueError('BasicBlock only supports groups=1 and base_width=64')
        if dilation > 1:
            raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
        # Both self.conv1 and self.downsample layers downsample the input when stride != 1
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = norm_layer(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = norm_layer(planes)
        self.downsample = downsample
        self.stride = stride

        if downsample is None:
            if stride != 1 or inplanes != planes * BasicBlock.expansion:
                self.downsample = nn.Sequential(
                    conv1x1(inplanes, planes * BasicBlock.expansion, stride),
                    norm_layer(planes * BasicBlock.expansion),
                )
                for modules in [self.downsample, ]:
                    for l in modules.modules():
                        if isinstance(l, Conv2d):
                            nn.init.kaiming_uniform_(l.weight, a=1)
        for l in [self.conv1, self.conv2, ]:
            nn.init.kaiming_uniform_(l.weight, a=1)

    def forward(self, x):
        identity = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        if self.downsample is not None:
            identity = self.downsample(x)

        out += identity
        out = self.relu(out)

        return out


class BasicBlockWithFixedBatchNorm(BasicBlock):
    def __init__(
        self,
        in_channels,
        out_channels,
        num_groups=1,
        stride=1,
        dilation=1
    ):
        super(BasicBlockWithFixedBatchNorm, self).__init__(
            inplanes=in_channels,
            planes=out_channels,
            groups=num_groups,
            stride=stride,
            dilation=dilation,
            norm_layer=FrozenBatchNorm2d
        )
# ################################################################################################################


_TRANSFORMATION_MODULES = Registry({
    "BasicBlockWithFixedBatchNorm": BasicBlockWithFixedBatchNorm,  # add by hui
    "BottleneckWithFixedBatchNorm": BottleneckWithFixedBatchNorm,
    "BottleneckWithGN": BottleneckWithGN,
})

_STEM_MODULES = Registry({
    "StemWithFixedBatchNorm": StemWithFixedBatchNorm,
    "StemWithGN": StemWithGN,
})

_STAGE_SPECS = Registry({
    "R-50-C2": ResNet50StagesTo2,  # add by hui
    "R-50-C3": ResNet50StagesTo3,    # add by hui
    "R-50-C4": ResNet50StagesTo4,
    "R-50-C5": ResNet50StagesTo5,
    "R-101-C4": ResNet101StagesTo4,
    "R-101-C5": ResNet101StagesTo5,
    "R-18-FPN": ResNet18FPNStagesTo5,  # add by hui
    "R-50-FPN": ResNet50FPNStagesTo5,
    "R-50-FPN-RETINANET": ResNet50FPNStagesTo5,
    "R-101-FPN": ResNet101FPNStagesTo5,
    "R-101-FPN-RETINANET": ResNet101FPNStagesTo5,
    "R-152-FPN": ResNet152FPNStagesTo5,
})