resnet.py

"""This ResNet implementation is based on the one in torchvision."""
import mlx.nn as nn

from layers import flatten, global_avg_pool2d, max_pool2d

__all__ = [
    "ResNet",
    "resnet18",
    "resnet34",
    "resnet50",
    "resnet101",
    "resnet152",
]


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


def conv1x1(in_planes, out_planes, stride=1):
    """1x1 convolution."""
    return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)


class BasicBlock(nn.Module):
    expansion: int = 1

    def __init__(
        self,
        inplanes,
        planes,
        stride=1,
        downsample=None,
    ) -> None:
        super().__init__()
        norm_layer = nn.LayerNorm

        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = norm_layer(planes)
        self.relu = nn.ReLU()
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = norm_layer(planes)
        self.downsample = downsample
        self.stride = stride

    def __call__(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 Bottleneck(nn.Module):
    # Bottleneck in torchvision places the stride for downsampling at 3x3 convolution(self.conv2)
    # while original implementation places the stride at the first 1x1 convolution(self.conv1)
    # according to "Deep residual learning for image recognition" https://arxiv.org/abs/1512.03385.
    # This variant is also known as ResNet V1.5 and improves accuracy according to
    # https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch.

    expansion: int = 4

    def __init__(
        self,
        inplanes,
        planes,
        stride=1,
        downsample=None,
    ):
        super().__init__()
        width = planes
        norm_layer = nn.LayerNorm
        # Both self.conv2 and self.downsample layers downsample the input when stride != 1
        self.conv1 = conv1x1(inplanes, width)
        self.bn1 = norm_layer(width)
        self.conv2 = conv3x3(width, width, stride)
        self.bn2 = norm_layer(width)
        self.conv3 = conv1x1(width, planes * self.expansion)
        self.bn3 = norm_layer(planes * self.expansion)
        self.relu = nn.ReLU()
        self.downsample = downsample
        self.stride = stride

    def __call__(self, x):
        identity = x

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

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

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

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

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

        return out


class ResNet(nn.Module):
    def __init__(
        self,
        block,
        layers,
        num_classes,
    ):
        super().__init__()
        self._norm_layer = nn.LayerNorm

        self.inplanes = 64

        self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = self._norm_layer(self.inplanes)
        self.relu = nn.ReLU()
        self.maxpool = max_pool2d
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        self.avgpool = global_avg_pool2d
        self.fc = nn.Linear(512 * block.expansion, num_classes)

    def _make_layer(
        self,
        block,
        planes,
        blocks,
        stride=1,
    ):
        norm_layer = self._norm_layer
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                conv1x1(self.inplanes, planes * block.expansion, stride),
                norm_layer(planes * block.expansion),
            )

        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample))
        self.inplanes = planes * block.expansion
        for _ in range(1, blocks):
            layers.append(block(self.inplanes, planes))
        return nn.Sequential(*layers)

    def _forward_impl(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        x = self.avgpool(x)
        x = flatten(x)
        x = self.fc(x)

        return x

    def __call__(self, x):
        return self._forward_impl(x)


def _resnet(block, layers, **kwargs):
    return ResNet(block, layers, **kwargs)


def resnet18(*args, **kwargs):
    """ResNet-18 from `Deep Residual Learning for Image Recognition <https://arxiv.org/abs/1512.03385>`__."""
    return _resnet(BasicBlock, [2, 2, 2, 2], *args, **kwargs)


def resnet34(*args, **kwargs):
    """ResNet-34 from `Deep Residual Learning for Image Recognition <https://arxiv.org/abs/1512.03385>`__."""
    return _resnet(BasicBlock, [3, 4, 6, 3], *args, **kwargs)


def resnet50(*args, **kwargs):
    """ResNet-50 from `Deep Residual Learning for Image Recognition <https://arxiv.org/abs/1512.03385>`__."""
    return _resnet(Bottleneck, [3, 4, 6, 3], *args, **kwargs)


def resnet101(*args, **kwargs):
    """ResNet-101 from `Deep Residual Learning for Image Recognition <https://arxiv.org/abs/1512.03385>`__."""
    return _resnet(Bottleneck, [3, 4, 23, 3], *args, **kwargs)


def resnet152(*args, **kwargs):
    """ResNet-152 from `Deep Residual Learning for Image Recognition <https://arxiv.org/abs/1512.03385>`__."""
    return _resnet(Bottleneck, [3, 8, 36, 3], *args, **kwargs)