multimae/output_adapter_utils.py

# Copyright (c) EPFL VILAB.
# All rights reserved.

# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
# --------------------------------------------------------
# Based on timm, DPT and ConvNeXt code bases
# https://github.com/rwightman/pytorch-image-models/tree/master/timm
# https://github.com/isl-org/DPT
# https://github.com/facebookresearch/ConvNeXt
# --------------------------------------------------------

import torch
import torch.nn as nn

from .multimae_utils import DropPath


class ConvNeXtBlock(nn.Module):
    r"""ConvNeXt Block. There are two equivalent implementations:
    (1) DwConv -> LayerNorm (channels_first) -> 1x1 Conv -> GELU -> 1x1 Conv; all in (N, C, H, W)
    (2) DwConv -> Permute to (N, H, W, C); LayerNorm (channels_last) -> Linear -> GELU -> Linear; Permute back
    We use (2) as we find it slightly faster in PyTorch

    Args:
        dim (int): Number of input channels.
        drop_path: Stochastic depth rate. Default: 0.0
        layer_scale_init_value (float): Init value for Layer Scale. Default: 0 (disabled for isotropic ConvNeXt).

    Code from: https://github.com/facebookresearch/ConvNeXt/blob/main/models/convnext.py
    """

    def __init__(self, dim, drop_path=0., layer_scale_init_value=0.):
        super().__init__()
        self.dwconv = nn.Conv2d(dim, dim, kernel_size=7, padding=3, groups=dim)  # depthwise conv
        self.norm = nn.LayerNorm(dim, eps=1e-6)
        self.pwconv1 = nn.Linear(dim, 4 * dim)  # pointwise/1x1 convs, implemented with linear layers
        self.act = nn.GELU()
        self.pwconv2 = nn.Linear(4 * dim, dim)
        self.gamma = nn.Parameter(layer_scale_init_value * torch.ones((dim)),
                                  requires_grad=True) if layer_scale_init_value > 0 else None
        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()

    def forward(self, x):
        input = x
        x = self.dwconv(x)
        x = x.permute(0, 2, 3, 1)  # (N, C, H, W) -> (N, H, W, C)
        x = self.norm(x)
        x = self.pwconv1(x)
        x = self.act(x)
        x = self.pwconv2(x)
        if self.gamma is not None:
            x = self.gamma * x
        x = x.permute(0, 3, 1, 2)  # (N, H, W, C) -> (N, C, H, W)

        x = input + self.drop_path(x)
        return x


class ResidualConvUnit_custom(nn.Module):
    """Residual convolution module."""

    def __init__(self, features, activation, bn):
        """Init.
        Args:
            features (int): number of features
        """
        super().__init__()

        self.bn = bn

        self.groups = 1

        self.conv1 = nn.Conv2d(
            features,
            features,
            kernel_size=3,
            stride=1,
            padding=1,
            bias=not self.bn,
            groups=self.groups,
        )

        self.conv2 = nn.Conv2d(
            features,
            features,
            kernel_size=3,
            stride=1,
            padding=1,
            bias=not self.bn,
            groups=self.groups,
        )

        if self.bn == True:
            self.bn1 = nn.BatchNorm2d(features)
            self.bn2 = nn.BatchNorm2d(features)

        self.activation = activation

        self.skip_add = nn.quantized.FloatFunctional()

    def forward(self, x):
        """Forward pass.
        Args:
            x (tensor): input
        Returns:
            tensor: output
        """

        out = self.activation(x)
        out = self.conv1(out)
        if self.bn == True:
            out = self.bn1(out)

        out = self.activation(out)
        out = self.conv2(out)
        if self.bn == True:
            out = self.bn2(out)

        if self.groups > 1:
            out = self.conv_merge(out)

        return self.skip_add.add(out, x)

def make_scratch(in_shape, out_shape, groups=1, expand=False):
    scratch = nn.Module()

    out_shape1 = out_shape
    out_shape2 = out_shape
    out_shape3 = out_shape
    out_shape4 = out_shape
    if expand == True:
        out_shape1 = out_shape
        out_shape2 = out_shape * 2
        out_shape3 = out_shape * 4
        out_shape4 = out_shape * 8

    scratch.layer1_rn = nn.Conv2d(
        in_shape[0],
        out_shape1,
        kernel_size=3,
        stride=1,
        padding=1,
        bias=False,
        groups=groups,
    )
    scratch.layer2_rn = nn.Conv2d(
        in_shape[1],
        out_shape2,
        kernel_size=3,
        stride=1,
        padding=1,
        bias=False,
        groups=groups,
    )
    scratch.layer3_rn = nn.Conv2d(
        in_shape[2],
        out_shape3,
        kernel_size=3,
        stride=1,
        padding=1,
        bias=False,
        groups=groups,
    )
    scratch.layer4_rn = nn.Conv2d(
        in_shape[3],
        out_shape4,
        kernel_size=3,
        stride=1,
        padding=1,
        bias=False,
        groups=groups,
    )

    scratch.layer_rn = nn.ModuleList([
        scratch.layer1_rn,
        scratch.layer2_rn,
        scratch.layer3_rn,
        scratch.layer4_rn,
    ])

    return scratch

class FeatureFusionBlock_custom(nn.Module):
    """Feature fusion block."""

    def __init__(
        self,
        features,
        activation,
        deconv=False,
        bn=False,
        expand=False,
        align_corners=True,
    ):
        """Init.
        Args:
            features (int): number of features
        """
        super(FeatureFusionBlock_custom, self).__init__()

        self.deconv = deconv
        self.align_corners = align_corners

        self.groups = 1

        self.expand = expand
        out_features = features
        if self.expand == True:
            out_features = features // 2

        self.out_conv = nn.Conv2d(
            features,
            out_features,
            kernel_size=1,
            stride=1,
            padding=0,
            bias=True,
            groups=1,
        )

        self.resConfUnit1 = ResidualConvUnit_custom(features, activation, bn)
        self.resConfUnit2 = ResidualConvUnit_custom(features, activation, bn)

        self.skip_add = nn.quantized.FloatFunctional()

    def forward(self, *xs):
        """Forward pass.
        Returns:
            tensor: output
        """
        output = xs[0]

        if len(xs) == 2:
            res = self.resConfUnit1(xs[1])
            output = self.skip_add.add(output, res)
            # output += res

        output = self.resConfUnit2(output)

        output = nn.functional.interpolate(
            output, scale_factor=2, mode="bilinear", align_corners=self.align_corners
        )

        output = self.out_conv(output)

        return output

def make_fusion_block(features, use_bn):
    return FeatureFusionBlock_custom(
        features,
        nn.ReLU(False),
        deconv=False,
        bn=use_bn,
        expand=False,
        align_corners=True,
    )

class Interpolate(nn.Module):
    """Interpolation module."""

    def __init__(self, scale_factor, mode, align_corners=False):
        """Init.
        Args:
            scale_factor (float): scaling
            mode (str): interpolation mode
        """
        super(Interpolate, self).__init__()

        self.interp = nn.functional.interpolate
        self.scale_factor = scale_factor
        self.mode = mode
        self.align_corners = align_corners

    def forward(self, x):
        """Forward pass.
        Args:
            x (tensor): input
        Returns:
            tensor: interpolated data
        """

        x = self.interp(
            x,
            scale_factor=self.scale_factor,
            mode=self.mode,
            align_corners=self.align_corners,
        )

        return x