INCEPT_V3_3D.py

from __future__ import division

from collections import namedtuple
import warnings
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.jit.annotations import Optional
from torch import Tensor

InceptionOutputs = namedtuple('InceptionOutputs', ['logits', 'aux_logits','embedding'])
InceptionOutputs.__annotations__ = {'logits': torch.Tensor, 'aux_logits': Optional[torch.Tensor],'embedding': torch.Tensor}


class Inception3_3D(nn.Module):
    def __init__(self, num_classes=2, aux_logits=True, transform_input=False,
                 inception_blocks=None, init_weights=False):
        super(Inception3_3D, self).__init__()
        if inception_blocks is None:
            inception_blocks = [
                BasicConv3d, InceptionA, InceptionB, InceptionC,
                InceptionD, InceptionE, InceptionAux
            ]
        assert len(inception_blocks) == 7
        conv_block = inception_blocks[0]
        inception_a = inception_blocks[1]
        inception_b = inception_blocks[2]
        inception_c = inception_blocks[3]
        inception_d = inception_blocks[4]
        inception_e = inception_blocks[5]
        inception_aux = inception_blocks[6]

        self.aux_logits = aux_logits
        self.transform_input = transform_input
        self.Conv2d_1a_3x3 = conv_block(1, 32, kernel_size=3, stride=2)
        self.Conv2d_2a_3x3 = conv_block(32, 32, kernel_size=3)
        self.Conv2d_2b_3x3 = conv_block(32, 64, kernel_size=3, padding=1)
        self.Conv2d_3b_1x1 = conv_block(64, 80, kernel_size=1)
        self.Conv2d_4a_3x3 = conv_block(80, 192, kernel_size=3)
        self.Mixed_5b = inception_a(192, pool_features=32)
        self.Mixed_5c = inception_a(256, pool_features=64)
        self.Mixed_5d = inception_a(288, pool_features=64)
        self.Mixed_6a = inception_b(288)
        self.Mixed_6b = inception_c(768, channels_7x7=128)
        self.Mixed_6c = inception_c(768, channels_7x7=160)
        self.Mixed_6d = inception_c(768, channels_7x7=160)
        self.Mixed_6e = inception_c(768, channels_7x7=192)
        if aux_logits:
            self.AuxLogits = inception_aux(768, num_classes)
        self.Mixed_7a = inception_d(768)
        self.Mixed_7b = inception_e(1280)
        self.Mixed_7c = inception_e(2816)
        self.fc = nn.Linear(2816, num_classes)
        if init_weights:
            for m in self.modules():
                if isinstance(m, nn.Conv2d) or isinstance(m, nn.Linear):
                    import scipy.stats as stats
                    stddev = m.stddev if hasattr(m, 'stddev') else 0.1
                    X = stats.truncnorm(-2, 2, scale=stddev)
                    values = torch.as_tensor(X.rvs(m.weight.numel()), dtype=m.weight.dtype)
                    values = values.view(m.weight.size())
                    with torch.no_grad():
                        m.weight.copy_(values)
                elif isinstance(m, nn.BatchNorm2d):
                    nn.init.constant_(m.weight, 1)
                    nn.init.constant_(m.bias, 0)

    def _transform_input(self, x):
        if self.transform_input:
            x_ch0 = torch.unsqueeze(x[:, 0], 1) * (0.229 / 0.5) + (0.485 - 0.5) / 0.5
            x_ch1 = torch.unsqueeze(x[:, 1], 1) * (0.224 / 0.5) + (0.456 - 0.5) / 0.5
            x_ch2 = torch.unsqueeze(x[:, 2], 1) * (0.225 / 0.5) + (0.406 - 0.5) / 0.5
            x = torch.cat((x_ch0, x_ch1, x_ch2), 1)
        return x

    def _forward(self, x):
        # N x 3 x 299 x 299
        x = self.Conv2d_1a_3x3(x)
        # N x 32 x 149 x 149
        x = self.Conv2d_2a_3x3(x)
        # N x 32 x 147 x 147
        x = self.Conv2d_2b_3x3(x)
        # N x 64 x 147 x 147
        x = F.max_pool3d(x, kernel_size=3, stride=2)
        # N x 64 x 73 x 73
        x = self.Conv2d_3b_1x1(x)
        # N x 80 x 73 x 73
        x = self.Conv2d_4a_3x3(x)
        # N x 192 x 71 x 71
        x = F.max_pool3d(x, kernel_size=3, stride=2)
        # N x 192 x 35 x 35
        x = self.Mixed_5b(x)
        # N x 256 x 35 x 35
        x = self.Mixed_5c(x)
        # N x 288 x 35 x 35
        x = self.Mixed_5d(x)
        # N x 288 x 35 x 35
        x = self.Mixed_6a(x)
        # N x 768 x 17 x 17
        x = self.Mixed_6b(x)
        # N x 768 x 17 x 17
        x = self.Mixed_6c(x)
        # N x 768 x 17 x 17
        x = self.Mixed_6d(x)
        # N x 768 x 17 x 17
        x = self.Mixed_6e(x)
        # N x 768 x 17 x 17
        aux_defined = self.training and self.aux_logits
        if aux_defined:
            aux = self.AuxLogits(x)
        else:
            aux = None
        # N x 768 x 17 x 17
        x = self.Mixed_7a(x)
        # N x 1280 x 8 x 8
        x = self.Mixed_7b(x)
        # N x 2048 x 8 x 8
        x = self.Mixed_7c(x)
        # N x 2048 x 8 x 8
        # Adaptive average pooling
        x = F.adaptive_avg_pool3d(x, (1, 1,1))
        embedding = x
        # N x 2048 x 1 x 1
        x = F.dropout(x, training=self.training)
        # N x 2048 x 1 x 1
        x = torch.flatten(x, 1)
        # N x 2048
        x = self.fc(x)
        # N x 1000 (num_classes)
        return x, aux, embedding

    @torch.jit.unused
    def eager_outputs(self, x, aux, embedding):
        if self.training and self.aux_logits:
            return InceptionOutputs(x, aux, embedding).logits
        else:
            return x

    def forward(self, x):
        x = self._transform_input(x)
        x, aux, embedding = self._forward(x)
        aux_defined = self.training and self.aux_logits
        if torch.jit.is_scripting():
            if not aux_defined:
                warnings.warn("Scripted Inception3 always returns Inception3 Tuple")
            return InceptionOutputs(x, aux, embedding).logits
        else:
            return self.eager_outputs(x, aux, embedding)


class InceptionA(nn.Module):

    def __init__(self, in_channels, pool_features, conv_block=None):
        super(InceptionA, self).__init__()
        if conv_block is None:
            conv_block = BasicConv3d
        self.branch1x1 = conv_block(in_channels, 64, kernel_size=1)

        self.branch5x5_1 = conv_block(in_channels, 48, kernel_size=1)
        self.branch5x5_2 = conv_block(48, 64, kernel_size=5, padding=2)

        self.branch3x3dbl_1 = conv_block(in_channels, 64, kernel_size=1)
        self.branch3x3dbl_2 = conv_block(64, 96, kernel_size=3, padding=1)
        self.branch3x3dbl_3 = conv_block(96, 96, kernel_size=3, padding=1)

        self.branch_pool = conv_block(in_channels, pool_features, kernel_size=1)

    def _forward(self, x):
        branch1x1 = self.branch1x1(x)

        branch5x5 = self.branch5x5_1(x)
        branch5x5 = self.branch5x5_2(branch5x5)

        branch3x3dbl = self.branch3x3dbl_1(x)
        branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
        branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl)

        branch_pool = F.avg_pool3d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)

        outputs = [branch1x1, branch5x5, branch3x3dbl, branch_pool]
        return outputs

    def forward(self, x):
        outputs = self._forward(x)
        return torch.cat(outputs, 1)


class InceptionB(nn.Module):

    def __init__(self, in_channels, conv_block=None):
        super(InceptionB, self).__init__()
        if conv_block is None:
            conv_block = BasicConv3d
        self.branch3x3 = conv_block(in_channels, 384, kernel_size=3, stride=2)

        self.branch3x3dbl_1 = conv_block(in_channels, 64, kernel_size=1)
        self.branch3x3dbl_2 = conv_block(64, 96, kernel_size=3, padding=1)
        self.branch3x3dbl_3 = conv_block(96, 96, kernel_size=3, stride=2)

    def _forward(self, x):
        branch3x3 = self.branch3x3(x)

        branch3x3dbl = self.branch3x3dbl_1(x)
        branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
        branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl)

        branch_pool = F.max_pool3d(x, kernel_size=3, stride=2)

        outputs = [branch3x3, branch3x3dbl, branch_pool]
        return outputs

    def forward(self, x):
        outputs = self._forward(x)
        return torch.cat(outputs, 1)


class InceptionC(nn.Module):

    def __init__(self, in_channels, channels_7x7, conv_block=None):
        super(InceptionC, self).__init__()
        if conv_block is None:
            conv_block = BasicConv3d
        self.branch1x1 = conv_block(in_channels, 192, kernel_size=1)

        c7 = channels_7x7
        self.branch7x7_1 = conv_block(in_channels, c7, kernel_size=1)
        self.branch7x7_1a = conv_block(c7,c7,kernel_size=(1,1,7), padding=(0,0, 3))
        self.branch7x7_2 = conv_block(c7, c7, kernel_size=(1, 7,1), padding=(0, 3, 0))
        self.branch7x7_3 = conv_block(c7, 192, kernel_size=(7, 1,1), padding=(3, 0, 0))

        self.branch7x7dbl_1 = conv_block(in_channels, c7, kernel_size=1)
        self.branch7x7dbl_2 = conv_block(c7, c7, kernel_size=(7, 1, 1), padding=(3, 0, 0))
        self.branch7x7dbl_3 = conv_block(c7, c7, kernel_size=(1, 7,1), padding=(0, 3,0))
        self.branch7x7dbl_1a = conv_block(c7, c7, kernel_size=(1, 1, 7), padding=(0,0,3))
        self.branch7x7dbl_3a = conv_block(c7, c7, kernel_size=(7, 1, 1), padding=(3,0,0))
        self.branch7x7dbl_4 = conv_block(c7, c7, kernel_size=(1, 7, 1), padding=(0,3, 0))
        self.branch7x7dbl_5 = conv_block(c7, 192, kernel_size=(1,1, 7), padding=(0, 0, 3))

        self.branch_pool = conv_block(in_channels, 192, kernel_size=1)

    def _forward(self, x):
        branch1x1 = self.branch1x1(x)

        branch7x7 = self.branch7x7_1(x)
        branch7x7 = self.branch7x7_1a(branch7x7)
        branch7x7 = self.branch7x7_2(branch7x7)
        branch7x7 = self.branch7x7_3(branch7x7)

        branch7x7dbl = self.branch7x7dbl_1(x)
        branch7x7dbl = self.branch7x7dbl_2(branch7x7dbl)
        branch7x7dbl = self.branch7x7dbl_3(branch7x7dbl)
        branch7x7dbl = self.branch7x7dbl_1a(branch7x7dbl)
        branch7x7dbl = self.branch7x7dbl_3a(branch7x7dbl)
        branch7x7dbl = self.branch7x7dbl_4(branch7x7dbl)
        branch7x7dbl = self.branch7x7dbl_5(branch7x7dbl)

        branch_pool = F.avg_pool3d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)

        outputs = [branch1x1, branch7x7, branch7x7dbl, branch_pool]
        return outputs

    def forward(self, x):
        outputs = self._forward(x)
        return torch.cat(outputs, 1)


class InceptionD(nn.Module):

    def __init__(self, in_channels, conv_block=None):
        super(InceptionD, self).__init__()
        if conv_block is None:
            conv_block = BasicConv3d
        self.branch3x3_1 = conv_block(in_channels, 192, kernel_size=1)
        self.branch3x3_2 = conv_block(192, 320, kernel_size=3, stride=2)

        self.branch7x7x3_1 = conv_block(in_channels, 192, kernel_size=1)
        self.branch7x7x3_1a = conv_block(192,192, kernel_size=(1, 1, 7), padding = (0,0,3))
        self.branch7x7x3_2 = conv_block(192, 192, kernel_size=(1, 7, 1), padding=(0, 3,0))
        self.branch7x7x3_3 = conv_block(192, 192, kernel_size=(7, 1, 1), padding=(3, 0, 0))
        self.branch7x7x3_4 = conv_block(192, 192, kernel_size=3, stride=2)

    def _forward(self, x):
        branch3x3 = self.branch3x3_1(x)
        branch3x3 = self.branch3x3_2(branch3x3)

        branch7x7x3 = self.branch7x7x3_1(x)
        branch7x7x3 = self.branch7x7x3_1a(branch7x7x3)
        branch7x7x3 = self.branch7x7x3_2(branch7x7x3)
        branch7x7x3 = self.branch7x7x3_3(branch7x7x3)
        branch7x7x3 = self.branch7x7x3_4(branch7x7x3)

        branch_pool = F.max_pool3d(x, kernel_size=3, stride=2)
        outputs = [branch3x3, branch7x7x3, branch_pool]
        return outputs

    def forward(self, x):
        outputs = self._forward(x)
        return torch.cat(outputs, 1)


class InceptionE(nn.Module):

    def __init__(self, in_channels, conv_block=None):
        super(InceptionE, self).__init__()
        if conv_block is None:
            conv_block = BasicConv3d
        self.branch1x1 = conv_block(in_channels, 320, kernel_size=1)

        self.branch3x3_1 = conv_block(in_channels, 384, kernel_size=1)
        self.branch3x3_2c = conv_block(384, 384, kernel_size=(1, 1, 3), padding=(0, 0, 1))
        self.branch3x3_2a = conv_block(384, 384, kernel_size=(1, 3, 1), padding=(0, 1, 0))
        self.branch3x3_2b = conv_block(384, 384, kernel_size=(3, 1, 1), padding=(1, 0, 0))

        self.branch3x3dbl_1 = conv_block(in_channels, 448, kernel_size=1)
        self.branch3x3dbl_2 = conv_block(448, 384, kernel_size=3, padding=1)
        self.branch3x3dbl_3c = conv_block(384, 384, kernel_size=(1, 1, 3), padding=(0, 0, 1))
        self.branch3x3dbl_3a = conv_block(384, 384, kernel_size=(1, 3, 1), padding=(0, 1, 0))
        self.branch3x3dbl_3b = conv_block(384, 384, kernel_size=(3, 1, 1), padding=(1, 0, 0))

        self.branch_pool = conv_block(in_channels, 192, kernel_size=1)

    def _forward(self, x):
        branch1x1 = self.branch1x1(x)

        branch3x3 = self.branch3x3_1(x)
        branch3x3 = [
            self.branch3x3_2c(branch3x3),
            self.branch3x3_2a(branch3x3),
            self.branch3x3_2b(branch3x3)

        ]
        branch3x3 = torch.cat(branch3x3, 1)

        branch3x3dbl = self.branch3x3dbl_1(x)
        branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
        branch3x3dbl = [
            self.branch3x3dbl_3c(branch3x3dbl),
            self.branch3x3dbl_3a(branch3x3dbl),
            self.branch3x3dbl_3b(branch3x3dbl),
        ]
        branch3x3dbl = torch.cat(branch3x3dbl, 1)

        branch_pool = F.avg_pool3d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)

        outputs = [branch1x1, branch3x3, branch3x3dbl, branch_pool]
        return outputs

    def forward(self, x):
        outputs = self._forward(x)
        return torch.cat(outputs, 1)


class InceptionAux(nn.Module):

    def __init__(self, in_channels, num_classes, conv_block=None):
        super(InceptionAux, self).__init__()
        if conv_block is None:
            conv_block = BasicConv3d
        self.conv0 = conv_block(in_channels, 128, kernel_size=1)
        self.conv1 = BasicConv3d_nopad(128,768, kernel_size=1)
        self.conv1.stddev = 0.01
        self.fc = nn.Linear(768, num_classes)
        self.fc.stddev = 0.001

    def forward(self, x):
        # N x 768 x 17 x 17
        x = F.avg_pool3d(x, kernel_size=5, stride=3)
        # N x 768 x 5 x 5
        x = self.conv0(x)
        # N x 128 x 5 x 5
        x = self.conv1(x)
        # N x 768 x 1 x 1
        # Adaptive average pooling
        x = F.adaptive_avg_pool3d(x, (1, 1, 1))
        # N x 768 x 1 x 1
        x = torch.flatten(x, 1)
        # N x 768
        x = self.fc(x)
        # N x 1000
        return x


class BasicConv3d(nn.Module):

    def __init__(self, in_channels, out_channels, **kwargs):
        super(BasicConv3d, self).__init__()
        self.conv = nn.Conv3d(in_channels, out_channels, bias=False, **kwargs)
        self.bn = nn.BatchNorm3d(out_channels, eps=0.001)

    def forward(self, x):
        x = self.conv(x)
        x = self.bn(x)
        return F.relu(x, inplace=True)

class BasicConv3d_nopad(nn.Module):

    def __init__(self, in_channels, out_channels, **kwargs):
        super(BasicConv3d_nopad, self).__init__()
        self.conv = nn.Conv3d(in_channels, out_channels, bias=False, padding=0,**kwargs)
        self.bn = nn.BatchNorm3d(out_channels, eps=0.001)

    def forward(self, x):
        x = self.conv(x)
        x = self.bn(x)
        return F.relu(x, inplace=True)