Enet-Model(pytorch版本)

$$Enet-Model(pytorch版本)$$

训练、验证代码逻辑

---

• cfg
• dataset
• evalution_segmentaion
• Test（指标计算）
• Predict（生成图像）

---

• Train

---

All.ipynb

---

import torch.nn as nn
from torchvision import models
import torch

class InitialBlock(nn.Module):
    def __init__(self,
                 in_channels,
                 out_channels,
                 bias=False,
                 relu=True):
        super().__init__()

        if relu:
            activation = nn.ReLU
        else:
            activation = nn.PReLU

        self.main_branch = nn.Conv2d(
            in_channels,
            out_channels - 3,
            kernel_size=3,
            stride=2,
            padding=1,
            bias=bias)

        # Extension branch
        self.ext_branch = nn.MaxPool2d(3, stride=2, padding=1)

        # Initialize batch normalization to be used after concatenation
        self.batch_norm = nn.BatchNorm2d(out_channels)

        # PReLU layer to apply after concatenating the branches
        self.out_activation = activation()

    def forward(self, x):
        main = self.main_branch(x)
        ext = self.ext_branch(x)

        # Concatenate branches
        out = torch.cat((main, ext), 1)

        # Apply batch normalization
        out = self.batch_norm(out)

        return self.out_activation(out)

class RegularBottleneck(nn.Module):
    def __init__(self,
                 channels,
                 internal_ratio=4,
                 kernel_size=3,
                 padding=0,
                 dilation=1,
                 asymmetric=False,
                 dropout_prob=0,
                 bias=False,
                 relu=True):
        super().__init__()

        internal_channels = channels // internal_ratio

        if relu:
            activation = nn.ReLU
        else:
            activation = nn.PReLU

        # 1x1 projection convolution
        self.ext_conv1 = nn.Sequential(
            nn.Conv2d(
                channels,
                internal_channels,
                kernel_size=1,
                stride=1,
                bias=bias), nn.BatchNorm2d(internal_channels), activation())

        if asymmetric:
            self.ext_conv2 = nn.Sequential(
                nn.Conv2d(
                    internal_channels,
                    internal_channels,
                    kernel_size=(kernel_size, 1),
                    stride=1,
                    padding=(padding, 0),
                    dilation=dilation,
                    bias=bias), nn.BatchNorm2d(internal_channels), activation(),
                nn.Conv2d(
                    internal_channels,
                    internal_channels,
                    kernel_size=(1, kernel_size),
                    stride=1,
                    padding=(0, padding),
                    dilation=dilation,
                    bias=bias), nn.BatchNorm2d(internal_channels), activation())
        else:
            self.ext_conv2 = nn.Sequential(
                nn.Conv2d(
                    internal_channels,
                    internal_channels,
                    kernel_size=kernel_size,
                    stride=1,
                    padding=padding,
                    dilation=dilation,
                    bias=bias), nn.BatchNorm2d(internal_channels), activation())

        # 1x1 expansion convolution
        self.ext_conv3 = nn.Sequential(
            nn.Conv2d(
                internal_channels,
                channels,
                kernel_size=1,
                stride=1,
                bias=bias), nn.BatchNorm2d(channels), activation())

        self.ext_regul = nn.Dropout2d(p=dropout_prob)

        # PReLU layer to apply after adding the branches
        self.out_activation = activation()

    def forward(self, x):
        # Main branch shortcut
        main = x

        # Extension branch
        ext = self.ext_conv1(x)
        ext = self.ext_conv2(ext)
        ext = self.ext_conv3(ext)
        ext = self.ext_regul(ext)

        # Add main and extension branches
        out = main + ext

        return self.out_activation(out)

class DownsamplingBottleneck(nn.Module):
    def __init__(self,
                 in_channels,
                 out_channels,
                 internal_ratio=4,
                 return_indices=False,
                 dropout_prob=0,
                 bias=False,
                 relu=True):
        super().__init__()

        # Store parameters that are needed later
        self.return_indices = return_indices

        internal_channels = in_channels // internal_ratio

        if relu:
            activation = nn.ReLU
        else:
            activation = nn.PReLU

        # Main branch - max pooling followed by feature map (channels) padding
        self.main_max1 = nn.MaxPool2d(
            2,
            stride=2,
            return_indices=return_indices)

        # 2x2 projection convolution with stride 2
        self.ext_conv1 = nn.Sequential(
            nn.Conv2d(
                in_channels,
                internal_channels,
                kernel_size=2,
                stride=2,
                bias=bias), nn.BatchNorm2d(internal_channels), activation())

        # Convolution
        self.ext_conv2 = nn.Sequential(
            nn.Conv2d(
                internal_channels,
                internal_channels,
                kernel_size=3,
                stride=1,
                padding=1,
                bias=bias), nn.BatchNorm2d(internal_channels), activation())

        # 1x1 expansion convolution
        self.ext_conv3 = nn.Sequential(
            nn.Conv2d(
                internal_channels,
                out_channels,
                kernel_size=1,
                stride=1,
                bias=bias), nn.BatchNorm2d(out_channels), activation())

        self.ext_regul = nn.Dropout2d(p=dropout_prob)

        # PReLU layer to apply after concatenating the branches
        self.out_activation = activation()

    def forward(self, x):
        # Main branch shortcut
        if self.return_indices:
            main, max_indices = self.main_max1(x)
        else:
            main = self.main_max1(x)

        # Extension branch
        ext = self.ext_conv1(x)
        ext = self.ext_conv2(ext)
        ext = self.ext_conv3(ext)
        ext = self.ext_regul(ext)

        # Main branch channel padding
        n, ch_ext, h, w = ext.size()
        ch_main = main.size()[1]
        padding = torch.zeros(n, ch_ext - ch_main, h, w)

        # Before concatenating, check if main is on the CPU or GPU and
        # convert padding accordingly
        if main.is_cuda:
            padding = padding.cuda()

        # Concatenate
        main = torch.cat((main, padding), 1)

        # Add main and extension branches
        out = main + ext

        return self.out_activation(out), max_indices

class UpsamplingBottleneck(nn.Module):
    
    def __init__(self,
                 in_channels,
                 out_channels,
                 internal_ratio=4,
                 dropout_prob=0,
                 bias=False,
                 relu=True):
        super().__init__()

        internal_channels = in_channels // internal_ratio

        if relu:
            activation = nn.ReLU
        else:
            activation = nn.PReLU

        # Main branch - max pooling followed by feature map (channels) padding
        self.main_conv1 = nn.Sequential(
            nn.Conv2d(in_channels, out_channels, kernel_size=1, bias=bias),
            nn.BatchNorm2d(out_channels))

        # Remember that the stride is the same as the kernel_size, just like
        # the max pooling layers
        self.main_unpool1 = nn.MaxUnpool2d(kernel_size=2)

        # 1x1 projection convolution with stride 1
        self.ext_conv1 = nn.Sequential(
            nn.Conv2d(
                in_channels, internal_channels, kernel_size=1, bias=bias),
            nn.BatchNorm2d(internal_channels), activation())

        # Transposed convolution
        self.ext_tconv1 = nn.ConvTranspose2d(
            internal_channels,
            internal_channels,
            kernel_size=2,
            stride=2,
            bias=bias)
        self.ext_tconv1_bnorm = nn.BatchNorm2d(internal_channels)
        self.ext_tconv1_activation = activation()

        # 1x1 expansion convolution
        self.ext_conv2 = nn.Sequential(
            nn.Conv2d(
                internal_channels, out_channels, kernel_size=1, bias=bias),
            nn.BatchNorm2d(out_channels), activation())

        self.ext_regul = nn.Dropout2d(p=dropout_prob)

        # PReLU layer to apply after concatenating the branches
        self.out_activation = activation()

    def forward(self, x, max_indices, output_size):
        # Main branch shortcut
        main = self.main_conv1(x)
        main = self.main_unpool1(
            main, max_indices, output_size=output_size)

        # Extension branch
        ext = self.ext_conv1(x)
        ext = self.ext_tconv1(ext, output_size=output_size)
        ext = self.ext_tconv1_bnorm(ext)
        ext = self.ext_tconv1_activation(ext)
        ext = self.ext_conv2(ext)
        ext = self.ext_regul(ext)

        # Add main and extension branches
        out = main + ext

        return self.out_activation(out)

class ENet(nn.Module):
    def __init__(self, n_classes, encoder_relu=False, decoder_relu=True):
        super().__init__()

        self.initial_block = InitialBlock(3, 16, relu=encoder_relu)

        # Stage 1 - Encoder
        self.downsample1_0 = DownsamplingBottleneck(
            16,
            64,
            return_indices=True,
            dropout_prob=0.01,
            relu=encoder_relu)
        self.regular1_1 = RegularBottleneck(
            64, padding=1, dropout_prob=0.01, relu=encoder_relu)
        self.regular1_2 = RegularBottleneck(
            64, padding=1, dropout_prob=0.01, relu=encoder_relu)
        self.regular1_3 = RegularBottleneck(
            64, padding=1, dropout_prob=0.01, relu=encoder_relu)
        self.regular1_4 = RegularBottleneck(
            64, padding=1, dropout_prob=0.01, relu=encoder_relu)

        # Stage 2 - Encoder
        self.downsample2_0 = DownsamplingBottleneck(
            64,
            128,
            return_indices=True,
            dropout_prob=0.1,
            relu=encoder_relu)
        self.regular2_1 = RegularBottleneck(
            128, padding=1, dropout_prob=0.1, relu=encoder_relu)
        self.dilated2_2 = RegularBottleneck(
            128, dilation=2, padding=2, dropout_prob=0.1, relu=encoder_relu)
        self.asymmetric2_3 = RegularBottleneck(
            128,
            kernel_size=5,
            padding=2,
            asymmetric=True,
            dropout_prob=0.1,
            relu=encoder_relu)
        self.dilated2_4 = RegularBottleneck(
            128, dilation=4, padding=4, dropout_prob=0.1, relu=encoder_relu)
        self.regular2_5 = RegularBottleneck(
            128, padding=1, dropout_prob=0.1, relu=encoder_relu)
        self.dilated2_6 = RegularBottleneck(
            128, dilation=8, padding=8, dropout_prob=0.1, relu=encoder_relu)
        self.asymmetric2_7 = RegularBottleneck(
            128,
            kernel_size=5,
            asymmetric=True,
            padding=2,
            dropout_prob=0.1,
            relu=encoder_relu)
        self.dilated2_8 = RegularBottleneck(
            128, dilation=16, padding=16, dropout_prob=0.1, relu=encoder_relu)

        # Stage 3 - Encoder
        self.regular3_0 = RegularBottleneck(
            128, padding=1, dropout_prob=0.1, relu=encoder_relu)
        self.dilated3_1 = RegularBottleneck(
            128, dilation=2, padding=2, dropout_prob=0.1, relu=encoder_relu)
        self.asymmetric3_2 = RegularBottleneck(
            128,
            kernel_size=5,
            padding=2,
            asymmetric=True,
            dropout_prob=0.1,
            relu=encoder_relu)
        self.dilated3_3 = RegularBottleneck(
            128, dilation=4, padding=4, dropout_prob=0.1, relu=encoder_relu)
        self.regular3_4 = RegularBottleneck(
            128, padding=1, dropout_prob=0.1, relu=encoder_relu)
        self.dilated3_5 = RegularBottleneck(
            128, dilation=8, padding=8, dropout_prob=0.1, relu=encoder_relu)
        self.asymmetric3_6 = RegularBottleneck(
            128,
            kernel_size=5,
            asymmetric=True,
            padding=2,
            dropout_prob=0.1,
            relu=encoder_relu)
        self.dilated3_7 = RegularBottleneck(
            128, dilation=16, padding=16, dropout_prob=0.1, relu=encoder_relu)

        # Stage 4 - Decoder
        self.upsample4_0 = UpsamplingBottleneck(
            128, 64, dropout_prob=0.1, relu=decoder_relu)
        self.regular4_1 = RegularBottleneck(
            64, padding=1, dropout_prob=0.1, relu=decoder_relu)
        self.regular4_2 = RegularBottleneck(
            64, padding=1, dropout_prob=0.1, relu=decoder_relu)

        # Stage 5 - Decoder
        self.upsample5_0 = UpsamplingBottleneck(
            64, 16, dropout_prob=0.1, relu=decoder_relu)
        self.regular5_1 = RegularBottleneck(
            16, padding=1, dropout_prob=0.1, relu=decoder_relu)
        self.transposed_conv = nn.ConvTranspose2d(
            16,
            n_classes,
            kernel_size=3,
            stride=2,
            padding=1,
            bias=False)

    def forward(self, x):
        # Initial block
        print('x:', x.size())
        input_size = x.size()
        x = self.initial_block(x);print('x:', x.size())

        # Stage 1 - Encoder
        stage1_input_size = x.size()
        x, max_indices1_0 = self.downsample1_0(x);print('x:', x.size());print('max_indices1_0:', max_indices1_0.size())
        x = self.regular1_1(x);print('x:', x.size())
        x = self.regular1_2(x);print('x:', x.size())
        x = self.regular1_3(x);print('x:', x.size())
        x = self.regular1_4(x);print('x:', x.size())

        # Stage 2 - Encoder
        stage2_input_size = x.size()
        x, max_indices2_0 = self.downsample2_0(x);print('x:', x.size());print('max_indices2_0:', max_indices2_0.size())
        x = self.regular2_1(x);print('x:', x.size())
        x = self.dilated2_2(x);print('x:', x.size())
        x = self.asymmetric2_3(x);print('x:', x.size())
        x = self.dilated2_4(x);print('x:', x.size())
        x = self.regular2_5(x);print('x:', x.size())
        x = self.dilated2_6(x);print('x:', x.size())
        x = self.asymmetric2_7(x);print('x:', x.size())
        x = self.dilated2_8(x);print('x:', x.size())

        # Stage 3 - Encoder
        x = self.regular3_0(x);print('x:', x.size())
        x = self.dilated3_1(x);print('x:', x.size())
        x = self.asymmetric3_2(x);print('x:', x.size())
        x = self.dilated3_3(x);print('x:', x.size())
        x = self.regular3_4(x);print('x:', x.size())
        x = self.dilated3_5(x);print('x:', x.size())
        x = self.asymmetric3_6(x);print('x:', x.size())
        x = self.dilated3_7(x);print('x:', x.size())

        # Stage 4 - Decoder
        x = self.upsample4_0(x, max_indices2_0, output_size=stage2_input_size);print('x:', x.size());
        x = self.regular4_1(x);print('x:', x.size())
        x = self.regular4_2(x);print('x:', x.size())

        # Stage 5 - Decoder
        x = self.upsample5_0(x, max_indices1_0, output_size=stage1_input_size);print('x:', x.size())
        x = self.regular5_1(x);print('x:', x.size())
        x = self.transposed_conv(x, output_size=input_size);print('x:', x.size())

        return x

# 随机生成输入数据
inputs = torch.randn((1, 3, 512, 512))
# 定义网络
model = ENet(n_classes=8)
# 前向传播
out = model(inputs)
# 打印输出大小
print('-----'*5)
print(out.size())
print('-----'*5)