pytorch 复现 FCN模型代码

作者简介：大家好，自我介绍： 人工智能硕博在读、精通python、某大厂nlp算法经历、机器学习、深度学习、自然语言处理、计算机视觉

个人主页：数学是算法的灵魂

觉得uu写的不错的话 麻烦动动小手 点赞 收藏⭐  评论

今天给大家带来的刷题系列是：pytorch 复现 FCN模型详细代码教程 

直奔主题模型图：

环境配置

pycharm python3.8 pytorch1.8 

pip配库模板

pip install tensorflow==2.2.0 -i https://pypi.tuna.tsinghua.edu.cn/simple --trusted-host pypi.tuna.tsinghua.edu.cn
**加粗样式**
pip install --user jupyterlab -i https://pypi.tuna.tsinghua.edu.cn/simple

导包：

import cv2
import numpy as np
import matplotlib.pyplot as plt
from PIL import Image

import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch.utils.data import Dataset, DataLoader, random_split
from torchvision import transforms
from torchvision import models

from tqdm import tqdm
import warnings

模型代码：

class FCN(nn.Module):
    def __init__(self,):
        super(FCN, self).__init__()
        self.stage1 = nn.Sequential(
            nn.Conv2d(in_channels=2, out_channels=128, kernel_size=(8,8), padding=1),
            nn.ReLU(),
            nn.BatchNorm2d(num_features=96),#
            # nn.MaxPool2d(kernel_size=2, padding=0)
        )
        self.stage2 = nn.Sequential(
            nn.Conv2d(in_channels=128, out_channels=256, kernel_size=(5,5), padding=1),
            nn.ReLU(),
            nn.BatchNorm2d(num_features=256),
            # nn.MaxPool2d(kernel_size=2, padding=0)
        )

        self.stage3 = nn.Sequential(
            nn.Conv2d(in_channels=256, out_channels=128, kernel_size=(3,3), padding=1),
            nn.ReLU(),
            nn.BatchNorm2d(num_features=128),
            #
            # nn.Conv2d(in_channels=384, out_channels=384, kernel_size=3, padding=1),
            # nn.ReLU(),
            # nn.BatchNorm2d(num_features=384),
            #
            # nn.Conv2d(in_channels=384, out_channels=256, kernel_size=3, padding=1),
            # nn.ReLU(),
            # nn.BatchNorm2d(num_features=256),
            #
            # nn.MaxPool2d(kernel_size=2, padding=0)
        )

        self.stage4 = nn.Sequential(
            nn.AvgPool2d(kernel_size=2, padding=0),
            nn.Softmax()
        )

    def forward(self, x):
        x = x.float()
        # conv1->pool1->输出
        x = self.stage1(x)
        # conv2->pool2->输出
        x = self.stage2(x)
        # conv3->pool3->输出输出, 经过上采样后, 需要用pool3暂存
        x = self.stage3(x)
        pool3 = x
        # conv4->pool4->输出输出, 经过上采样后, 需要用pool4暂存
        output = self.stage4(x)
        return output
model=FCN()
print(model)

结果打印：