学习记录 —— pytorch example for MNIST

PyTorch实现MNIST：理解Conv2d与网络训练

最新推荐文章于 2024-07-09 17:32:19 发布

原创

最新推荐文章于 2024-07-09 17:32:19 发布 · 756 阅读

2 ·

CC 4.0 BY-SA版权

这篇博客记录了使用PyTorch实现MNIST数据集的示例，详细解释了nn.Conv2d的参数，强调了在训练和测试模型时切换model的train/eval模式的重要性，并指出在PyTorch中无需手动定义反向传播，forward函数即可自动处理。博主还讨论了MNIST数据集为何几乎线性可分，并用超平面的概念进行了简单说明。

代码来自：mnist

from __future__ import print_function
import argparse
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets,transforms

class Net(nn.Module):
    def __init__(self):
        super(Net,self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv2_drop = nn.Dropout2d()
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10)

    def forward(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        x = x.view(-1, 320)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training=self.training)
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)<