pytorch实现卷积神经网络(MNIST,99%准确率)

「已注销」

已于 2022-10-02 23:30:00 修改

阅读量1.4k

点赞数 2

于 2022-10-02 23:27:16 首次发布

本文链接：https://blog.youkuaiyun.com/m0_73817310/article/details/127147664

版权

本文介绍了如何使用PyTorch构建卷积神经网络（CNN），以99%的准确率识别MNIST手写数字数据集。内容包括数据加载、GPU计算以及卷积层的作用和LeNet网络结构的讨论。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

导入相关的库

import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor

导入数据

training_data = datasets.MNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor(),
)


test_data = datasets.MNIST(
    root="data",
    train=False,
    download=True,
    transform=ToTensor(),
)

We pass the as an argument to . This wraps an iterable over our dataset, and supports automatic batching, sampling, shuffling and multiprocess data loading. Here we define a batch size of 256, i.e. each element in the dataloader iterable will return a batch of 64 features and labels.

batch_size = 256

# Create data loaders.
train_dataloader = DataLoader(training_data, batch_size=batch_size)
test_dataloader = DataLoader(test_data, batch_size=batch_size)

for X, y in test_dataloader:
    print(f"Shape of X [N, C, H, W]: {X.shape}")
    print(f"Shape of y: {y.shape} {y.dtype}")
    break

Shape of X [N, C, H, W]: torch.Size([256, 1, 28, 28])
Shape of y: torch.Size([256]) torch.int64

使用GPU计算

device &

最低0.47元/天解锁文章