深度学习==RNN循环神经网络手写数字识别

一个java开发

于 2024-09-22 21:11:48 发布

阅读量239

点赞数 1

分类专栏：大模型文章标签：深度学习 rnn 人工智能

本文链接：https://blog.youkuaiyun.com/hebian1994/article/details/142443946

版权

训练

import torch
from torch import nn, optim
import torch.nn.functional as F

# 检查是否有GPU可用
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")


# 定义 RNN 模型
class RNNModel(nn.Module):
    def __init__(self, input_size, hidden_size, output_size, num_layers=1):
        super(RNNModel, self).__init__()
        self.rnn = nn.RNN(input_size, hidden_size, num_layers, batch_first=True)
        self.fc = nn.Linear(hidden_size, output_size)

    def forward(self, x):
        out, _ = self.rnn(x)
        out = out[:, -1, :]  # 取最后一个时间步的输出
        out = self.fc(out)
        return F.log_softmax(out, dim=1)


# 模型参数
input_size = 28  # 假设输入为28维，例如MNIST的每行像素
hidden_size = 128
output_size = 10  # 例如10个分类
num_layers = 1
learning_rate = 0.001
epochs = 5

# 创建模型
model = RNNModel(input_size, hidden_size, output_size, num_layers).to(device)
optimizer = optim.Adam(mode