欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

pytorch LSTM

程序员文章站 2024-03-24 23:10:10
...
import torch
import torch.nn as nn
import torchvision.datasets as dsets
import torchvision.transforms as transforms
import matplotlib.pyplot as plt

# 超参数设置
EPOCH = 1        # 训练批次
BATCH_SIZE = 64  # 批次,N
TIME_STEP = 28   #
INPUT_SIZE = 128
LR = 0.01
DOWNLOAD_MNIST = False


# 下载数据集
train_data = dsets.MNIST(root='./mnist/', train=True, transform=transforms.ToTensor(), download=DOWNLOAD_MNIST)


# 设置dataloader
train_loader = torch.utils.data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)

# 转化成为样本数据
test_data = dsets.MNIST(root='./mnist/', train=False, transform=transforms.ToTensor())
test_x = test_data.test_data.type(torch.FloatTensor)[:2000] / 255.
test_y = test_data.test_labels.numpy()[:2000]


# 定义循环神经网络
class RNN(nn.Module):
    def __init__(self):
        super(RNN, self).__init__()

        self.input = nn.Linear(28,128)
        self.rnn = nn.LSTM(
            input_size=INPUT_SIZE,
            hidden_size=64,
            num_layers=2,
            # batch_first=False  # (time_step,batch,input)
            batch_first = True   # (batch,time_step,input)
        )
        self.out = nn.Linear(64, 10)

    def forward(self, x):
        x = x.view(-1,28)      # NHWC -> (N*H,W*C)
        x = self.input(x)
        x = x.view(-1,28,128)  # (N*H,W*C) -> (N,time_step,input)
        r_out, (h_n, h_c) = self.rnn(x, None)
        out = self.out(r_out[:, -1, :])
        return out


rnn = RNN()
print(rnn)

optimizer = torch.optim.Adam(rnn.parameters(), lr=LR)  # optimize all cnn parameters
loss_func = nn.CrossEntropyLoss()

# 训练网络
for epoch in range(EPOCH):
    for step, (b_x, b_y) in enumerate(train_loader):
        b_x = b_x.permute(0, 2, 3, 1)  # NCHW -> NHWC

        output = rnn(b_x)
        loss = loss_func(output, b_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
相关标签: pytorch