如何在pytorch基本示例中包含批量大小? [英] How to include batch size in pytorch basic example?

问题描述

我是 pytorch 的新手.以下是使用 nn 模块训练带有一些随机数据的简单单层模型的基本示例(从这里)

I am new to pytorch. The following is the basic example of using nn module to train a simple one-layer model with some random data (from here)

import torch
N, D_in, H, D_out = 64, 1000, 100, 10

x = torch.randn(N, D_in)
y = torch.randn(N, D_out)

model = torch.nn.Sequential(
    torch.nn.Linear(D_in, H),
    torch.nn.ReLU(),
    torch.nn.Linear(H, D_out),
)
loss_fn = torch.nn.MSELoss(reduction='sum')
optimizer = torch.optim.Adam(model.parameters(), lr=1e-4)
for t in range(500):
    y_pred = model(x)

    loss = loss_fn(y_pred, y)
    print(t, loss.item())

    optimizer.zero_grad()
    loss.backward()
    optimizer.step()

据我所知，示例中的batch size等于1，换句话说，使用单个点(64个)来计算梯度和更新参数.我的问题是:如何修改此示例以训练批量大小大于 1 的模型?

As far as I understand, the batch size is equal to 1 in the example, in other words, a single point (out of 64) is used to calculate gradients and update parameters. My question is: how to modify this example to train the model with the batch size greater than one?

推荐答案

实际上 N 是批大小.所以你只需要修改 N 当前它的设置为 64.所以你在每个训练批次中都有 64 个大小为/dim D_in 的向量.

In fact N is the batch size. So you just need to modify N currently its set to 64. So you have in every training batch 64 vectors with size / dim D_in.

我查看了你发布的链接，你也可以看看评论——也有一些解释:)

I checked the link you posted, you can also take a look at the comments - there is some explanation too :)

# -*- coding: utf-8 -*-
import numpy as np

# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10

# Create random input and output data
x = np.random.randn(N, D_in)
y = np.random.randn(N, D_out)

# Randomly initialize weights
w1 = np.random.randn(D_in, H)
w2 = np.random.randn(H, D_out)

learning_rate = 1e-6
for t in range(500):
    # Forward pass: compute predicted y
    h = x.dot(w1)
    h_relu = np.maximum(h, 0)
    y_pred = h_relu.dot(w2)

    # Compute and print loss
    loss = np.square(y_pred - y).sum()
    print(t, loss)

    # Backprop to compute gradients of w1 and w2 with respect to loss
    grad_y_pred = 2.0 * (y_pred - y)
    grad_w2 = h_relu.T.dot(grad_y_pred)
    grad_h_relu = grad_y_pred.dot(w2.T)
    grad_h = grad_h_relu.copy()
    grad_h[h < 0] = 0
    grad_w1 = x.T.dot(grad_h)

    # Update weights
    w1 -= learning_rate * grad_w1
    w2 -= learning_rate * grad_w2

这篇关于如何在pytorch基本示例中包含批量大小?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！