3.12_ValueError: x and y must have same first dimension, but have shapes (100,) and (1,)

在练习3.12-权重衰减时，运行如下代码报错：

#定义和训练测试
batch_size,num_epochs,lr = 1,100,0.003
net,loss = d2l.linreg,d2l.squared_lossdataset = torch.utils.data.TensorDataset(train_features,train_labels)
train_iter = torch.utils.data.DataLoader(dataset,batch_size,shuffle=True)def fit_and_plot(lambd):w,b = init_params()train_ls,test_ls = [],[]for _ in range(num_epochs):for X,y in train_iter:#添加了L2范数惩罚项l = loss(net(X,w,b),y) + lambd * l2_penalty(w)l = l.sum()if w.grad is not None:w.grad.data.zero_()b.grad.data.zero_()l.backward()d2l.sgd([w,b],lr,batch_size)train_ls.append(loss(net(train_features,w,b),train_labels).mean().item())test_ls.append(loss(net(test_features,w,b),test_labels).mean().item())d2l.semilogy(range(1,num_epochs + 1),train_ls,'epochs','loss',range(1,num_epochs + 1),test_ls,['train','test'])print('L2 norm of w:',w.norm().item())#观察过拟合
fit_and_plot(lambd=0)

如图：

字面意思是“x和y必须具有相同的第一维度，但具有形状（100）和（1）”。报错时所指向的包是确认无误的，逐行对比输入代码和书里的代码内容也没有差异，最后发现是最后几行没有对齐所导致的

修改后：

        train_ls.append(loss(net(train_features,w,b),train_labels).mean().item())test_ls.append(loss(net(test_features,w,b),test_labels).mean().item())d2l.semilogy(range(1,num_epochs + 1),train_ls,'epochs','loss',range(1,num_epochs + 1),test_ls,['train','test'])print('L2 norm of w:',w.norm().item())

运行结果：

3.12_ValueError: x and y must have same first dimension, but have shapes (100,) and (1,)相关推荐

ValueError: x and y must have same first dimension, but have shapes (100,) and (0,)
成功解决运行YOLOX训练日志文件数据画图报错 ValueError: x and y must have same first dimension, but have shapes (100,) a ...
ValueError: x and y must have same first dimension, but have shapes (0,) and (951424,)
ValueError: x and y must have same first dimension, but have shapes (0,) and (951424,) 使用Python画图的时候 ...
【Python】ValueError: x and y must have same first dimension, but have shapes (5,) and (4,)
调用 matplotlib 作图的时候,输入的 x 和 y 的值数量不一致产生的.画图的 xy 的值必须在一个维度,就是 x 有几个数,y 就要有几个数.比如下面代码,我 x 输出 [2, 4, 6 ...
Python如何对数组求导（差分）？
文章目录 diff ediff1d diff diff是numpy中用于求差分的函数,函数定义为 diff(a, n=1, axis=-1, prepend=<no value>, app ...
python predict y和x是必须一致吗_数据科学python错误 - ValueError：x和y必须具有相同的第一维...
对于背景,我计算了一组sample_means,每个样本大小200次.然后,我计算每个样本大小的平均值和标准偏差,然后将其存储在数组中.这是我的代码: in[] = sample_sizes = np ...
基于Python的QPSK音频的波形和频谱
1.需求分析现有一个QPSK.wav的音频文件,要求使用Python读取该文件画出其波形和频谱. 2.代码实现 import wave import numpy as np import pyl ...
机器学习实战——Logistic回归
书籍:<机器学习实战>中文版 IDE:PyCharm Edu 4.02 环境:Adaconda3 python3.6 关键词:sigmoid函数.批梯度上升法.随机梯度上升法 from ...
NameError: name ‘weights‘ is not defined
Error display: NameError: name 'weights' is not defined Root Cause: missing code : # add this code w ...
Machine Learning in Action 读书笔记---第5章 Logistic回归
Machine Learning in Action 读书笔记第5章 Logistic回归文章目录 Machine Learning in Action 读书笔记一.Logistic回归 1.L ...
Python数据分析入门与实践-笔记
第1章实验环境的搭建本章将主要介绍Anaconda和Jupyter Notebook.包括如何在windows,Mac,linux等平台上安装Anaconda,以及Jupyter Notebook ...

3.12_ValueError: x and y must have same first dimension, but have shapes (100,) and (1,)

3.12_ValueError: x and y must have same first dimension, but have shapes (100,) and (1,)相关推荐

最新文章

热门文章