神经网络，python报错：AttributeError: 'DataFrame' object has no attribute 'ravel'

Posted 2023-03-28

利用已有的库，写的一段神经网络的代码：
import pandas as pd
from sklearn.neural_network import MLPClassifier
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split

X=pd.read_csv('a_data.csv',usecols=(0,1,2,3,4,5,6,7,8,))
y=pd.read_csv('a_data.csv',usecols=(9,),dtype=str)

X_train,X_test,y_train,y_test=train_test_split(X,y)
scaler=StandardScaler()
scaler.fit(X_train)
StandardScaler(copy=True,with_mean=True,with_std=True)
X_train=scaler.transform(X_train)
X_test=scaler.transform(X_test)

mlp=MLPClassifier(hidden_layer_sizes=(11),activation="logistic",solver='adam',alpha=0.0001,
batch_size='auto',learning_rate='constant',learning_rate_init=0.1,
power_t=0.5,max_iter=1000,shuffle=True,random_state=None,tol=0.001,
verbose=False,warm_start=False,momentum=0.9,nesterovs_momentum=True,
early_stopping=False,validation_fraction=0.1,beta_1=0.9,beta_2=0.999,
epsilon=1e-08)
mlp.fit(X_train,y_train.ravel())
predictions = mlp.predict(X_test)

注：原先在mlp.fit(X_train,y_train.ravel())中我没有添加.ravel()，但是python提示： DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
y = column_or_1d(y, warn=True)。添加ravel之后便出现如上问题。求高手帮忙看看。

参考技术A y_train.values.ravel()
这样试试，因为你的y不是一维向量。
我建议你先看看数据追问

这是我的部分数据的截图，因为是神经网络，由9个输入产生1个输出，前面9列是输入，最后1列是输出。根据这些数据，能帮我看看我的代码有哪些问题吗？

注：我刚才照你说的，改为y_train.values.ravel()，运行后无报错，但是提示“Process finished with exit code 0。这是什么问题？

追答

你y的datatype 为什么是str 你试试 a
Process finished with exit code 0 是程序正常运行并完成

追问

datatype是str的原因我也不清楚，不过改了y_train.values.ravel()，刚刚再试了，出结果了！谢谢啦！

本回答被提问者和网友采纳

Python：（人工智能识别手写数字）使用卷积神经网络代码多个报错及相应解决方法

整个卷积神经网络代码（入门：识别手写数字）如下：

import torch
import torch.nn as nn
from torch.autograd import Variable
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt

EPOCH = 1
BATCH_SIZE = 50
LR = 0.001
DOWNLOAD_MNIST = False

train_data = torchvision.datasets.MNIST(
    root='./mnist',
    train=True,
    transform=torchvision.transforms.ToTensor(),
    download=DOWNLOAD_MNIST
)

# print(train_data.train_data.size())
# print(train_data.train_labels.size())
# plt.imshow(train_data.train_data[0].numpy(),cmap='gray')
# plt.title('%i' % train_data.train_labels[0])
# plt.show()

train_loader = Data.DataLoader(dataset=train_data,batch_size=BATCH_SIZE,shuffle=True,num_workers=2)

test_data = torchvision.datasets.MNIST(root='./mnist',train=False)
test_x = Variable(torch.unsqueeze(test_data.test_data,dim=1),volatile=True).type(torch.FloatTensor)[:2000]/255.
test_y = test_data.test_labels[:2000]

class CNN(nn.Module):
    def __init__(self):
        super(CNN,self).__init__()
        self.conv1 = nn.Sequential(
            nn.Conv2d(
                in_channels=1,
                out_channels=16,
                kernel_size=5,
                stride=1,
                padding=2, # (5-1)/2
            ),
            nn.ReLU,
            nn.MaxPool2d(kernel_size=2),
        )
        self.conv2 = nn.Sequential(
            nn.Conv2d(16,32,5,1,2),
            nn.ReLU,
            nn.MaxPool2d(2)
        )
        self.out = nn.Linear(32*7*7,10)

    def forward(self,x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(x.size(0),-1)
        output = self.out(x)
        return output
cnn = CNN()
# for(b_x,b_y) in train_loader:
optimizer = torch.optim.Adam(cnn.parameters(),lr=LR)
loss_func = nn.CrossEntropyLoss()

for epoch in range(EPOCH):
    for step,(x,y) in enumerate(train_loader):
        b_x = Variable(x)
        b_y = Variable(y)

        output = cnn(b_x)
        loss = loss_func(output,b_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if step % 50 == 0:
            test_output = cnn(test_x)
            pred_y = torch.max(test_output,1)[1].data.squeeze()
            accuracy = sum(pred_y == test_y) / test_y.size(0)
            print('Epoch:',epoch,'| train loss: %.4f' % loss.data[0],'| test accuracy: %.2f' % accuracy)

test_output = cnn(test_x[:10])
pred_y = torch.max(test_output,1)[1].data.numpy().squeeze()
print(pred_y,'prediction number')
print(test_y[:10].numpy(),'real number')

第一次使用的时候记得将DOWNLOAD_MNIST改成True。

第一个报错：

TypeError: torch.nn.modules.activation.ReLU is not a Module subclass

解决方法：应当将代码中nn.ReLU改为nn.ReLU()。

第二个报错：

RuntimeError: DataLoader worker (pid(s) 8772, 8773) exited unexpectedly

解决方法：将 train_loader = Data.DataLoader(dataset=train_data,batch_size=BATCH_SIZE,shuffle=True,num_workers=2) 中的num_workers=2改为0。

第三个报错：

IndexError: invalid index of a 0-dim tensor. Use tensor.item() in Python or tensor.item<T>() in C++ to convert a 0-dim tensor to a number

解决方法：将 print(‘Epoch:’,epoch,’| train loss: %.4f’ % loss.data[0],’| test accuracy: %.2f’ % accuracy) 中的loss.data[0]改为：loss.item() 。

修改后的代码：

import torch
import torch.nn as nn
from torch.autograd import Variable
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt

EPOCH = 1
BATCH_SIZE = 50
LR = 0.001
DOWNLOAD_MNIST = False

train_data = torchvision.datasets.MNIST(
    root='./mnist',
    train=True,
    transform=torchvision.transforms.ToTensor(),
    download=DOWNLOAD_MNIST
)

# print(train_data.train_data.size())
# print(train_data.train_labels.size())
# plt.imshow(train_data.train_data[0].numpy(),cmap='gray')
# plt.title('%i' % train_data.train_labels[0])
# plt.show()

train_loader = Data.DataLoader(dataset=train_data,batch_size=BATCH_SIZE,shuffle=True,num_workers=0)

test_data = torchvision.datasets.MNIST(root='./mnist',train=False)
test_x = Variable(torch.unsqueeze(test_data.test_data,dim=1),volatile=True).type(torch.FloatTensor)[:2000]/255.
test_y = test_data.test_labels[:2000]

class CNN(nn.Module):
    def __init__(self):
        super(CNN,self).__init__()
        self.conv1 = nn.Sequential(
            nn.Conv2d(
                in_channels=1,
                out_channels=16,
                kernel_size=5,
                stride=1,
                padding=2, # (5-1)/2
            ),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2),
        )
        self.conv2 = nn.Sequential(
            nn.Conv2d(16,32,5,1,2),
            nn.ReLU(),
            nn.MaxPool2d(2)
        )
        self.out = nn.Linear(32*7*7,10)

    def forward(self,x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(x.size(0),-1)
        output = self.out(x)
        return output
cnn = CNN()
# for(b_x,b_y) in train_loader:
optimizer = torch.optim.Adam(cnn.parameters(),lr=LR)
loss_func = nn.CrossEntropyLoss()

for epoch in range(EPOCH):
    for step,(x,y) in enumerate(train_loader):
        b_x = Variable(x)
        b_y = Variable(y)

        output = cnn(b_x)
        loss = loss_func(output,b_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if step % 50 == 0:
            test_output = cnn(test_x)
            pred_y = torch.max(test_output,1)[1].data.squeeze()
            accuracy = sum(pred_y == test_y) / test_y.size(0)
            print('Epoch:',epoch,'| train loss: %.4f' % loss.item(),'| test accuracy: %.2f' % accuracy)

test_output = cnn(test_x[:10])
pred_y = torch.max(test_output,1)[1].data.numpy().squeeze()
print(pred_y,'prediction number')
print(test_y[:10].numpy(),'real number')