RuntimeError: expected scalar type Float but found Long neural network

Question

我知道有一些问题与此问题类似，但当我按照它们进行操作时，似乎让我陷入了困境。好像我刚刚解决的问题导致了另一个问题。

这是我保留的 2 个兔子洞解决方案，因为它们似乎解决了他们的问题。我怀疑他们会有什么帮助，但在这里他们只是为了以防万一。

一个：

batch_X = batch_X.to(device=device, dtype=torch.int64)
batch_y = batch_y.to(device=device, dtype=torch.int64)

两个：

 x = x.view(x.size(0), -1)

这是我遇到的错误。

Traceback (most recent call last):
  File "c:/Users/14055/Desktop/Research/new 1.0.py", line 93, in <module>
    training()
  File "c:/Users/14055/Desktop/Research/new 1.0.py", line 63, in training
    output = model(batch_X)                              # passed input data here!!!!!!!!!!!!!!!!!!!!!!!!!!
  File "C:\Users055\AppData\Local\Programs\Python\Python36\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl
    return forward_call(*input, **kwargs)
  File "c:/Users/14055/Desktop/Research/new 1.0.py", line 31, in forward
    x = F.relu(self.fc1(x))
  File "C:\Users055\AppData\Local\Programs\Python\Python36\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl
    return forward_call(*input, **kwargs)
  File "C:\Users055\AppData\Local\Programs\Python\Python36\lib\site-packages\torch\nn\modules\linear.py", line 96, in forward
    return F.linear(input, self.weight, self.bias)
  File "C:\Users055\AppData\Local\Programs\Python\Python36\lib\site-packages\torch\nn\functional.py", line 1847, in linear
    return torch._C._nn.linear(input, weight, bias)
RuntimeError: expected scalar type Float but found Long

我的代码如下

import torch.cuda
import torch
import numpy as np
import sys
import torch.nn as nn
import torch.nn.functional as F
from torchsummary import summary
#-------------------------------------------------------------------------
torch.cuda.set_device(0)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
np.set_printoptions(threshold=sys.maxsize) 
#-------------------------------------------------------------------------

input_data = torch.Tensor(np.load("inputData.npy", allow_pickle=True))
predict_data = torch.Tensor(np.load("predict.npy", allow_pickle=True))

input_data = input_data.type(torch.FloatTensor)
predict_data = predict_data.type(torch.FloatTensor)


print(type(input_data))

class NeuralNet(nn.Module):
    def __init__(self, gpu = True):
        super(NeuralNet, self ).__init__()
        self.fc1 = nn.Linear(248, 750).to(device)
        self.fc2 = nn.Linear(750, 10).to(device)

    def forward(self, x):
        x = x.view(x.size(0), -1)
        x = F.relu(self.fc1(x))
        x = self.fc2(x).to(device)
        return x.to(device)

def training():
    model.to(device)
    training.criterion = nn.CrossEntropyLoss() 
    optimizer= torch.optim.SGD(model.parameters(), lr=0.003, weight_decay= 0.00005, momentum = .9, nesterov = True)   
    n_epochs = 20000  
    a = np.float64([9,9,9,9,9]) #antioverfit   
    testing_loss = 0.0

    BATCH_SIZE = 10
    EPOCHS = 3
    for epoch in range(EPOCHS):


        if(testing_loss <= a[4]): # part of anti overfit
            train_loss = 0.0        
            testing_loss = 0.0


            model.train()
            for i in (range(0, len(input_data), BATCH_SIZE)):
                batch_X = input_data[i:i+BATCH_SIZE]
                batch_y = predict_data[i:i+BATCH_SIZE]

                optimizer.zero_grad()

                batch_X = batch_X.to(device=device, dtype=torch.int64) #gpu                        # input data here!!!!!!!!!!!!!!!!!!!!!!!!!!
                batch_y = batch_y.to(device=device, dtype=torch.int64) #gpu                    # larget data here!!!!!!!!!!!!!!!!!!!!!!!!!!

                output = model(batch_X)                              # passed input data here!!!!!!!!!!!!!!!!!!!!!!!!!!
                loss = training.criterion(output, batch_y)           
                loss.backward()
                optimizer.step()
                train_loss += loss.item()*batch_X.size(0) 

            train_loss = train_loss/len(predict_data.train_loader.dataset)
            print('Epoch: {} \tTraining Loss: {:.6f}'.format(epoch+1, train_loss))


            model.eval()  # Gets Validation loss 
            train_loss = 0.0         
            with torch.no_grad():
                for i in (range(0, len(input_data), BATCH_SIZE)):
                    batch_X = input_data[i:i+BATCH_SIZE]
                    batch_y = predict_data[i:i+BATCH_SIZE] 

                    batch_X = batch_X.to(device=device, dtype=torch.int64)
                    batch_y = batch_y.to(device=device, dtype=torch.int64)
                    output = model(batch_X)
                    loss = training.criterion(output, batch_y).to(device=device, dtype=torch.int64)
                    testing_loss += loss.item()*batch_X.size(0)
            testing_loss = testing_loss / len(predict_data.test_loader.dataset)           
            print('Validation loss = ' , testing_loss)                      
            a = np.insert(a,0,testing_loss) # part of anti overfit         
            a = np.delete(a,5)           
    print('Validation loss = ' , testing_loss) 

model = NeuralNet().to(device=device)
#summary(model, input_size=(1, 248, 248))
training()

Answer 1

为什么要将 X 和 Y 投射到 int64？主要是这个问题。

batch_X = batch_X.to(device=device, dtype=torch.int64) #gpu                        # input data here!!!!!!!!!!!!!!!!!!!!!!!!!!
batch_y = batch_y.to(device=device, dtype=torch.int64) #gpu

您将 batch_X 和 batch_Y 转换为 int64 a.k.a long，但 float 是预期的，因此出现错误。将其替换为

batch_X = batch_X.to(device=device) 
batch_y = batch_y.to(device=device, dtype=torch.int64)

或

batch_X = batch_X.to(device=device, dtype=torch.float) 
batch_y = batch_y.to(device=device, dtype=torch.int64)

这应该可以解决您的问题。

编辑：您只需要将 y 保持为 int。由于您使用的是 CrossEntropyLoss，它需要目标标签（预计为 int 或 long）。总的来说，你需要保持x的数据类型为float，y应该是long或int。

RuntimeError: expected scalar type Float but found Long neural network

RuntimeError: expected scalar type Float but found Long neural network

python

pytorch