Question

问题定义：

我必须使用MSELoss函数来定义分类损失问题。因此，它总是说关于张量形状的错误消息。

整个错误消息：

torch.Size（[32，10]）torch.Size（[32]） -------------------------------------------------- ------------------------- RuntimeError Traceback（最近一次调用最后） 53输出= model.forward（图片） 54个print（output.shape，labels.shape） ---> 55损失=准则（输出，标签） 56 loss.backward（） 57 Optimizer.step（）

/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py在通话（（自己，*输入，** kwargs） 530 result = self._slow_forward（* input，** kwargs）其他531 -> 532结果= self.forward（* input，** kwargs） 533 for self._forward_hooks.values（）的钩子： 534 hook_result = hook（自己，输入，结果）

/opt/conda/lib/python3.7/site-packages/torch/nn/modules/loss.py在前进（自己，输入，目标） 429 430 def转发（自身，输入，目标）： -> 431 return F.mse_loss（input，target，reduction = self.reduction） 432 433

/opt/conda/lib/python3.7/site-packages/torch/nn/functional.py在 mse_loss（输入，目标，size_average，减少，减少）2213
ret = torch.mean（ret），如果缩减=='mean'则为torch.sum（ret）
2214其他： -> 2215 expand_input，expand_target =火炬。广播_张量（input，target）2216 ret = 火炬_C._nn.mse_loss（扩展输入，扩展目标， _Reduction.get_enum（reduction））2217返回ret

/opt/conda/lib/python3.7/site-packages/torch/functional.py在 broadcast_tensors（*张量） 50 [0，1，2]]） 51“”“ ---> 52返回割炬._C._VariableFunctions.broadcast_tensors（张量） 53 54

> RuntimeError：张量a（10）的大小必须与张量的大小匹配 b（32）在非单维度1

如何重整张量，应该改变哪个张量（输出或标签）以计算损失？

完整代码附在下面。

import numpy as np
import torch

# Loading the Fashion-MNIST dataset
from torchvision import datasets, transforms

# Get GPU Device
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

transform = transforms.Compose([transforms.ToTensor(),
                                    transforms.Normalize((0.5,), (0.5,))])
# Download and load the training data
trainset = datasets.FashionMNIST('MNIST_data/', download = True, train = True, transform = transform)
testset = datasets.FashionMNIST('MNIST_data/', download = True, train = False, transform = transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size = 32, shuffle = True, num_workers=4)
testloader = torch.utils.data.DataLoader(testset, batch_size = 32, shuffle = True, num_workers=4)

# Examine a sample
dataiter = iter(trainloader)
images, labels = dataiter.next()

# Define the network architecture
from torch import nn, optim
import torch.nn.functional as F

model = nn.Sequential(nn.Linear(784, 128),
                      nn.ReLU(),
                      nn.Linear(128, 10),
                      nn.LogSoftmax(dim = 1))
model.to(device)

# Define the loss
criterion = nn.MSELoss()

# Define the optimizer
optimizer = optim.Adam(model.parameters(), lr = 0.001)

# Define the epochs
epochs = 5

train_losses, test_losses = [], []

for e in range(epochs):
  running_loss = 0
  for images, labels in trainloader:
    # Flatten Fashion-MNIST images into a 784 long vector
    images = images.to(device)
    labels = labels.to(device)
    images = images.view(images.shape[0], -1)

    # Training pass
    optimizer.zero_grad()
    output = model.forward(images)
    print(output.shape, labels.shape)
    loss = criterion(output, labels)
    loss.backward()
    optimizer.step()

    running_loss += loss.item()
  else:
    test_loss = 0
    accuracy = 0

    # Turn off gradients for validation, saves memory and computation
    with torch.no_grad():
      # Set the model to evaluation mode
      model.eval()

      # Validation pass
      for images, labels in testloader:
        images = images.to(device)
        labels = labels.to(device)
        images = images.view(images.shape[0], -1)
        ps = model(images)
        test_loss += criterion(ps, labels)
        top_p, top_class = ps.topk(1, dim = 1)
        equals = top_class == labels.view(*top_class.shape)
        accuracy += torch.mean(equals.type(torch.FloatTensor))

    model.train()

    print("Epoch: {}/{}..".format(e+1, epochs),
          "Training loss: {:.3f}..".format(running_loss/len(trainloader)),
          "Test loss: {:.3f}..".format(test_loss/len(testloader)),
          "Test Accuracy: {:.3f}".format(accuracy/len(testloader)))

Answer 1

从错误之前打印的输出torch.Size([32, 10]) torch.Size([32])。

左边是模型给你的，右边是来自trainloader的东西，通常您将其用于nn.CrossEntropyLoss之类的东西。

从完整的错误日志来看，该错误来自此行

loss = criterion(output, labels)

完成这项工作的方法称为“一站式编码”，如果是我出于懒惰，我会这样写。

ones = torch.sparse.torch.eye(10).to(device)  # number of class class
labels = ones.index_select(0, labels)

（pytorch / mse）如何更改张量的形状？

1 个答案: