pytorch: "multi-target not supported" error message

Question

So I want to classify some (3, 50, 50) pictures. First I loaded the dataset from the file without a dataloader or batches, it worked. Now, after adding both things I get that error:

RuntimeError: multi-target not supported at /pytorch/aten/src/THCUNN/generic/ClassNLLCriterion.cu:15

I found a lot of answers in the internet, mostly to use target.squeeze(1) but it doesn´t work for me. My target-batch looks like following:

tensor([[1, 0],
        [1, 0],
        [1, 0],
        [1, 0],
        [1, 0],
        [1, 0],
        [1, 0],
        [1, 0]], device='cuda:0')

Shouldn't that be okay?

Here the full code (notice that Im only creating the structure of the model on which Im going to apply the full and correct dataset afterwards, because I dont have the full data yet, only 32 pictures and no labels, thats why I added torch.tensor([1, 0]) as a placeholder for all labels):

import torch
import torch.utils.data
import torch.nn as nn
import torch.nn.functional as F
import torch.optim
from torch.autograd import Variable

import numpy as np
from PIL import Image


class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()

        # model structur:
        self.conv1 = nn.Conv2d(3, 10, kernel_size=(5,5),  stride=(1,1))
        self.conv2 = nn.Conv2d(10, 20, kernel_size=(5,5),  stride=(1,1))            # with mapool: output = 20 * (9,9) feature-maps -> flatten
        self.fc1 = nn.Linear(20*9*9, 250)
        self.fc2 = nn.Linear(250, 100)
        self.fc3 = nn.Linear(100, 2)

    def forward(self, x):
        # conv layers
        x = F.relu(self.conv1(x))   # shape: 1, 10, 46, 46
        x = F.max_pool2d(x, 2, 2)   # shape: 1, 10, 23, 23
        x = F.relu(self.conv2(x))   # shape: 1, 20, 19, 19
        x = F.max_pool2d(x, 2, 2)   # shape: 1, 20, 9, 9

        # flatten to dense layer:
        x = x.view(-1, 20*9*9)

        # dense layers
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        output = F.log_softmax(self.fc3(x), dim=1)
        return output


class Run:
    def __init__(self, epochs, learning_rate, dropout, momentum):
        # load model
        self.model = Model().cuda()

        # hyperparameters:
        self.epochs = epochs
        self.learning_rate = learning_rate
        self.dropout = dropout

    def preporcessing(self):
        dataset_folder = "/media/theodor/hdd/Programming/BWKI/dataset/bilder/"

        dataset = []
        for i in range(0, 35): 
            sample_image = Image.open(dataset_folder + str(i) + ".png")
            data = torch.from_numpy(np.array(sample_image)).type("torch.Tensor").reshape(3, 50, 50)
            target = torch.tensor([[1, 0]])
            sample = (data, target)
            dataset.append(sample)

        train_loader = torch.utils.data.DataLoader(dataset, batch_size=8)

        return train_loader

    def train(self):
        train_set = self.preporcessing()

        criterion = nn.CrossEntropyLoss()
        optimizer = torch.optim.SGD(self.model.parameters(), lr=self.learning_rate) 
        for epoch in range(self.epochs):
            epoch_loss = 0
            for i, data in enumerate(train_set, 0):

                sample, target = data
                # set data as cuda varibale
                sample = Variable(sample.float().cuda())
                target = Variable(target.cuda())
                # initialize optimizer
                optimizer.zero_grad()
                # predict
                output = self.model(sample)
                # backpropagation
                print(output, target.squeeze(1))
                loss = criterion(output, target.squeeze(1))    # ERROR MESSAGE: RuntimeError: multi-target not supported at /pytorch/aten/src/THCUNN/generic/ClassNLLCriterion.cu:15
                loss.backward()
                optimizer.step()
            
                epoch_loss += loss.item()

            print("loss after epoch [", epoch, "|", self.epochs, "] :", epoch_loss)


run = Run(10, 0.001, 0.5, 0.9)
run.train()

So I expected it to start training (of course not learning anything because the labels are wrong).

Answer 1

For nn.CrossEntropyLoss the target has to be a single number from the interval [0, #classes] instead of a one-hot encoded target vector. Your target is [1, 0], thus PyTorch thinks you want to have multiple labels per input which is not supported.

Replace your one-hot-encoded targets:

[1, 0] --> 0

[0, 1] --> 1