web-dev-qa-db-fra.com

RuntimeError: type scalaire attendu Long mais float trouvé

Je ne peux pas faire correspondre les dtypes, soit la perte veut long, soit le modèle veut float si je change mes tenseurs en long. La forme des tenseurs est 42000, 1, 28, 28 et 42000. Je ne sais pas où je peux changer les types de dtypes requis pour le modèle ou la perte.

Je ne suis pas sûr si dataloader est nécessaire, l'utilisation de Variable ne fonctionnait pas non plus.

dataloaders_train = torch.utils.data.DataLoader(Xt_train, batch_size=64)

dataloaders_test = torch.utils.data.DataLoader(Yt_train, batch_size=64)

class Network(nn.Module):
    def __init__(self):
        super().__init__()


        self.hidden = nn.Linear(42000, 256)

        self.output = nn.Linear(256, 10)


        self.sigmoid = nn.Sigmoid()
        self.softmax = nn.Softmax(dim=1)

    def forward(self, x):

        x = self.hidden(x)
        x = self.sigmoid(x)
        x = self.output(x)
        x = self.softmax(x)

        return x

model = Network()

input_size = 784
hidden_sizes = [28, 64]
output_size = 10 
model = nn.Sequential(nn.Linear(input_size, hidden_sizes[0]),
                      nn.ReLU(),
                      nn.Linear(hidden_sizes[0], hidden_sizes[1]),
                      nn.ReLU(),
                      nn.Linear(hidden_sizes[1], output_size),
                      nn.Softmax(dim=1))
print(model)

criterion = nn.NLLLoss()
optimizer = optim.SGD(model.parameters(), lr=0.003)

epochs = 5

for e in range(epochs):
    running_loss = 0
    for images, labels in Zip(dataloaders_train, dataloaders_test):

        images = images.view(images.shape[0], -1)
        #images, labels = Variable(images), Variable(labels)
        print(images.dtype)
        print(labels.dtype)

        optimizer.zero_grad()

        output = model(images)
        loss = criterion(output, labels)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
    else:
        print(f"Training loss: {running_loss}")

Qui donne

RuntimeError                              Traceback (most recent call last)
<ipython-input-128-68109c274f8f> in <module>
     11 
     12         output = model(images)
---> 13         loss = criterion(output, labels)
     14         loss.backward()
     15         optimizer.step()

/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs)
    530             result = self._slow_forward(*input, **kwargs)
    531         else:
--> 532             result = self.forward(*input, **kwargs)
    533         for hook in self._forward_hooks.values():
    534             hook_result = hook(self, input, result)

/opt/conda/lib/python3.6/site-packages/torch/nn/modules/loss.py in forward(self, input, target)
    202 
    203     def forward(self, input, target):
--> 204         return F.nll_loss(input, target, weight=self.weight, ignore_index=self.ignore_index, reduction=self.reduction)
    205 
    206 

/opt/conda/lib/python3.6/site-packages/torch/nn/functional.py in nll_loss(input, target, weight, size_average, ignore_index, reduce, reduction)
   1836                          .format(input.size(0), target.size(0)))
   1837     if dim == 2:
-> 1838         ret = torch._C._nn.nll_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
   1839     Elif dim == 4:
   1840         ret = torch._C._nn.nll_loss2d(input, target, weight, _Reduction.get_enum(reduction), ignore_index)

RuntimeError: expected scalar type Long but found Float
pythonmachine-learningdeep-learningpytorchartificial-intelligence
3
user12975267

LongTensor est synonyme d'entier. PyTorch n'acceptera pas un FloatTensor comme cible catégorique, il vous dit donc de convertir votre tenseur en LongTensor. Voici comment changer votre type de cible:

Yt_train = Yt_train.type(torch.LongTensor)

C'est très bien documenté sur le site Web de PyTorch, vous ne regretterez certainement pas d'avoir passé une minute ou deux à lire cette page. PyTorch définit essentiellement neuf types de tenseur de processeur et neuf types de tenseur de processeur graphique:

╔══════════════════════════╦═══════════════════════════════╦════════════════════╦═════════════════════════╗
║        Data type         ║             dtype             ║     CPU tensor     ║       GPU tensor        ║
╠══════════════════════════╬═══════════════════════════════╬════════════════════╬═════════════════════════╣
║ 32-bit floating point    ║ torch.float32 or torch.float  ║ torch.FloatTensor  ║ torch.cuda.FloatTensor  ║
║ 64-bit floating point    ║ torch.float64 or torch.double ║ torch.DoubleTensor ║ torch.cuda.DoubleTensor ║
║ 16-bit floating point    ║ torch.float16 or torch.half   ║ torch.HalfTensor   ║ torch.cuda.HalfTensor   ║
║ 8-bit integer (unsigned) ║ torch.uint8                   ║ torch.ByteTensor   ║ torch.cuda.ByteTensor   ║
║ 8-bit integer (signed)   ║ torch.int8                    ║ torch.CharTensor   ║ torch.cuda.CharTensor   ║
║ 16-bit integer (signed)  ║ torch.int16 or torch.short    ║ torch.ShortTensor  ║ torch.cuda.ShortTensor  ║
║ 32-bit integer (signed)  ║ torch.int32 or torch.int      ║ torch.IntTensor    ║ torch.cuda.IntTensor    ║
║ 64-bit integer (signed)  ║ torch.int64 or torch.long     ║ torch.LongTensor   ║ torch.cuda.LongTensor   ║
║ Boolean                  ║ torch.bool                    ║ torch.BoolTensor   ║ torch.cuda.BoolTensor   ║
╚══════════════════════════╩═══════════════════════════════╩════════════════════╩═════════════════════════╝
4
Nicolas Gervais