Expected 4-dimensional input for 4-dimensional weight [192, 768, 1, 1], but got 2-dimensional input of size [50, 1000] instead

1

I’m try to modify Inception v3 pre trained in pytorch to have a multi-output. ( 4 output precisely).

I get this error: Expected 4-dimensional input for 4-dimensional weight [192, 768, 1, 1], but got 2-dimensional input of size [50, 1000] instead

My input shape is : torch.Size([50, 3, 299, 299])

This is the code for my model,

class CNN1(nn.Module):
    def __init__(self, pretrained):
        super(CNN1, self).__init__()
        if pretrained is True:
            self.model = models.inception_v3(pretrained=True)    
        modules = list(self.model.children())[:-1]      # delete the last fc layer.
        self.features = nn.Sequential(*modules)
        self.fc0 = nn.Linear(2048, 10)   #digit 0
        self.fc1 = nn.Linear(2048, 10)  #digit 1
        self.fc2 = nn.Linear(2048, 10)    #digit 2
        self.fc3 = nn.Linear(2048, 10)   #digit 3  
    def forward(self, x):
        bs, _, _, _ = x.shape
        x = self.features(x)
        x = F.adaptive_avg_pool2d(x, 1).reshape(bs, -1)

        label0 = self.fc0(x)
        label1 = self.fc1(x)
        label2= self.fc2(x) 
        label3= self.fc3(x)
          
        return {'label0': label0, 'label1': label1,'label2':label2, 'label3': label3}

and this is a piece of iteration:

        for batch_idx, sample_batched in enumerate(train_dataloader):
            # importing data and moving to GPU
            image,label0, label1, label2, label3 = sample_batched['image'].to(device),\
                                             sample_batched['label0'].to(device),\
                                              sample_batched['label1'].to(device),\
                                               sample_batched['label2'].to(device) ,\
                                                       sample_batched['label3'].to(device)  

            
            # zero the parameter gradients
            optimizer.zero_grad()
            output=model(image.float())

anyone have a suggestion?

2

if you have input (50,3,299,299) and something in between gets (50, 1000) but expects 4d input, it probably means you are trying to pass 1d ouput to image-processing layer (channels, h, w)

(50, 1000) looks like an output of some classifier with batch size 50 and num_classes = 1000

3

Hi! I have a similar error, did you find any solution for this error? Thanks:)