Pass correct image shape to model that uses a conv1d and con2d in the same network

vision
1

so i am trying to implement the VGG network, everything in the paper, but i have when i am using the architecture that has a conv1-255 as part of it network. below is my code

 def _make_convo_layers(architecture) -> torch.nn.Sequential:
        """
        Create convolutional layers from the vgg architecture type passed in.
        :param architecture:
        """
        layers = []
        in_channels = 3
        for layer in architecture:
            if type(layer) == int:
                out_channels = layer
                layers += [nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1, stride=1), nn.ReLU()]
                # layers.append([nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1, stride=1) + nn.ReLU()])
                in_channels = layer
            elif (layer == 'Conv1-256'):
                out_channels = 256
                layers += [nn.Conv1d(256, out_channels, kernel_size=3, padding=1, stride=1), nn.ReLU()]
            elif (layer == 'LRN'):
                layers += [nn.LocalResponseNorm(5, alpha=0.0001, beta=0.75, k=1)]
            elif (layer == 'M'):
                layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        return nn.Sequential(*layers)

below is me passing some random data to the model


device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(device)
vgg = VGGNet(config['vgg16-C1']).to(device)
x = torch.randn(1, 3, 224, 224).to(device)
model = vgg(x).to(device)
print(model.shape)

below is the error i received when i passed the x variable to the model

RuntimeError: Expected 3-dimensional input for 3-dimensional weight [256, 256, 3], but got 4-dimensional input of size [1, 256, 56, 56] instead

any help, will do please

2

In your code you are using nn.Conv1d which seems to be a typo:

elif (layer == 'Conv1-256'):
    out_channels = 256
    layers += [nn.Conv1d(256, out_channels, kernel_size=3, padding=1, stride=1), nn.ReLU()]

Replace it with nn.Conv2d and it should work.