ValueError: Expected more than 1 spatial element when training, got input size torch.Size([8, 64, 1, 1])

Hi all
I keep getting this error:

ValueError: Expected more than 1 spatial element when training, got input size torch.Size([8, 64, 1, 1]).

Here is my code:

class DepthWiseConv2d(nn.Module):

    def __init__(self, in_channels, out_channels, kernel_size, groups, stride):
            super(DepthWiseConv2d, self).__init__()
            self.depthwise = nn.Sequential(
                       nn.Conv2d(in_channels, in_channels, kernel_size = kernel_size,
                                     groups = groups, stride = stride, padding = 1),
                       nn.InstanceNorm2d(in_channels),
                       nn.ReLU(True)
            )
            self.pointwise = nn.Sequential(
                       nn.Conv2d(in_channels, out_channels, kernel_size = kernel_size,
                               stride = stride),
                       nn.InstanceNorm2d(out_channels),
                       nn.ReLU(True)
            )
    def forward(self, x):
         out = self.depthwise(x)
         out = self.pointwise(out)
         return out

class VGGEncoder(nn.Module):

def __init__(self):
    super().__init__()
    vgg = vgg19(pretrained=True).features
    self.slice1 = vgg[: 2]
    self.slice2 = vgg[2: 7]
    self.slice3 = vgg[7: 12]
    self.slice4 = vgg[12: 21]
    for p in self.parameters():
        p.requires_grad = False

def forward(self, images, output_last_feature=False):
    h1 = self.slice1(images)
    h2 = self.slice2(h1)
    h3 = self.slice3(h2)
    h4 = self.slice4(h3)
    if output_last_feature:
        return h4
    else:
        return h1, h2, h3, h4

class WeightAndBias(nn.Module):
“”“Weight/Bias Network”""

def __init__(self, in_channels = 512):
    super(WeightAndBias,self).__init__()
    self.dwconv1 = DepthWiseConv2d(in_channels, 128, 3, 128, 2)
    self.dwconv2 = DepthWiseConv2d(128, 64, 3, 64, 2)
    # self.adapool1 = nn.AdaptiveMaxPool2d()
    self.dwconv3 = DepthWiseConv2d(64, 64, 3, 64, 2)
    # self.adapool2 = nn.AdaptiveMaxPool2d()

def forward(self, x):
    out = self.dwconv1(x)
    out = self.dwconv2(out)
    print(out.shape)
    # out = self.adapool1(out)
    out = self.dwconv3(out)
    # out = self.adapool2(out)
    return out

Here is my test case:

s = torch.rand(8,3,256,256)
out = VGGEncoder()(s, True)
out = WeightAndBias(512)(out)
print(out.shape)

Thank you!