Customized loss function - topk

I am trying to implement a customized loss function in pytorch based on the formula below.

def TopKLoss(pred, target, top_k=0.7):

    pred = F.log_softmax(pred)

    n = pred.size(0)
    c = pred.size(1)
    out_size = (n,) + pred.size()[2:]
    if target.size()[1:] != pred.size()[2:]:
        raise ValueError('Expected target size {}, got {}'.format(
            out_size, target.size()))

    pred = pred.contiguous()
    target = target.contiguous()

    for batch_no in range(n):
        for class_no in range(c):
            pixel_sum = (torch.numel(pred[batch_no][class_no]<top_k and target[batch_no]==class_no))
            topk_loss+= pixel_sum

    return topk_loss

This is what I have until now, but it throws an error when I try to sum over the elements
which respect the condition.

RuntimeError: bool value of Tensor with more than one value is ambiguous 

Can somebody help with this?