meijie0401

I know why the dimension is 962 and 1054 respectively: north pole and south pole, have 32 corresponded UV points respectively, and each of 30 boundary vertices has two corresponded...

I think when batchsize is not 1, we should divide 'regularizers' by 2*batch size just like following. What's your idea? regularizers = sum([tf.nn.l2_loss(variable) for variable in self.variables])//(2*batch_size)

So even if you don't append 'wd, bd, weight, and bias' to varilables list, they are still can be updated by tensorflow ? Only when we want to use regularization,...

@walsvid Hi thanks for your code for tensorboard. But I also want to see the loss on validation dataset. Do you know how to feed validation dataset to feed_dict ?...

@walsvid Thank you!! another quick questoin: is there normalization for input image in this repo? I can't l locate normolization in this code.