Did L_var term in discriminative loss forget to divide the batch_size?
kyuusaku opened this issue · comments
kyuusaku commented
jsis3d/losses/discriminative.py
Line 61 in d4c27e6
for i in range(batch_size):
n = size[i]
loss += torch.sum(var[i,:,:n]) / torch.sum(masks[i,:,:n])
loss /= batch_size
Pham Quang Hieu commented
Hi @kyuusaku,
Good catch, let me correct the code. I'm not sure it will have any impact on the performance though.