When do Validation
Opened this issue · 1 comments
celiazzx commented
Have you met this problem?
self.queue[ind, :, ptr:ptr + batch_size] = keys.T
RuntimeError: The expanded size of the tensor (6) must match the existing size (16) at non-singleton dimension 1. Target sizes: [128, 6]. Tensor sizes: [128, 16]
celiazzx commented
It looks like ptr will begin at 506 or other numbers when ContrastiveTrainer do the forward, it will leads to when tload the last batch data it will out of queue range