Meaning of parameters

1

I am running the imagenet exampe in pytorch.

However, I don’t understand the meaning of data_time.val and data_time.avg. Even the loss.val and loss.avg.
Any one can help me understand it ?

2

data_time, losses etc are of type

class AverageMeter(object):
    """Computes and stores the average and current value"""
    def __init__(self):
        self.reset()

    def reset(self):
        self.val = 0
        self.avg = 0
        self.sum = 0
        self.count = 0

    def update(self, val, n=1):
        self.val = val
        self.sum += val * n
        self.count += n
        self.avg = self.sum / self.count

It’s thus just used to compute and store some statistics, e.g. about the loss.
It’s being updated e.g. in these lines: https://github.com/pytorch/examples/blob/master/imagenet/main.py#L199

3 Likes
3

Cool.
I understand it. Thank you