gossip_sgd.py [463:505]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            prec1, prec5 = accuracy(output, target, topk=(1, 5))
            losses.update(loss.item(), features.size(0))
            top1.update(prec1.item(), features.size(0))
            top5.update(prec5.item(), features.size(0))

        log.info(' * Prec@1 {top1.avg:.3f} Prec@5 {top5.avg:.3f}'
                 .format(top1=top1, top5=top5))

    return top1.avg


def accuracy(output, target, topk=(1,)):
    """ Computes the precision@k for the specified values of k """
    with torch.no_grad():
        maxk = max(topk)
        batch_size = target.size(0)

        _, pred = output.topk(maxk, 1, True, True)
        pred = pred.t()
        correct = pred.eq(target.view(1, -1).expand_as(pred))

        res = []
        for k in topk:
            correct_k = correct[:k].view(-1).float().sum(0, keepdim=True)
            res.append(correct_k.mul_(100.0 / batch_size))
        return res


def update_state(state, update_dict):
    """ Helper function to update global state dict """
    for key in update_dict:
        state[key] = copy.deepcopy(update_dict[key])


def update_peers_per_itr(model, epoch):
    """ Update the model's peers per itr according to specified schedule """
    ppi = None
    e_max = -1
    for e in args.ppi_schedule:
        if e_max <= e and epoch >= e:
            e_max = e
            ppi = args.ppi_schedule[e]
    model.update_gossiper('peers_per_itr', ppi)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



gossip_sgd_adpsgd.py [433:475]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            prec1, prec5 = accuracy(output, target, topk=(1, 5))
            losses.update(loss.item(), features.size(0))
            top1.update(prec1.item(), features.size(0))
            top5.update(prec5.item(), features.size(0))

        log.info(' * Prec@1 {top1.avg:.3f} Prec@5 {top5.avg:.3f}'
                 .format(top1=top1, top5=top5))

    return top1.avg


def accuracy(output, target, topk=(1,)):
    """ Computes the precision@k for the specified values of k """
    with torch.no_grad():
        maxk = max(topk)
        batch_size = target.size(0)

        _, pred = output.topk(maxk, 1, True, True)
        pred = pred.t()
        correct = pred.eq(target.view(1, -1).expand_as(pred))

        res = []
        for k in topk:
            correct_k = correct[:k].view(-1).float().sum(0, keepdim=True)
            res.append(correct_k.mul_(100.0 / batch_size))
        return res


def update_state(state, update_dict):
    """ Helper function to update global state dict """
    for key in update_dict:
        state[key] = copy.deepcopy(update_dict[key])


def update_peers_per_itr(model, epoch):
    """ Update the model's peers per itr according to specified schedule """
    ppi = None
    e_max = -1
    for e in args.ppi_schedule:
        if e_max <= e and epoch >= e:
            e_max = e
            ppi = args.ppi_schedule[e]
    model.update_gossiper('peers_per_itr', ppi)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -