Python utils.accuracy方法代碼示例

本文整理匯總了Python中torch.utils.accuracy方法的典型用法代碼示例。如果您正苦於以下問題：Python utils.accuracy方法的具體用法？Python utils.accuracy怎麽用？Python utils.accuracy使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類torch.utils的用法示例。

在下文中一共展示了utils.accuracy方法的15個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: child_valid

# 需要導入模塊: from torch import utils [as 別名]
# 或者: from torch.utils import accuracy [as 別名]
def child_valid(valid_queue, model, arch_pool, criterion):
    valid_acc_list = []
    with torch.no_grad():
        model.eval()
        for i, arch in enumerate(arch_pool):
            # for step, (input, target) in enumerate(valid_queue):
            inputs, targets = next(iter(valid_queue))
            inputs = inputs.cuda()
            targets = targets.cuda()
                
            logits, _ = model(inputs, arch, bn_train=True)
            loss = criterion(logits, targets)
                
            prec1, prec5 = utils.accuracy(logits, targets, topk=(1, 5))
            valid_acc_list.append(prec1.data/100)
            
            if (i+1) % 100 == 0:
                logging.info('Valid arch %s\n loss %.2f top1 %f top5 %f', ' '.join(map(str, arch[0] + arch[1])), loss, prec1, prec5)
        
    return valid_acc_list

開發者ID:renqianluo，項目名稱:NAO_pytorch，代碼行數:22，代碼來源:train_search.py

示例2: valid

# 需要導入模塊: from torch import utils [as 別名]
# 或者: from torch.utils import accuracy [as 別名]
def valid(valid_queue, model, criterion):
    objs = utils.AvgrageMeter()
    top1 = utils.AvgrageMeter()
    top5 = utils.AvgrageMeter()
    with torch.no_grad():
        model.eval()
        for step, (input, target) in enumerate(valid_queue):
            input = input.cuda()
            target = target.cuda()
        
            logits, _ = model(input)
            loss = criterion(logits, target)
        
            prec1, prec5 = utils.accuracy(logits, target, topk=(1, 5))
            n = input.size(0)
            objs.update(loss.data, n)
            top1.update(prec1.data, n)
            top5.update(prec5.data, n)
        
            if (step+1) % 100 == 0:
                logging.info('valid %03d %e %f %f', step+1, objs.avg, top1.avg, top5.avg)

    return top1.avg, top5.avg, objs.avg

開發者ID:renqianluo，項目名稱:NAO_pytorch，代碼行數:25，代碼來源:train_imagenet.py

示例3: valid

# 需要導入模塊: from torch import utils [as 別名]
# 或者: from torch.utils import accuracy [as 別名]
def valid(valid_queue, model, criterion):
    objs = utils.AvgrageMeter()
    top1 = utils.AvgrageMeter()
    top5 = utils.AvgrageMeter()
    with torch.no_grad():
        model.eval()
        for step, (input, target) in enumerate(valid_queue):
            input = input.cuda()
            target = target.cuda()
        
            logits, _ = model(input)
            loss = criterion(logits, target)
        
            prec1, prec5 = utils.accuracy(logits, target, topk=(1, 5))
            n = input.size(0)
            objs.update(loss.data, n)
            top1.update(prec1.data, n)
            top5.update(prec5.data, n)
        
            if (step+1) % 100 == 0:
                logging.info('valid %03d %e %f %f', step+1, objs.avg, top1.avg, top5.avg)

    return top1.avg, objs.avg

開發者ID:renqianluo，項目名稱:NAO_pytorch，代碼行數:25，代碼來源:train_cifar.py

示例4: child_valid

# 需要導入模塊: from torch import utils [as 別名]
# 或者: from torch.utils import accuracy [as 別名]
def child_valid(valid_queue, model, arch_pool, criterion):
    valid_acc_list = []
    with torch.no_grad():
        model.eval()
        for i, arch in enumerate(arch_pool):
            #for step, (inputs, targets) in enumerate(valid_queue):
            inputs, targets = next(iter(valid_queue))
            inputs = inputs.cuda()
            targets = targets.cuda()
                
            logits, _ = model(inputs, arch, bn_train=True)
            loss = criterion(logits, targets)
                
            prec1, prec5 = utils.accuracy(logits, targets, topk=(1, 5))
            valid_acc_list.append(prec1.data/100)
            
            if (i+1) % 100 == 0:
                logging.info('Valid arch %s\n loss %.2f top1 %f top5 %f', ' '.join(map(str, arch[0] + arch[1])), loss, prec1, prec5)
        
    return valid_acc_list

開發者ID:renqianluo，項目名稱:NAO_pytorch，代碼行數:22，代碼來源:train_search.py

示例5: infer

# 需要導入模塊: from torch import utils [as 別名]
# 或者: from torch.utils import accuracy [as 別名]
def infer(valid_queue, model, criterion):
    objs = utils.AvgrageMeter()
    top1 = utils.AvgrageMeter()
    top5 = utils.AvgrageMeter()
    model.eval()

    for step, (input, target) in enumerate(valid_queue):
        input = input.cuda()
        target = target.cuda(non_blocking=True)

        logits = model(input, discrete=True)
        loss = criterion(logits, target)

        prec1, prec5 = utils.accuracy(logits, target, topk=(1, 5))
        n = input.size(0)
        objs.update(loss.data.item(), n)
        top1.update(prec1.data.item(), n)
        top5.update(prec5.data.item(), n)

        if step % args.report_freq == 0:
            logging.info('valid %03d %e %f %f', step, objs.avg, top1.avg, top5.avg)
            if args.debug:
                break

    return top1.avg, objs.avg

開發者ID:automl，項目名稱:nasbench-1shot1，代碼行數:27，代碼來源:train.py

示例6: infer

# 需要導入模塊: from torch import utils [as 別名]
# 或者: from torch.utils import accuracy [as 別名]
def infer(valid_queue, model, criterion):
    objs = utils.AvgrageMeter()
    top1 = utils.AvgrageMeter()
    top5 = utils.AvgrageMeter()
    model.eval()

    for step, (input, target) in enumerate(valid_queue):
        input = input.cuda()
        target = target.cuda(non_blocking=True)

        logits = model(input)
        loss = criterion(logits, target)

        prec1, prec5 = utils.accuracy(logits, target, topk=(1, 5))
        n = input.size(0)
        objs.update(loss.data.item(), n)
        top1.update(prec1.data.item(), n)
        top5.update(prec5.data.item(), n)

        if step % args.report_freq == 0:
            logging.info('valid %03d %e %f %f', step, objs.avg, top1.avg, top5.avg)

    return top1.avg, objs.avg

開發者ID:automl，項目名稱:nasbench-1shot1，代碼行數:25，代碼來源:train_search.py

示例7: infer

# 需要導入模塊: from torch import utils [as 別名]
# 或者: from torch.utils import accuracy [as 別名]
def infer(valid_queue, model, criterion):
    objs = utils.AvgrageMeter()
    top1 = utils.AvgrageMeter()
    top5 = utils.AvgrageMeter()
    model.eval()

    for step, (input, target) in enumerate(valid_queue):
        input = input.cuda()
        target = target.cuda(non_blocking=True)

        logits = model(input)
        loss = criterion(logits, target)

        prec1, prec5 = utils.accuracy(logits, target, topk=(1, 5))
        n = input.size(0)
        objs.update(loss.data.item(), n)
        top1.update(prec1.data.item(), n)
        top5.update(prec5.data.item(), n)

        if step % args.report_freq == 0:
            logging.info('valid %03d %e %f %f', step, objs.avg, top1.avg, top5.avg)
            if args.debug:
                break

    return top1.avg, objs.avg

開發者ID:automl，項目名稱:nasbench-1shot1，代碼行數:27，代碼來源:train_search.py

示例8: infer

# 需要導入模塊: from torch import utils [as 別名]
# 或者: from torch.utils import accuracy [as 別名]
def infer(valid_queue, model, criterion):
    objs = utils.AvgrageMeter()
    top1 = utils.AvgrageMeter()
    top5 = utils.AvgrageMeter()
    model.eval()

    for step, (input, target) in enumerate(valid_queue):
        input = Variable(input, volatile=True).cuda()
        target = Variable(target, volatile=True).cuda(async=True)

        logits, _ = model(input)
        loss = criterion(logits, target)

        prec1, prec5 = utils.accuracy(logits, target, topk=(1, 5))
        n = input.size(0)
        objs.update(loss.data[0], n)
        top1.update(prec1.data[0], n)
        top5.update(prec5.data[0], n)

        if step % args.report_freq == 0:
            logging.info('valid %03d %e %f %f', step, objs.avg, top1.avg, top5.avg)

    return top1.avg, top5.avg, objs.avg

開發者ID:automl，項目名稱:nasbench-1shot1，代碼行數:25，代碼來源:train_imagenet.py

示例9: infer

# 需要導入模塊: from torch import utils [as 別名]
# 或者: from torch.utils import accuracy [as 別名]
def infer(valid_queue, model, criterion):
    objs = utils.AvgrageMeter()
    top1 = utils.AvgrageMeter()
    top5 = utils.AvgrageMeter()
    model.eval()

    for step, (input, target) in enumerate(valid_queue):
        input = Variable(input, volatile=True).cuda()
        target = Variable(target, volatile=True).cuda(async=True)

        logits, _ = model(input)
        loss = criterion(logits, target)

        prec1, prec5 = utils.accuracy(logits, target, topk=(1, 5))
        n = input.size(0)
        objs.update(loss.data[0], n)
        top1.update(prec1.data[0], n)
        top5.update(prec5.data[0], n)

        if step % args.report_freq == 0:
            logging.info('valid %03d %e %f %f', step, objs.avg, top1.avg, top5.avg)

    return top1.avg, objs.avg

開發者ID:automl，項目名稱:nasbench-1shot1，代碼行數:25，代碼來源:train.py

示例10: child_valid

# 需要導入模塊: from torch import utils [as 別名]
# 或者: from torch.utils import accuracy [as 別名]
def child_valid(self, valid_queue, model, arch_pool, criterion):
        valid_acc_list = []
        with torch.no_grad():
            model.eval()
            for i, arch in enumerate(arch_pool):
                # for step, (inputs, targets) in enumerate(valid_queue):
                inputs, targets = valid_queue.next_batch()
                inputs = inputs.cuda()
                targets = targets.cuda()
                arch_l = arch
                arch = self.process_arch(arch)
                logits, _ = model(inputs, arch, bn_train=True)
                loss = criterion(logits, targets)

                prec1, prec5 = self.utils.accuracy(logits, targets, topk=(1, 5))
                valid_acc_list.append(prec1.data / 100)

                if (i + 1) % 100 == 0:
                    logging.info('Valid arch %s\n loss %.2f top1 %f top5 %f', self.process_archname(arch_l),
                                 loss, prec1, prec5)
        return valid_acc_list

開發者ID:kcyu2014，項目名稱:eval-nas，代碼行數:23，代碼來源:enas_search_policy.py

示例11: infer

# 需要導入模塊: from torch import utils [as 別名]
# 或者: from torch.utils import accuracy [as 別名]
def infer(valid_queue, model, criterion):
  objs = utils.AvgrageMeter()
  top1 = utils.AvgrageMeter()
  top5 = utils.AvgrageMeter()
  model.eval()

  for step, (input, target) in enumerate(valid_queue):
    input = Variable(input, volatile=True).cuda()
    target = Variable(target, volatile=True).cuda(async=True)

    logits, _ = model(input)
    loss = criterion(logits, target)

    prec1, prec5 = utils.accuracy(logits, target, topk=(1, 5))
    n = input.size(0)
    objs.update(loss.data[0], n)
    top1.update(prec1.data[0], n)
    top5.update(prec5.data[0], n)

    if step % args.report_freq == 0:
      logging.info('valid %03d %e %f %f', step, objs.avg, top1.avg, top5.avg)

  return top1.avg, top5.avg, objs.avg

開發者ID:kcyu2014，項目名稱:eval-nas，代碼行數:25，代碼來源:train_imagenet.py

示例12: infer

# 需要導入模塊: from torch import utils [as 別名]
# 或者: from torch.utils import accuracy [as 別名]
def infer(test_queue, model, criterion):
  objs = utils.AvgrageMeter()
  top1 = utils.AvgrageMeter()
  top5 = utils.AvgrageMeter()
  model.eval()

  for step, (input, target) in enumerate(test_queue):
    input = Variable(input, volatile=True).cuda()
    target = Variable(target, volatile=True).cuda(async=True)

    logits, _ = model(input)
    loss = criterion(logits, target)

    prec1, prec5 = utils.accuracy(logits, target, topk=(1, 5))
    n = input.size(0)
    objs.update(loss.data[0], n)
    top1.update(prec1.data[0], n)
    top5.update(prec5.data[0], n)

    if step % args.report_freq == 0:
      logging.info('test %03d %e %f %f', step, objs.avg, top1.avg, top5.avg)

  return top1.avg, objs.avg

開發者ID:kcyu2014，項目名稱:eval-nas，代碼行數:25，代碼來源:test.py

示例13: infer

# 需要導入模塊: from torch import utils [as 別名]
# 或者: from torch.utils import accuracy [as 別名]
def infer(valid_queue, model, criterion):
  objs = utils.AverageMeter()
  top1 = utils.AverageMeter()
  top5 = utils.AverageMeter()
  model.eval()

  for step, (input, target) in enumerate(valid_queue):
    input = Variable(input, volatile=True).cuda()
    target = Variable(target, volatile=True).cuda(async=True)

    logits, _ = model(input)
    loss = criterion(logits, target)

    prec1, prec5 = utils.accuracy(logits, target, topk=(1, 5))
    n = input.size(0)
    objs.update(loss.data[0], n)
    top1.update(prec1.data[0], n)
    top5.update(prec5.data[0], n)

    if step % args.report_freq == 0:
      logging.info('valid %03d %e %f %f', step, objs.avg, top1.avg, top5.avg)

  return top1.avg, objs.avg

開發者ID:kcyu2014，項目名稱:eval-nas，代碼行數:25，代碼來源:train.py

示例14: valid

# 需要導入模塊: from torch import utils [as 別名]
# 或者: from torch.utils import accuracy [as 別名]
def valid(valid_queue, model, criterion):
    objs = search_policies.cnn.utils.AverageMeter()
    top1 = search_policies.cnn.utils.AverageMeter()
    top5 = search_policies.cnn.utils.AverageMeter()
    with torch.no_grad():
        model.eval()
        for step, (input, target) in enumerate(valid_queue):
            input = input.cuda()
            target = target.cuda()
        
            logits, _ = model(input)
            loss = criterion(logits, target)
        
            prec1, prec5 = utils.accuracy(logits, target, topk=(1, 5))
            n = input.size(0)
            objs.update(loss.data, n)
            top1.update(prec1.data, n)
            top5.update(prec5.data, n)
        
            if (step+1) % 100 == 0:
                logging.info('valid %03d %e %f %f', step+1, objs.avg, top1.avg, top5.avg)

    return top1.avg, objs.avg

開發者ID:kcyu2014，項目名稱:eval-nas，代碼行數:25，代碼來源:train_cifar.py

示例15: child_valid

# 需要導入模塊: from torch import utils [as 別名]
# 或者: from torch.utils import accuracy [as 別名]
def child_valid(self,valid_queue, model, arch_pool, criterion):
        valid_acc_list = []
        with torch.no_grad():
            model.eval()
            for i, arch in enumerate(arch_pool):
                # for step, (inputs, targets) in enumerate(valid_queue):
                inputs, targets = next(iter(valid_queue))
                inputs = inputs.cuda()
                targets = targets.cuda()
                arch_l = arch
                arch = self.process_arch(arch)
                logits, _ = model(inputs, arch, bn_train=True)
                loss = criterion(logits, targets)

                prec1, prec5 = self.utils.accuracy(logits, targets, topk=(1, 5))
                valid_acc_list.append(prec1.data / 100)

                if (i + 1) % 100 == 0:
                    logging.info('Valid arch %s\n loss %.2f top1 %f top5 %f', self.process_archname(arch_l),
                                 loss, prec1, prec5)

        return valid_acc_list

開發者ID:kcyu2014，項目名稱:eval-nas，代碼行數:24，代碼來源:nao_search_policy.py

注：本文中的torch.utils.accuracy方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台，相關代碼片段篩選自各路編程大神貢獻的開源項目，源碼版權歸原作者所有，傳播和使用請參考對應項目的License；未經允許，請勿轉載。