Python utils.calculate_accuracy() Examples

The following are 4 code examples of utils.calculate_accuracy(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module utils , or try the search function .
Example #1
Source File: test.py    From DriverPostureClassification with MIT License 4 votes vote down vote up 
def test(data_loader, model, args, device):
    batch_time = AverageMeter()
    data_time = AverageMeter()
    top1 = AverageMeter()
    top3 = AverageMeter()

    # switch to evaluate mode
    model.eval()

    end_time = time.time()
    for i, (input, target) in enumerate(data_loader):
        # measure data loading time
        data_time.update(time.time() - end_time)

        input = input.to(device)
        target = target.to(device)

        # compute output and loss
        output = model(input)

        # measure accuracy and record loss
        prec1, prec3 = calculate_accuracy(output, target, topk=(1, 3))
        # prec1[0]: convert torch.Size([1]) to torch.Size([])
        top1.update(prec1[0].item(), input.size(0))
        top3.update(prec3[0].item(), input.size(0))

        # measure elapsed time
        batch_time.update(time.time() - end_time)
        end_time = time.time()

        if (i + 1) % args.log_interval == 0:
            print('Test Iter [{0}/{1}]\t'
                  'Prec@1 {top1.val:.3f} ({top1.avg:.3f})\t'
                  'Prec@3 {top3.val:.3f} ({top3.avg:.3f})\t'
                  'Batch Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
                  'Data Time {data_time.val:.3f} ({data_time.avg:.3f})'.format(
                      i + 1,
                      len(data_loader),
                      top1=top1,
                      top3=top3,
                      batch_time=batch_time,
                      data_time=data_time))

    print(' * Prec@1 {top1.avg:.2f}% | Prec@3 {top3.avg:.2f}%'.format(
        top1=top1, top3=top3))

    return top1.avg
Example #2
Source File: validation.py    From video-classification-3d-cnn-pytorch with MIT License 4 votes vote down vote up 
def val_epoch(epoch, data_loader, model, criterion, opt, logger):
    print('validation at epoch {}'.format(epoch))

    model.eval()

    batch_time = AverageMeter()
    data_time = AverageMeter()
    losses = AverageMeter()
    accuracies = AverageMeter()

    end_time = time.time()
    for i, (inputs, targets) in enumerate(data_loader):
        data_time.update(time.time() - end_time)

        if not opt.no_cuda:
            targets = targets.cuda(async=True)
        inputs = Variable(inputs, volatile=True)
        targets = Variable(targets, volatile=True)
        outputs = model(inputs)
        loss = criterion(outputs, targets)
        acc = calculate_accuracy(outputs, targets)

        losses.update(loss.data[0], inputs.size(0))
        accuracies.update(acc, inputs.size(0))

        batch_time.update(time.time() - end_time)
        end_time = time.time()

        print('Epoch: [{0}][{1}/{2}]\t'
              'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
              'Data {data_time.val:.3f} ({data_time.avg:.3f})\t'
              'Loss {loss.val:.4f} ({loss.avg:.4f})\t'
              'Acc {acc.val:.3f} ({acc.avg:.3f})'.format(
                  epoch, i + 1, len(data_loader), batch_time=batch_time,
                  data_time=data_time, loss=losses, acc=accuracies))

    logger.log({
        'epoch': epoch,
        'loss': losses.avg,
        'acc': accuracies.avg
    })

    return losses.avg
Example #3
Source File: validation.py    From video_feature_extractor with Apache License 2.0 4 votes vote down vote up 
def val_epoch(epoch, data_loader, model, criterion, opt, logger):
    print('validation at epoch {}'.format(epoch))

    model.eval()

    batch_time = AverageMeter()
    data_time = AverageMeter()
    losses = AverageMeter()
    accuracies = AverageMeter()

    end_time = time.time()
    for i, (inputs, targets) in enumerate(data_loader):
        data_time.update(time.time() - end_time)

        if not opt.no_cuda:
            targets = targets.cuda(async=True)
        inputs = Variable(inputs, volatile=True)
        targets = Variable(targets, volatile=True)
        outputs = model(inputs)
        loss = criterion(outputs, targets)
        acc = calculate_accuracy(outputs, targets)

        losses.update(loss.data[0], inputs.size(0))
        accuracies.update(acc, inputs.size(0))

        batch_time.update(time.time() - end_time)
        end_time = time.time()

        print('Epoch: [{0}][{1}/{2}]\t'
              'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
              'Data {data_time.val:.3f} ({data_time.avg:.3f})\t'
              'Loss {loss.val:.4f} ({loss.avg:.4f})\t'
              'Acc {acc.val:.3f} ({acc.avg:.3f})'.format(
                  epoch, i + 1, len(data_loader), batch_time=batch_time,
                  data_time=data_time, loss=losses, acc=accuracies))

    logger.log({
        'epoch': epoch,
        'loss': losses.avg,
        'acc': accuracies.avg
    })

    return losses.avg
Example #4
Source File: validation.py    From video-caption.pytorch with MIT License 4 votes vote down vote up 
def val_epoch(epoch, data_loader, model, criterion, opt, logger):
    print('validation at epoch {}'.format(epoch))

    model.eval()

    batch_time = AverageMeter()
    data_time = AverageMeter()
    losses = AverageMeter()
    accuracies = AverageMeter()

    end_time = time.time()
    for i, (inputs, targets) in enumerate(data_loader):
        data_time.update(time.time() - end_time)

        if not opt.no_cuda:
            targets = targets.cuda(async=True)
        inputs = Variable(inputs, volatile=True)
        targets = Variable(targets, volatile=True)
        outputs = model(inputs)
        loss = criterion(outputs, targets)
        acc = calculate_accuracy(outputs, targets)

        losses.update(loss.data[0], inputs.size(0))
        accuracies.update(acc, inputs.size(0))

        batch_time.update(time.time() - end_time)
        end_time = time.time()

        print('Epoch: [{0}][{1}/{2}]\t'
              'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t'
              'Data {data_time.val:.3f} ({data_time.avg:.3f})\t'
              'Loss {loss.val:.4f} ({loss.avg:.4f})\t'
              'Acc {acc.val:.3f} ({acc.avg:.3f})'.format(
                  epoch, i + 1, len(data_loader), batch_time=batch_time,
                  data_time=data_time, loss=losses, acc=accuracies))

    logger.log({
        'epoch': epoch,
        'loss': losses.avg,
        'acc': accuracies.avg
    })

    return losses.avg