Python utils.AvgrageMeter() Examples

The following are 30 code examples of utils.AvgrageMeter(). 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: train_search.py    From NAS-Benchmark with GNU General Public License v3.0 6 votes vote down vote up 
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)
        with torch.no_grad():
            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
Example #2
Source File: train_cifar.py    From NAO_pytorch with GNU General Public License v3.0 6 votes vote down vote up 
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
Example #3
Source File: train_cifar.py    From NAS-Benchmark with GNU General Public License v3.0 6 votes vote down vote up 
def infer(test_iterator, model, criterion):
    objs = utils.AvgrageMeter()
    top1 = utils.AvgrageMeter()
    model.eval()

    for step in test_iterator.yield_steps():
        input_, target = test_iterator.__next__()
        input_ = input_.cuda(non_blocking=True)
        target = target.cuda(non_blocking=True)
        with torch.no_grad():
            logits, _ = model(input_)
            loss = criterion(logits, target)

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

        if step % args.report_freq == 0:
            logging.info('Test Step: %03d Objs: %e Acc: %f', step, objs.avg, top1.avg)

    return top1.avg, objs.avg
Example #4
Source File: train_controller.py    From NAO_pytorch with GNU General Public License v3.0 6 votes vote down vote up 
def nao_valid(queue, model):
    pa = utils.AvgrageMeter()
    hs = utils.AvgrageMeter()
    mse = utils.AvgrageMeter()
    with torch.no_grad():
        model.eval()
        for step, sample in enumerate(queue):
            encoder_input = sample['encoder_input']
            encoder_target = sample['encoder_target']
            decoder_target = sample['decoder_target']
            
            encoder_input = encoder_input.cuda()
            encoder_target = encoder_target.cuda()
            decoder_target = decoder_target.cuda()
            
            predict_value, logits, arch = model(encoder_input)
            n = encoder_input.size(0)
            pairwise_acc = utils.pairwise_accuracy(encoder_target.data.squeeze().tolist(),
                                                predict_value.data.squeeze().tolist())
            hamming_dis = utils.hamming_distance(decoder_target.data.squeeze().tolist(), arch.data.squeeze().tolist())
            mse.update(F.mse_loss(predict_value.data.squeeze(), encoder_target.data.squeeze()), n)
            pa.update(pairwise_acc, n)
            hs.update(hamming_dis, n)
    return mse.avg, pa.avg, hs.avg
Example #5
Source File: train_imagenet.py    From NAO_pytorch with GNU General Public License v3.0 6 votes vote down vote up 
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
Example #6
Source File: test_controller.py    From NAO_pytorch with GNU General Public License v3.0 6 votes vote down vote up 
def nao_valid(queue, model):
    pa = utils.AvgrageMeter()
    hs = utils.AvgrageMeter()
    with torch.no_grad():
        model.eval()
        for step, sample in enumerate(queue):
            encoder_input = sample['encoder_input']
            encoder_target = sample['encoder_target']
            decoder_target = sample['decoder_target']
            
            encoder_input = encoder_input.cuda()
            encoder_target = encoder_target.cuda()
            decoder_target = decoder_target.cuda()
            
            predict_value, logits, arch = model(encoder_input)
            n = encoder_input.size(0)
            pairwise_acc = utils.pairwise_accuracy(encoder_target.data.squeeze().tolist(),
                                                predict_value.data.squeeze().tolist())
            hamming_dis = utils.hamming_distance(decoder_target.data.squeeze().tolist(), arch.data.squeeze().tolist())
            pa.update(pairwise_acc, n)
            hs.update(hamming_dis, n)
    return pa.avg, hs.avg
Example #7
Source File: train_cifar.py    From NAO_pytorch with GNU General Public License v3.0 6 votes vote down vote up 
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
Example #8
Source File: train_imagenet.py    From NAO_pytorch with GNU General Public License v3.0 6 votes vote down vote up 
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
Example #9
Source File: test_imagenet.py    From NAS-Benchmark with GNU General Public License v3.0 6 votes vote down vote up 
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
Example #10
Source File: test.py    From NAS-Benchmark with GNU General Public License v3.0 6 votes vote down vote up 
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
Example #11
Source File: test.py    From eval-nas with MIT License 6 votes vote down vote up 
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
Example #12
Source File: test_imagenet.py    From eval-nas with MIT License 6 votes vote down vote up 
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
Example #13
Source File: train_search.py    From eval-nas with MIT License 6 votes vote down vote up 
def nao_valid(queue, model):
    pa = utils.AvgrageMeter()
    hs = utils.AvgrageMeter()
    with torch.no_grad():
        model.eval()
        for step, sample in enumerate(queue):
            encoder_input = sample['encoder_input']
            encoder_target = sample['encoder_target']
            decoder_target = sample['decoder_target']
            
            encoder_input = encoder_input.cuda()
            encoder_target = encoder_target.cuda()
            decoder_target = decoder_target.cuda()
            
            predict_value, logits, arch = model(encoder_input)
            n = encoder_input.size(0)
            pairwise_acc = utils.pairwise_accuracy(encoder_target.data.squeeze().tolist(), predict_value.data.squeeze().tolist())
            hamming_dis = utils.hamming_distance(decoder_target.data.squeeze().tolist(), arch.data.squeeze().tolist())
            pa.update(pairwise_acc, n)
            hs.update(hamming_dis, n)
    return pa.avg, hs.avg
Example #14
Source File: train_cifar.py    From NAS-Benchmark with GNU General Public License v3.0 6 votes vote down vote up 
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
Example #15
Source File: train_imagenet.py    From eval-nas with MIT License 6 votes vote down vote up 
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
Example #16
Source File: train.py    From NAS-Benchmark with GNU General Public License v3.0 6 votes vote down vote up 
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(non_blocking=True)
    target = target.cuda(non_blocking=True)
    #input = Variable(input).cuda()
    #target = Variable(target).cuda(async=True)
    with torch.no_grad():
      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
Example #17
Source File: test.py    From NAS-Benchmark with GNU General Public License v3.0 6 votes vote down vote up 
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 = input.cuda()
    target = target.cuda()
    with torch.no_grad():
        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('test %03d %e %f %f', step, objs.avg, top1.avg, top5.avg)

  return top1.avg, objs.avg
Example #18
Source File: train_search.py    From NAS-Benchmark with GNU General Public License v3.0 6 votes vote down vote up 
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)
    #input = Variable(input).cuda()
    #target = Variable(target).cuda(async=True)
    with torch.no_grad():
      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
Example #19
Source File: train_cifar.py    From NAS-Benchmark with GNU General Public License v3.0 6 votes vote down vote up 
def infer(valid_queue, model, criterion):
    objs = utils.AvgrageMeter()
    top1 = utils.AvgrageMeter()
    model.eval()

    for step, (input, target) in enumerate(valid_queue):
        input = input.cuda(non_blocking=True)
        target = target.cuda(non_blocking=True)
        with torch.no_grad():
            logits, _ = model(input)
            loss = criterion(logits, target)

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

        if step % args.report_freq == 0:
            logging.info('Valid Step: %03d Objs: %e Acc: %f', step, objs.avg, top1.avg)

    return top1.avg, objs.avg
Example #20
Source File: train_search.py    From NAS-Benchmark with GNU General Public License v3.0 6 votes vote down vote up 
def nao_valid(queue, model):
    pa = utils.AvgrageMeter()
    hs = utils.AvgrageMeter()
    with torch.no_grad():
        model.eval()
        for step, sample in enumerate(queue):
            encoder_input = sample['encoder_input']
            encoder_target = sample['encoder_target']
            decoder_target = sample['decoder_target']

            encoder_input = encoder_input.cuda()
            encoder_target = encoder_target.cuda()
            decoder_target = decoder_target.cuda()

            predict_value, logits, arch = model(encoder_input)
            n = encoder_input.size(0)
            pairwise_acc = utils.pairwise_accuracy(encoder_target.data.squeeze().tolist(),
                                                   predict_value.data.squeeze().tolist())
            hamming_dis = utils.hamming_distance(decoder_target.data.squeeze().tolist(), arch.data.squeeze().tolist())
            pa.update(pairwise_acc, n)
            hs.update(hamming_dis, n)
    return pa.avg, hs.avg
Example #21
Source File: train.py    From darts with Apache License 2.0 6 votes vote down vote up 
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
Example #22
Source File: test.py    From darts with Apache License 2.0 6 votes vote down vote up 
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
Example #23
Source File: train_imagenet.py    From darts with Apache License 2.0 6 votes vote down vote up 
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
Example #24
Source File: train_search.py    From darts with Apache License 2.0 6 votes vote down vote up 
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
Example #25
Source File: train_imagenet.py    From eval-nas with MIT License 6 votes vote down vote up 
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
Example #26
Source File: train.py    From AutoDL with Apache License 2.0 5 votes vote down vote up 
def test(model, test_prog, test_vars, exe, data_list):
    """
        test
    """
    test_py_reader, loss_test, acc_test = test_vars
    test_prog = test_prog.clone(for_test=True)
    objs = utils.AvgrageMeter()

    test_reader = reader.test10(FLAGS.data_path, FLAGS.batch_size, data_list)
    test_py_reader.decorate_paddle_reader(test_reader)

    test_py_reader.start()
    test_fetch_list = [acc_test]
    test_start_time = time.time()
    step_id = 0
    try:
        while True:
            prev_test_start_time = test_start_time
            test_start_time = time.time()
            acc_v, = exe.run(
                test_prog, fetch_list=test_fetch_list)
            objs.update(np.array(acc_v), np.array(acc_v).shape[0])
            step_id += 1
    except fluid.core.EOFException:
        test_py_reader.reset()
    print("test acc {0}".format(objs.avg))
    return objs.avg
Example #27
Source File: train.py    From SinglePathOneShot with MIT License 5 votes vote down vote up 
def validate(model, device, args, *, all_iters=None):
    objs = AvgrageMeter()
    top1 = AvgrageMeter()
    top5 = AvgrageMeter()

    loss_function = args.loss_function
    val_dataprovider = args.val_dataprovider

    model.eval()
    max_val_iters = 250
    t1  = time.time()
    with torch.no_grad():
        for _ in range(1, max_val_iters + 1):
            data, target = val_dataprovider.next()
            target = target.type(torch.LongTensor)
            data, target = data.to(device), target.to(device)

            output = model(data)
            loss = loss_function(output, target)

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

    logInfo = 'TEST Iter {}: loss = {:.6f},\t'.format(all_iters, objs.avg) + \
              'Top-1 err = {:.6f},\t'.format(1 - top1.avg / 100) + \
              'Top-5 err = {:.6f},\t'.format(1 - top5.avg / 100) + \
              'val_time = {:.6f}'.format(time.time() - t1)
    logging.info(logInfo)
Example #28
Source File: train_imagenet.py    From NAS-Benchmark with GNU General Public License v3.0 5 votes vote down vote up 
def train(train_queue, model, optimizer, global_step, criterion):
    objs = utils.AvgrageMeter()
    top1 = utils.AvgrageMeter()
    top5 = utils.AvgrageMeter()
    model.train()
    for step, (input, target) in enumerate(train_queue):
        input = input.cuda().requires_grad_()
        target = target.cuda()
    
        optimizer.zero_grad()
        logits, aux_logits = model(input, global_step)
        global_step += 1
        loss = criterion(logits, target)
        if aux_logits is not None:
            aux_loss = criterion(aux_logits, target)
            loss += 0.4 * aux_loss
        loss.backward()
        nn.utils.clip_grad_norm_(model.parameters(), args.grad_clip)
        optimizer.step()
    
        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('train %03d loss %e top1 %f top5 %f', step+1, objs.avg, top1.avg, top5.avg)

    return top1.avg, objs.avg, global_step
Example #29
Source File: train_search.py    From enas-pytorch with Apache License 2.0 5 votes vote down vote up 
def train(train_loader, model, controller, optimizer):
    total_loss = utils.AvgrageMeter()
    total_top1 = utils.AvgrageMeter()

    for step, (data, target) in enumerate(train_loader):
        model.train()
        n = data.size(0)

        data = data.cuda()
        target = target.cuda()

        optimizer.zero_grad()

        controller.eval()
        dag, _, _ = controller()

        logits, _ = model(data, dag)
        loss = F.cross_entropy(logits, target)

        loss.backward()
        optimizer.step()

        prec1 = utils.accuracy(logits, target)[0]
        total_loss.update(loss.item(), n)
        total_top1.update(prec1.item(), n)

        if step % args.report_freq == 0:
            logging.info('train %03d %e %f', step, total_loss.avg, total_top1.avg)

    return total_top1.avg
Example #30
Source File: train_search.py    From NAS-Benchmark with GNU General Public License v3.0 5 votes vote down vote up 
def child_train(train_queue, model, optimizer, global_step, arch_pool, arch_pool_prob, criterion):
    objs = utils.AvgrageMeter()
    top1 = utils.AvgrageMeter()
    top5 = utils.AvgrageMeter()
    model.train()
    for step, (input, target) in enumerate(train_queue):
        input = input.cuda().requires_grad_()
        target = target.cuda()

        optimizer.zero_grad()
        # sample an arch to train
        arch = utils.sample_arch(arch_pool, arch_pool_prob)
        logits, aux_logits = model(input, arch, global_step)
        global_step += 1
        loss = criterion(logits, target)
        if aux_logits is not None:
            aux_loss = criterion(aux_logits, target)
            loss += 0.4 * aux_loss
        loss.backward()
        nn.utils.clip_grad_norm_(model.parameters(), args.child_grad_bound)
        optimizer.step()

        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('Train %03d loss %e top1 %f top5 %f', step + 1, objs.avg, top1.avg, top5.avg)
            logging.info('Arch: %s', ' '.join(map(str, arch[0] + arch[1])))

    return top1.avg, objs.avg, global_step