本文整理汇总了Python中lib.utils.AverageMeter方法的典型用法代码示例。如果您正苦于以下问题:Python utils.AverageMeter方法的具体用法?Python utils.AverageMeter怎么用?Python utils.AverageMeter使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类lib.utils
的用法示例。
在下文中一共展示了utils.AverageMeter方法的9个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: validate
# 需要导入模块: from lib import utils [as 别名]
# 或者: from lib.utils import AverageMeter [as 别名]
def validate(epoch, model, ema=None):
"""
Evaluates the cross entropy between p_data and p_model.
"""
bpd_meter = utils.AverageMeter()
ce_meter = utils.AverageMeter()
if ema is not None:
ema.swap()
update_lipschitz(model)
model = parallelize(model)
model.eval()
correct = 0
total = 0
start = time.time()
with torch.no_grad():
for i, (x, y) in enumerate(tqdm(test_loader)):
x = x.to(device)
bpd, logits, _, _ = compute_loss(x, model)
bpd_meter.update(bpd.item(), x.size(0))
if args.task in ['classification', 'hybrid']:
y = y.to(device)
loss = criterion(logits, y)
ce_meter.update(loss.item(), x.size(0))
_, predicted = logits.max(1)
total += y.size(0)
correct += predicted.eq(y).sum().item()
val_time = time.time() - start
if ema is not None:
ema.swap()
s = 'Epoch: [{0}]\tTime {1:.2f} | Test bits/dim {bpd_meter.avg:.4f}'.format(epoch, val_time, bpd_meter=bpd_meter)
if args.task in ['classification', 'hybrid']:
s += ' | CE {:.4f} | Acc {:.2f}'.format(ce_meter.avg, 100 * correct / total)
logger.info(s)
return bpd_meter.avg
示例2: evaluate
# 需要导入模块: from lib import utils [as 别名]
# 或者: from lib.utils import AverageMeter [as 别名]
def evaluate():
# build dataset
val_loader, n_class = get_dataset()
# build model
net = get_model(n_class)
criterion = nn.CrossEntropyLoss()
if use_cuda:
net = net.cuda()
net = torch.nn.DataParallel(net, list(range(args.n_gpu)))
cudnn.benchmark = True
# begin eval
net.eval()
batch_time = AverageMeter()
losses = AverageMeter()
top1 = AverageMeter()
top5 = AverageMeter()
end = time.time()
with torch.no_grad():
for batch_idx, (inputs, targets) in enumerate(val_loader):
if use_cuda:
inputs, targets = inputs.cuda(), targets.cuda()
inputs, targets = Variable(inputs), Variable(targets)
outputs = net(inputs)
loss = criterion(outputs, targets)
# measure accuracy and record loss
prec1, prec5 = accuracy(outputs.data, targets.data, topk=(1, 5))
losses.update(loss.item(), inputs.size(0))
top1.update(prec1.item(), inputs.size(0))
top5.update(prec5.item(), inputs.size(0))
# timing
batch_time.update(time.time() - end)
end = time.time()
progress_bar(batch_idx, len(val_loader), 'Loss: {:.3f} | Acc1: {:.3f}% | Acc5: {:.3f}%'
.format(losses.avg, top1.avg, top5.avg))
示例3: train
# 需要导入模块: from lib import utils [as 别名]
# 或者: from lib.utils import AverageMeter [as 别名]
def train(epoch, train_loader):
print('\nEpoch: %d' % epoch)
net.train()
batch_time = AverageMeter()
losses = AverageMeter()
top1 = AverageMeter()
top5 = AverageMeter()
end = time.time()
for batch_idx, (inputs, targets) in enumerate(train_loader):
if use_cuda:
inputs, targets = inputs.cuda(), targets.cuda()
optimizer.zero_grad()
outputs = net(inputs)
loss = criterion(outputs, targets)
loss.backward()
optimizer.step()
# measure accuracy and record loss
prec1, prec5 = accuracy(outputs.data, targets.data, topk=(1, 5))
losses.update(loss.item(), inputs.size(0))
top1.update(prec1.item(), inputs.size(0))
top5.update(prec5.item(), inputs.size(0))
# timing
batch_time.update(time.time() - end)
end = time.time()
progress_bar(batch_idx, len(train_loader), 'Loss: {:.3f} | Acc1: {:.3f}% | Acc5: {:.3f}%'
.format(losses.avg, top1.avg, top5.avg))
writer.add_scalar('loss/train', losses.avg, epoch)
writer.add_scalar('acc/train_top1', top1.avg, epoch)
writer.add_scalar('acc/train_top5', top5.avg, epoch)
示例4: train
# 需要导入模块: from lib import utils [as 别名]
# 或者: from lib.utils import AverageMeter [as 别名]
def train(epoch):
print('\nEpoch: %d' % epoch)
adjust_learning_rate(optimizer, epoch)
train_loss = AverageMeter()
data_time = AverageMeter()
batch_time = AverageMeter()
correct = 0
total = 0
# switch to train mode
net.train()
end = time.time()
for batch_idx, (inputs, targets, indexes) in enumerate(trainloader):
data_time.update(time.time() - end)
if use_cuda:
inputs, targets, indexes = inputs.cuda(), targets.cuda(), indexes.cuda()
optimizer.zero_grad()
features = net(inputs)
outputs = lemniscate(features, indexes)
loss = criterion(outputs, indexes)
loss.backward()
optimizer.step()
train_loss.update(loss.item(), inputs.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
print('Epoch: [{}][{}/{}]'
'Time: {batch_time.val:.3f} ({batch_time.avg:.3f}) '
'Data: {data_time.val:.3f} ({data_time.avg:.3f}) '
'Loss: {train_loss.val:.4f} ({train_loss.avg:.4f})'.format(
epoch, batch_idx, len(trainloader), batch_time=batch_time, data_time=data_time, train_loss=train_loss))
示例5: train
# 需要导入模块: from lib import utils [as 别名]
# 或者: from lib.utils import AverageMeter [as 别名]
def train(cur_iter, total_iter,data_loader, model, criterion, optimizer,scheduler, opt):
model.eval()
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
accuracies = AverageMeter()
end_time = time.time()
i=cur_iter
while i<total_iter:
for _,(inputs,targets) in enumerate(data_loader):
if not opt.no_cuda:
targets = targets.cuda(async=True)
targets = Variable(targets)
inputs = Variable(inputs)
outputs = model(inputs)
loss = criterion(outputs, targets)
acc=calculate_accuracy(outputs,targets)
optimizer.zero_grad()
loss.backward()
optimizer.step()
scheduler.step(loss.data[0])
print('Iter:{} Loss_conf:{} acc:{} lr:{}'.format(i+1,loss.data[0],acc,optimizer.param_groups[0]['lr']),flush=True)
i+=1
if i%2000==0:
save_file_path = os.path.join(opt.result_dir, 'model_iter{}.pth'.format(i))
print("save to {}".format(save_file_path))
states = {
'state_dict': model.state_dict(),
'optimizer' : optimizer.state_dict(),
}
torch.save(states, save_file_path)
if i>=total_iter:
break
save_file_path = os.path.join(opt.result_dir, 'model_final.pth'.format(opt.checkpoint_path))
print("save to {}".format(save_file_path))
states = {
'state_dict': model.state_dict(),
'optimizer' : optimizer.state_dict(),
}
torch.save(states, save_file_path)
示例6: test
# 需要导入模块: from lib import utils [as 别名]
# 或者: from lib.utils import AverageMeter [as 别名]
def test(epoch, test_loader, save=True):
global best_acc
net.eval()
batch_time = AverageMeter()
losses = AverageMeter()
top1 = AverageMeter()
top5 = AverageMeter()
end = time.time()
with torch.no_grad():
for batch_idx, (inputs, targets) in enumerate(test_loader):
if use_cuda:
inputs, targets = inputs.cuda(), targets.cuda()
outputs = net(inputs)
loss = criterion(outputs, targets)
# measure accuracy and record loss
prec1, prec5 = accuracy(outputs.data, targets.data, topk=(1, 5))
losses.update(loss.item(), inputs.size(0))
top1.update(prec1.item(), inputs.size(0))
top5.update(prec5.item(), inputs.size(0))
# timing
batch_time.update(time.time() - end)
end = time.time()
progress_bar(batch_idx, len(test_loader), 'Loss: {:.3f} | Acc1: {:.3f}% | Acc5: {:.3f}%'
.format(losses.avg, top1.avg, top5.avg))
if save:
writer.add_scalar('loss/test', losses.avg, epoch)
writer.add_scalar('acc/test_top1', top1.avg, epoch)
writer.add_scalar('acc/test_top5', top5.avg, epoch)
is_best = False
if top1.avg > best_acc:
best_acc = top1.avg
is_best = True
print('Current best acc: {}'.format(best_acc))
save_checkpoint({
'epoch': epoch,
'model': args.model,
'dataset': args.dataset,
'state_dict': net.module.state_dict() if isinstance(net, nn.DataParallel) else net.state_dict(),
'acc': top1.avg,
'optimizer': optimizer.state_dict(),
}, is_best, checkpoint_dir=log_dir)
示例7: _validate
# 需要导入模块: from lib import utils [as 别名]
# 或者: from lib.utils import AverageMeter [as 别名]
def _validate(self, val_loader, model, verbose=False):
'''
Validate the performance on validation set
:param val_loader:
:param model:
:param verbose:
:return:
'''
batch_time = AverageMeter()
losses = AverageMeter()
top1 = AverageMeter()
top5 = AverageMeter()
criterion = nn.CrossEntropyLoss().cuda()
# switch to evaluate mode
model.eval()
end = time.time()
t1 = time.time()
with torch.no_grad():
for i, (input, target) in enumerate(val_loader):
target = target.cuda(non_blocking=True)
input_var = torch.autograd.Variable(input).cuda()
target_var = torch.autograd.Variable(target).cuda()
# compute output
output = model(input_var)
loss = criterion(output, target_var)
# measure accuracy and record loss
prec1, prec5 = accuracy(output.data, target, topk=(1, 5))
losses.update(loss.item(), input.size(0))
top1.update(prec1.item(), input.size(0))
top5.update(prec5.item(), input.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
t2 = time.time()
if verbose:
print('* Test loss: %.3f top1: %.3f top5: %.3f time: %.3f' %
(losses.avg, top1.avg, top5.avg, t2 - t1))
if self.acc_metric == 'acc1':
return top1.avg
elif self.acc_metric == 'acc5':
return top5.avg
else:
raise NotImplementedError
示例8: train
# 需要导入模块: from lib import utils [as 别名]
# 或者: from lib.utils import AverageMeter [as 别名]
def train(train_loader, model, lemniscate, criterion, optimizer, epoch):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
# switch to train mode
model.train()
end = time.time()
optimizer.zero_grad()
for i, (input, target, index) in enumerate(train_loader):
# measure data loading time
data_time.update(time.time() - end)
target = target.cuda(async=True)
index = index.cuda(async=True)
input_var = torch.autograd.Variable(input)
target_var = torch.autograd.Variable(target)
index_var = torch.autograd.Variable(index)
# compute output
feature = model(input_var)
output = lemniscate(feature, index_var)
loss = criterion(output, index_var) / args.iter_size
loss.backward()
# measure accuracy and record loss
losses.update(loss.data[0] * args.iter_size, input.size(0))
if (i+1) % args.iter_size == 0:
# compute gradient and do SGD step
optimizer.step()
optimizer.zero_grad()
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if i % args.print_freq == 0:
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'.format(
epoch, i, len(train_loader), batch_time=batch_time,
data_time=data_time, loss=losses))
示例9: NN
# 需要导入模块: from lib import utils [as 别名]
# 或者: from lib.utils import AverageMeter [as 别名]
def NN(epoch, net, lemniscate, trainloader, testloader, recompute_memory=0):
net.eval()
net_time = AverageMeter()
cls_time = AverageMeter()
losses = AverageMeter()
correct = 0.
total = 0
testsize = testloader.dataset.__len__()
trainFeatures = lemniscate.memory.t()
if hasattr(trainloader.dataset, 'imgs'):
trainLabels = torch.LongTensor([y for (p, y) in trainloader.dataset.imgs]).cuda()
else:
trainLabels = torch.LongTensor(trainloader.dataset.train_labels).cuda()
if recompute_memory:
transform_bak = trainloader.dataset.transform
trainloader.dataset.transform = testloader.dataset.transform
temploader = torch.utils.data.DataLoader(trainloader.dataset, batch_size=100, shuffle=False, num_workers=1)
for batch_idx, (inputs, targets, indexes) in enumerate(temploader):
targets = targets.cuda(async=True)
batchSize = inputs.size(0)
features = net(inputs)
trainFeatures[:, batch_idx*batchSize:batch_idx*batchSize+batchSize] = features.data.t()
trainLabels = torch.LongTensor(temploader.dataset.train_labels).cuda()
trainloader.dataset.transform = transform_bak
end = time.time()
with torch.no_grad():
for batch_idx, (inputs, targets, indexes) in enumerate(testloader):
targets = targets.cuda(async=True)
batchSize = inputs.size(0)
features = net(inputs)
net_time.update(time.time() - end)
end = time.time()
dist = torch.mm(features, trainFeatures)
yd, yi = dist.topk(1, dim=1, largest=True, sorted=True)
candidates = trainLabels.view(1,-1).expand(batchSize, -1)
retrieval = torch.gather(candidates, 1, yi)
retrieval = retrieval.narrow(1, 0, 1).clone().view(-1)
yd = yd.narrow(1, 0, 1)
total += targets.size(0)
correct += retrieval.eq(targets.data).sum().item()
cls_time.update(time.time() - end)
end = time.time()
print('Test [{}/{}]\t'
'Net Time {net_time.val:.3f} ({net_time.avg:.3f})\t'
'Cls Time {cls_time.val:.3f} ({cls_time.avg:.3f})\t'
'Top1: {:.2f}'.format(
total, testsize, correct*100./total, net_time=net_time, cls_time=cls_time))
return correct/total