def train(train_loader, epoch, model, optimizer, criterion, device):
top1 = AverageMeter('Acc@1', ':6.2f')
progress = ProgressMeter(len(train_loader),
top1,
prefix="Epoch: [{}]".format(epoch))
# switch to train mode
model.train()
for i, (inputs, target) in enumerate(train_loader):
inputs = inputs.to(device)
target = target.to(device)
# compute output
output = model(inputs)
loss = criterion(output, target)
# measure accuracy and record loss, accuracy
acc1 = accuracy(output, target, topk=(1, ))
top1.update(acc1[0].item(), inputs.size(0))
# compute gradient and do SGD step
optimizer.zero_grad()
loss.backward()
optimizer.step()
if i % PRINTFREQ == 0:
progress.print(i)
print('=> Acc@1 {top1.avg:.3f}'.format(top1=top1))
def train(train_loader, model, criteria, optimizer, device, batch_size):
model.train()
evaluator = Evaluator(21)
evaluator.reset()
train_loss = AverageMeter("Loss", ":.4")
progress = ProgressMeter(len(train_loader), train_loss)
for i, (image, mask) in enumerate(train_loader):
image = image.to(device)
mask = mask.to(device)
output = model(image)
loss = criteria(output, mask)
predict = output.data.cpu().numpy()
predict = np.argmax(predict, axis=1)
target = mask.cpu().numpy()
evaluator.add_batch(target, predict)
train_loss.update(loss.item(), batch_size)
optimizer.zero_grad()
loss.backward()
optimizer.step()
if i % 100 == 0:
progress.print(i)
evaluator.add_batch(target, predict)
info = {"loss": train_loss.val,
"pixel acc": evaluator.Pixel_Accuracy(),
"mean acc": evaluator.Pixel_Accuracy_Class(),
"miou": evaluator.Mean_Intersection_over_Union()}
return info
def train(train_loader, epoch, model, optimizer, criterion):
batch_time = AverageMeter('Time', ':6.3f')
data_time = AverageMeter('Data', ':6.3f')
losses = AverageMeter('Loss', ':.4e')
top1 = AverageMeter('Acc@1', ':6.2f')
top5 = AverageMeter('Acc@5', ':6.2f')
progress = ProgressMeter(len(train_loader), batch_time, data_time, losses,
top1, top5, prefix="Epoch: [{}]".format(epoch))
# switch to train mode
model.train()
end = time.time()
for i, (input, target) in enumerate(train_loader):
# measure data loading time
data_time.update(time.time() - end)
input = input.cuda()
target = target.cuda()
r = np.random.rand(1)
if args.beta > 0 and r < args.cutmix_prob:
# generate mixed sample
lam = np.random.beta(args.beta, args.beta)
rand_index = torch.randperm(input.size()[0]).cuda()
target_a = target
target_b = target[rand_index]
bbx1, bby1, bbx2, bby2 = rand_bbox(input.size(), lam)
input[:, :, bbx1:bbx2, bby1:bby2] = input[rand_index, :, bbx1:bbx2, bby1:bby2]
# adjust lambda to exactly match pixel ratio
lam = 1 - ((bbx2 - bbx1) * (bby2 - bby1) / (input.size()[-1] * input.size()[-2]))
# compute output
output = model(input)
loss = criterion(output, target_a) * lam + criterion(output, target_b) * (1. - lam)
else:
# compute output
output = model(input)
loss = criterion(output, target)
# measure accuracy and record loss, accuracy
acc1, acc5 = accuracy(output, target, topk=(1, 5))
losses.update(loss.item(), input.size(0))
top1.update(acc1[0].item(), input.size(0))
top5.update(acc5[0].item(), input.size(0))
# compute gradient and do SGD step
optimizer.zero_grad()
loss.backward()
optimizer.step()
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if i % args.print_freq == 0:
progress.print(i)
print('=> Acc@1 {top1.avg:.3f} Acc@5 {top5.avg:.3f}'
.format(top1=top1, top5=top5))
return top1.avg
def validate_identification(cfg, model, test_loader, criterion):
batch_time = AverageMeter('Time', ':6.3f')
losses = AverageMeter('Loss', ':.4e')
top1 = AverageMeter('Acc@1', ':6.2f')
top5 = AverageMeter('Acc@5', ':6.2f')
progress = ProgressMeter(len(test_loader),
batch_time,
losses,
top1,
top5,
prefix='Test: ',
logger=logger)
# switch to evaluate mode
model.eval()
with torch.no_grad():
end = time.time()
for i, (input, target) in enumerate(test_loader):
input = input.cuda(non_blocking=True) #.squeeze(0)
target = target.cuda(non_blocking=True)
# compute output
output = model(input)
# MODIFYING EVALUATION STAGE: WHY AVG THIS THING?
# output = torch.mean(output, dim=0, keepdim=True)
# output = model.forward_classifier(output)
print("DEBUG 1")
print(f'Target shape: {target.shape}. Target:')
print(target)
print(f'output of forward shape: {output.shape}. output:')
print(output)
acc1 = accuracy(output, target, topk=(1, ))
top1.update(acc1[0], input.size(0))
# top5.update(acc5[0], input.size(0))
loss = criterion(output, target)
losses.update(loss.item(), 1)
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if i % 2000 == 0:
progress.print(i)
# This gives formatting problems. Just printing the top1 object is fine
# logger.info('Test Acc@1: {:.8f} Acc@5: {:.8f}'.format(top1.avg, top5.avg))
print(top1)
return top1.avg
def train_epoch(train_loader, model, criterion, optimizer, epoch, args):
""" 训练模型一个epoch的数据
:param train_loader: 训练集
:param model: 模型
:param criterion: 损失函数
:param optimizer: 优化器
:param epoch: 当前迭代次数
:param args: 训练超参
"""
batch_time = AverageMeter('Time', ':6.3f')
data_time = AverageMeter('Data', ':6.3f')
losses = AverageMeter('Loss', ':.4e')
top1 = AverageMeter('Acc@1', ':6.2f')
progress = ProgressMeter(len(train_loader), batch_time, data_time,
losses, top1, prefix=f"Epoch: [{epoch}]")
# 训练模式
model.train()
end_time = time.time()
for i, (images, scores, _) in enumerate(train_loader):
# 更新数据加载时间度量
data_time.update(time.time() - end_time)
if args.cuda:
images = images.cuda(args.gpu, non_blocking=True)
scores = scores.cuda(args.gpu, non_blocking=True)
# 网络推理
outputs = model(images)
loss = criterion(outputs, scores)
# 计算梯度、更新
optimizer.zero_grad()
if args.cuda:
with amp.scale_loss(loss, optimizer) as scaled_loss:
scaled_loss.backward()
else:
loss.backward()
optimizer.step()
# 更新度量
acc1, _, _ = criterion.accuracy(outputs, scores)
batch_size = images.size(0)/2 if args.criterion == 'rank' else images.size(0)
losses.update(loss.detach().cpu().item(), batch_size)
top1.update(acc1.item(), batch_size)
# 更新一个batch训练时间度量
batch_time.update(time.time() - end_time)
end_time = time.time()
if i % args.print_freq == 0:
progress.print(i)
return losses.avg, top1.avg
def validate(val_loader, model, criterion):
batch_time = AverageMeter("Time", ":6.3f")
losses = AverageMeter("Loss", ":.4e")
top1 = AverageMeter("Acc@1", ":6.2f")
top5 = AverageMeter("Acc@5", ":6.2f")
progress = ProgressMeter(len(val_loader),
batch_time,
losses,
top1,
top5,
prefix="Test: ")
# switch to evaluate mode
model.eval()
total_loss = 0.0
with torch.no_grad():
end = time.time()
for i, (input, target) in enumerate(val_loader):
input = input.cuda()
target = target.cuda()
# compute output
output = model(input)
loss = criterion(output, target)
# measure accuracy and record loss
acc1, acc5 = accuracy(output, target, topk=(1, 5))
losses.update(loss.item(), input.size(0))
top1.update(acc1[0], input.size(0))
top5.update(acc5[0], input.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
total_loss += loss.item()
if i % args.print_freq == 0:
progress.print(i)
end = time.time()
print("====> Acc@1 {top1.avg:.3f} Acc@5 {top5.avg:.3f}".format(
top1=top1, top5=top5))
total_loss = total_loss / len(val_loader)
return top1.avg
def validate_identification(cfg, model, test_loader, criterion):
batch_time = AverageMeter('Time', ':6.3f')
losses = AverageMeter('Loss', ':.4e')
top1 = AverageMeter('Acc@1', ':6.2f')
top5 = AverageMeter('Acc@5', ':6.2f')
progress = ProgressMeter(len(test_loader),
batch_time,
losses,
top1,
top5,
prefix='Test: ',
logger=logger)
# switch to evaluate mode
model.eval()
with torch.no_grad():
end = time.time()
for i, (input, target) in enumerate(test_loader):
input = input.cuda(non_blocking=True).squeeze(0)
target = target.cuda(non_blocking=True)
# compute output
output = model(input)
output = torch.mean(output, dim=0, keepdim=True)
output = model.forward_classifier(output)
acc1, acc5 = accuracy(output, target, topk=(1, 5))
top1.update(acc1[0], input.size(0))
top5.update(acc5[0], input.size(0))
loss = criterion(output, target)
losses.update(loss.item(), 1)
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if i % 2000 == 0:
progress.print(i)
logger.info('Test Acc@1: {:.8f} Acc@5: {:.8f}'.format(
top1.avg, top5.avg))
return top1.avg
def validate_verification(cfg, model, test_loader):
batch_time = AverageMeter('Time', ':6.3f')
progress = ProgressMeter(len(test_loader),
batch_time,
prefix='Test: ',
logger=logger)
# switch to evaluate mode
model.eval()
labels, distances = [], []
with torch.no_grad():
end = time.time()
for i, (input1, input2, label) in enumerate(test_loader):
input1 = input1.cuda(non_blocking=True).squeeze(0)
input2 = input2.cuda(non_blocking=True).squeeze(0)
label = label.cuda(non_blocking=True)
# compute output
outputs1 = model(input1).mean(dim=0).unsqueeze(0)
outputs2 = model(input2).mean(dim=0).unsqueeze(0)
dists = F.cosine_similarity(outputs1, outputs2)
dists = dists.data.cpu().numpy()
distances.append(dists)
labels.append(label.data.cpu().numpy())
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if i % 2000 == 0:
progress.print(i)
labels = np.array([sublabel for label in labels for sublabel in label])
distances = np.array(
[subdist for dist in distances for subdist in dist])
eer = compute_eer(distances, labels)
logger.info('Test EER: {:.8f}'.format(np.mean(eer)))
return eer
def train(cfg,
model,
optimizer,
train_loader,
val_loader,
criterion,
architect,
epoch,
writer_dict,
lr_scheduler=None):
batch_time = AverageMeter('Time', ':6.3f')
data_time = AverageMeter('Data', ':6.3f')
losses = AverageMeter('Loss', ':.4e')
top1 = AverageMeter('Acc@1', ':6.2f')
top5 = AverageMeter('Acc@5', ':6.2f')
alpha_entropies = AverageMeter('Entropy', ':.4e')
progress = ProgressMeter(len(train_loader),
batch_time,
data_time,
losses,
top1,
top5,
alpha_entropies,
prefix="Epoch: [{}]".format(epoch),
logger=logger)
writer = writer_dict['writer']
# switch to train mode
model.train()
end = time.time()
for i, (input, target) in enumerate(train_loader):
global_steps = writer_dict['train_global_steps']
if lr_scheduler:
current_lr = lr_scheduler.set_lr(optimizer, global_steps, epoch)
else:
current_lr = cfg.TRAIN.LR
# measure data loading time
data_time.update(time.time() - end)
input = input.cuda(non_blocking=True)
target = target.cuda(non_blocking=True)
input_search, target_search = next(iter(val_loader))
input_search = input_search.cuda(non_blocking=True)
target_search = target_search.cuda(non_blocking=True)
# step architecture
architect.step(input_search, target_search)
alpha_entropy = architect.model.compute_arch_entropy()
alpha_entropies.update(alpha_entropy.mean(), input.size(0))
# compute output
output = model(input)
# measure accuracy and record loss
acc1, acc5 = accuracy(output, target, topk=(1, 5))
top1.update(acc1[0], input.size(0))
top5.update(acc5[0], input.size(0))
loss = criterion(output, target)
losses.update(loss.item(), input.size(0))
# compute gradient and do SGD step
optimizer.zero_grad()
loss.backward()
optimizer.step()
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
# write to logger
writer.add_scalar('lr', current_lr, global_steps)
writer.add_scalar('train_loss', losses.val, global_steps)
writer.add_scalar('arch_entropy', alpha_entropies.val, global_steps)
writer_dict['train_global_steps'] = global_steps + 1
# log acc for cross entropy loss
writer.add_scalar('train_acc1', top1.val, global_steps)
writer.add_scalar('train_acc5', top5.val, global_steps)
if i % cfg.PRINT_FREQ == 0:
progress.print(i)
def train_epoch(train_loader, model, criterion, optimizer, epoch, args):
"""
训练模型一个epoch的数据
:param train_loader: 训练集
:param model: 模型
:param criterion: 损失函数
:param optimizer: 优化器
:param epoch: 当前迭代次数
:param args: 训练超参
"""
global mix_up, multi_scale, bn_gammas, net_weights
batch_time = AverageMeter('Time', ':6.3f')
data_time = AverageMeter('Data', ':6.3f')
losses = AverageMeter('Loss', ':.4e')
top1 = AverageMeter('Acc@1', ':6.2f')
progress = ProgressMeter(len(train_loader),
batch_time,
data_time,
losses,
top1,
prefix=f"Epoch: [{epoch}]")
# 训练模式
model.train()
end_time = time.time()
for i, (images, targets, _, weights) in enumerate(train_loader):
# 更新数据加载时间度量
data_time.update(time.time() - end_time)
# 只有训练集，才可能进行mixup和multi-scale数据增强
images, targets1, targets2, mix_rate = mix_up(images, targets)
if args.multi_scale:
images = multi_scale(images)
images = DataLoaderX.normalize(images, args)
if args.cuda:
images = images.cuda(args.gpu, non_blocking=True)
targets1 = targets1.cuda(args.gpu, non_blocking=True)
weights = weights.cuda(args.gpu, non_blocking=True)
if targets2 is not None:
targets2 = targets2.cuda(args.gpu, non_blocking=True)
mix_rate = mix_rate.cuda(args.gpu, non_blocking=True)
output = model(images)
loss = criterion(output, targets1, weights)
if targets2 is not None:
loss = mix_rate * loss + (1.0 - mix_rate) * criterion(
output, targets2, weights)
if mix_rate < 0.5:
targets1 = targets2
optimizer.zero_grad()
if args.cuda:
with amp.scale_loss(loss, optimizer) as scaled_loss:
scaled_loss.backward()
else:
loss.backward()
# network slimming
if args.sparsity:
for gamma in bn_gammas:
gamma.data.add_(-torch.sign(gamma.data),
alpha=args.slim *
optimizer.param_groups[0]['lr'])
# weight decay
for param in net_weights:
param.data.add_(-param.data,
alpha=args.weight_decay *
optimizer.param_groups[0]['lr'])
optimizer.step()
# 更新度量
acc1 = accuracy(output, targets1)
losses.update(loss.detach().cpu().item(), images.size(0))
top1.update(acc1.item(), images.size(0))
# 更新一个batch训练时间度量
batch_time.update(time.time() - end_time)
end_time = time.time()
if i % args.print_freq == 0:
progress.print(i)
return losses.avg, top1.avg
def train(train_loader, epoch, model, optimizer, criterion):
batch_time = AverageMeter('Time', ':6.3f')
losses = AverageMeter('Loss', ':.4e')
top1 = AverageMeter('Acc@1', ':6.2f')
top5 = AverageMeter('Acc@5', ':6.2f')
progress = ProgressMeter(len(train_loader),
batch_time,
losses,
top1,
top5,
prefix="Epoch: [{}]".format(epoch))
# switch to train mode
model.train()
end = time.time()
for i, (input, target) in enumerate(train_loader):
# measure data loading time
input = input.cuda()
target = target.cuda()
# get the image size
I_x, I_y = input.size()[2:]
#draw a boundary position
w = int(np.round(I_x * np.random.beta(0.3, 0.3)))
h = int(np.round(I_y * np.random.beta(0.3, 0.3)))
w_ = [w, I_x - w, w, I_x - w]
h_ = [h, h, I_y - h, I_y - h]
#select and crop four images
cropped_images = {}
c_ = {}
W_ = {}
for k in range(4):
index = torch.randperm(input.size(0))
index = index.cuda()
x_k = np.random.randint(0, I_x - w_[k] + 1)
y_k = np.random.randint(0, I_y - h_[k] + 1)
cropped_images[k] = input[index][:, :, x_k:x_k + w_[k],
y_k:y_k + h_[k]]
c_[k] = target[index]
W_[k] = (w_[k] * h_[k]) / (I_x * I_y)
#patch cropped images
patched_images = torch.cat((torch.cat(
(cropped_images[0], cropped_images[1]),
2), torch.cat((cropped_images[2], cropped_images[3]), 2)), 3)
# compute output
output = model(patched_images)
loss = sum([W_[k] * criterion(output, c_[k]) for k in range(4)])
#print(criterion(output, c_[k]))
#loss = criterion(output, target)
# measure accuracy and record loss, accuracy
acc1, acc5 = accuracy(output, target, topk=(1, 5))
losses.update(loss.item(), input.size(0))
top1.update(acc1[0].item(), input.size(0))
top5.update(acc5[0].item(), input.size(0))
# compute gradient and do SGD step
optimizer.zero_grad()
loss.backward()
optimizer.step()
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
if i % print_freq == 0:
progress.print(i)
print('==> Train Accuracy: Acc@1 {top1.avg:.3f} || Acc@5 {top5.avg:.3f}'.
format(top1=top1, top5=top5))
return top1.avg