def __init__(self, dataset, conf, unlabeled_indices=None):
super().__init__(dataset, conf, unlabeled_indices)
self.lossnet = lossnet.LossNet(
feature_sizes=conf["lossnet"]["feature_sizes"],
num_channels=conf["lossnet"]["num_channels"])
self.lossnet_optimizer = getattr(
optimUtils, self.conf["lossnet"]["optimizer"]["name"])(
self.lossnet.parameters(), conf["lossnet"]["optimizer"])
self.lossnet.to(self.device)
self.sampler = LossPredictionSampler(self.budget, self.model,
self.lossnet, self.device)
ADDENDUM] # ADDENDUM == 1000, 最开始的，不过好像后来逐渐每次label的data加1000
unlabeled_set = indices[ADDENDUM:]
train_loader = DataLoader(
cifar10_train,
batch_size=BATCH, # BATCH == 128, 可以改改！！
sampler=SubsetRandomSampler(
labeled_set), # 这是怎么弄得？？？好像只选了那1000个label数据来train??
pin_memory=True) # 这是干啥的？？
test_loader = DataLoader(cifar10_test, batch_size=BATCH)
dataloaders = {'train': train_loader, 'test': test_loader}
# Model
resnet18 = resnet.ResNet18(
num_classes=10).cuda() # 注意者利用的 resNet18, 还可以改成resnet很深的模型
loss_module = lossnet.LossNet().cuda()
models = {'backbone': resnet18, 'module': loss_module}
torch.backends.cudnn.benchmark = False # if True, causes cuDNN to benchmark multiple convolution algorithms
# and select the fastest.
# Active learning cycles # 主动学习
for cycle in range(CYCLES): # CYCLES:10
# Loss, criterion and scheduler (re)initialization
criterion = nn.CrossEntropyLoss(reduction='none')
optim_backbone = optim.SGD(
models['backbone'].parameters(),
lr=LR, # ??用Adam 可以嘛？？LR 才0.1, 可以改！！
momentum=MOMENTUM,
weight_decay=WDECAY)
optim_module = optim.SGD(
models['module'].parameters(),