def segmentation_task(tmpdir):
model = nn.Sequential(nn.Conv2d(3, 32, 3), nn.ReLU(), nn.Conv2d(32, 64, 3),
nn.MaxPool2d(2), nn.Conv2d(64, 64, 3), Dropout2d(),
nn.ConvTranspose2d(64, 10, 3, 1))
model = ModelWrapper(model, nn.CrossEntropyLoss())
test = datasets.CIFAR10(tmpdir,
train=False,
download=True,
transform=transforms.ToTensor())
return model, test
def classification_task(tmpdir):
model = nn.Sequential(nn.Conv2d(3, 32, 3), nn.ReLU(), nn.Conv2d(32, 64, 3),
nn.MaxPool2d(2), nn.AdaptiveAvgPool2d((7, 7)),
Flatten(), nn.Linear(7 * 7 * 64, 128), Dropout(),
nn.Linear(128, 10))
model = ModelWrapper(model, nn.CrossEntropyLoss())
test = datasets.CIFAR10(tmpdir,
train=False,
download=True,
transform=transforms.ToTensor())
return model, test
def segmentation_task(tmpdir):
model = nn.Sequential(nn.Conv2d(3, 32, 3),
nn.ReLU(),
nn.Conv2d(32, 64, 3),
nn.MaxPool2d(2),
nn.Conv2d(64, 64, 3),
Dropout2d(),
nn.ConvTranspose2d(64, 10, 3, 1)
)
model = ModelWrapper(model, nn.CrossEntropyLoss())
test = SimpleDataset()
return model, test
def __init__(self, exp_dict):
super().__init__()
self.backbone = models.vgg16(
pretrained=exp_dict["imagenet_pretraining"], progress=True)
num_ftrs = self.backbone.classifier[-1].in_features
self.backbone.classifier[-1] = torch.nn.Linear(num_ftrs,
exp_dict["num_classes"])
self.backbone = patch_module(self.backbone)
self.initial_weights = deepcopy(self.backbone.state_dict())
self.backbone.cuda()
self.batch_size = exp_dict['batch_size']
self.calibrate = exp_dict.get('calibrate', False)
self.learning_epoch = exp_dict['learning_epoch']
self.optimizer = torch.optim.SGD(self.backbone.parameters(),
lr=exp_dict['lr'],
weight_decay=5e-4,
momentum=0.9,
nesterov=True)
self.criterion = CrossEntropyLoss()
shuffle_prop = exp_dict.get('shuffle_prop', 0.0)
max_sample = -1
self.heuristic = get_heuristic(exp_dict['heuristic'],
shuffle_prop=shuffle_prop)
self.wrapper = ModelWrapper(self.backbone, criterion=self.criterion)
self.wrapper.add_metric(
'cls_report',
lambda: ClassificationReport(exp_dict["num_classes"]))
self.wrapper.add_metric('accuracy', lambda: Accuracy())
self.loop = ActiveLearningLoop(None,
self.wrapper.predict_on_dataset,
heuristic=self.heuristic,
ndata_to_label=exp_dict['query_size'],
batch_size=self.batch_size,
iterations=exp_dict['iterations'],
use_cuda=True,
max_sample=max_sample)
self.calib_set = get_dataset('calib', exp_dict['dataset'])
self.valid_set = get_dataset('val', exp_dict['dataset'])
self.calibrator = DirichletCalibrator(
self.wrapper,
exp_dict["num_classes"],
lr=0.001,
reg_factor=exp_dict['reg_factor'],
mu=exp_dict['mu'])
self.active_dataset = None
self.active_dataset_settings = None
def classification_task(tmpdir):
model = nn.Sequential(nn.Conv2d(3, 32, 3),
nn.ReLU(),
nn.Conv2d(32, 64, 3),
nn.MaxPool2d(2),
nn.AdaptiveAvgPool2d((7, 7)),
Flatten(),
nn.Linear(7 * 7 * 64, 128),
Dropout(),
nn.Linear(128, 10)
)
model = ModelWrapper(model, nn.CrossEntropyLoss())
test = SimpleDataset()
return model, test
def __init__(self,
wrapper: ModelWrapper,
num_classes: int,
lr: float,
reg_factor: float,
mu: float = None):
self.num_classes = num_classes
self.criterion = nn.CrossEntropyLoss()
self.lr = lr
self.reg_factor = reg_factor
self.mu = mu or reg_factor
self.dirichlet_linear = nn.Linear(self.num_classes, self.num_classes)
self.model = nn.Sequential(wrapper.model, self.dirichlet_linear)
self.wrapper = ModelWrapper(self.model, self.criterion)
self.wrapper.add_metric("ece", lambda: ECE())
self.wrapper.add_metric("ece", lambda: ECE_PerCLs(num_classes))
def val_on_loader(self, loader, savedir=None):
val_data = loader.dataset
if self.calibrate:
self.calibrator.calibrate(self.calib_set,
self.valid_set,
batch_size=16,
epoch=10,
use_cuda=True,
double_fit=True)
calibrated_model = ModelWrapper(self.calibrator.calibrated_model,
None)
self.loop.get_probabilities = calibrated_model.predict_on_dataset
self.loop.step()
self.wrapper.test_on_dataset(val_data,
batch_size=self.batch_size,
use_cuda=True,
average_predictions=20)
metrics = self.wrapper.metrics
mets = self._format_metrics(metrics, 'test')
mets.update({'num_samples': len(self.active_dataset)})
return mets
def main():
args = parse_args()
batch_size = args.batch_size
use_cuda = torch.cuda.is_available()
hyperparams = vars(args)
pprint(hyperparams)
active_set, test_set = get_datasets(hyperparams["initial_pool"],
hyperparams["data_path"])
# We will use the FocalLoss
criterion = FocalLoss(gamma=2, alpha=0.25)
# Our model is a simple Unet
model = smp.Unet(
encoder_name="resnext50_32x4d",
encoder_depth=5,
encoder_weights="imagenet",
decoder_use_batchnorm=False,
classes=len(pascal_voc_ids),
)
# Add a Dropout layerto use MC-Dropout
add_dropout(model, classes=len(pascal_voc_ids), activation=None)
# This will enable Dropout at test time.
model = MCDropoutModule(model)
# Put everything on GPU.
if use_cuda:
model.cuda()
# Make an optimizer
optimizer = optim.SGD(model.parameters(),
lr=hyperparams["lr"],
momentum=0.9,
weight_decay=5e-4)
# Keep a copy of the original weights
initial_weights = deepcopy(model.state_dict())
# Add metrics
model = ModelWrapper(model, criterion)
model.add_metric("cls_report",
lambda: ClassificationReport(len(pascal_voc_ids)))
# Which heuristic you want to use?
# We will use our custom reduction function.
heuristic = get_heuristic(hyperparams["heuristic"], reduction=mean_regions)
# The ALLoop is in charge of predicting the uncertainty and
loop = ActiveLearningLoop(
active_set,
model.predict_on_dataset_generator,
heuristic=heuristic,
query_size=hyperparams["query_size"],
# Instead of predicting on the entire pool, only a subset is used
max_sample=1000,
batch_size=batch_size,
iterations=hyperparams["iterations"],
use_cuda=use_cuda,
)
acc = []
for epoch in tqdm(range(args.al_step)):
# Following Gal et al. 2016, we reset the weights.
model.load_state_dict(initial_weights)
# Train 50 epochs before sampling.
model.train_on_dataset(active_set, optimizer, batch_size,
hyperparams["learning_epoch"], use_cuda)
# Validation!
model.test_on_dataset(test_set, batch_size, use_cuda)
should_continue = loop.step()
metrics = model.metrics
val_loss = metrics["test_loss"].value
logs = {
"val": val_loss,
"epoch": epoch,
"train": metrics["train_loss"].value,
"labeled_data": active_set.labelled,
"Next Training set size": len(active_set),
"cls_report": metrics["test_cls_report"].value,
}
pprint(logs)
acc.append(logs)
if not should_continue:
break
def main():
args = parse_args()
use_cuda = torch.cuda.is_available()
torch.backends.cudnn.benchmark = True
random.seed(1337)
torch.manual_seed(1337)
if not use_cuda:
print("warning, the experiments would take ages to run on cpu")
hyperparams = vars(args)
active_set, test_set = get_datasets(hyperparams["initial_pool"])
heuristic = get_heuristic(hyperparams["heuristic"],
hyperparams["shuffle_prop"])
criterion = CrossEntropyLoss()
model = vgg16(pretrained=False, num_classes=10)
weights = load_state_dict_from_url(
"https://download.pytorch.org/models/vgg16-397923af.pth")
weights = {k: v for k, v in weights.items() if "classifier.6" not in k}
model.load_state_dict(weights, strict=False)
# change dropout layer to MCDropout
model = patch_module(model)
if use_cuda:
model.cuda()
optimizer = optim.SGD(model.parameters(),
lr=hyperparams["lr"],
momentum=0.9)
# Wraps the model into a usable API.
model = ModelWrapper(model, criterion)
logs = {}
logs["epoch"] = 0
# for prediction we use a smaller batchsize
# since it is slower
active_loop = ActiveLearningLoop(
active_set,
model.predict_on_dataset,
heuristic,
hyperparams.get("query_size", 1),
batch_size=10,
iterations=hyperparams["iterations"],
use_cuda=use_cuda,
)
# We will reset the weights at each active learning step.
init_weights = deepcopy(model.state_dict())
for epoch in tqdm(range(args.epoch)):
# Load the initial weights.
model.load_state_dict(init_weights)
model.train_on_dataset(
active_set,
optimizer,
hyperparams["batch_size"],
hyperparams["learning_epoch"],
use_cuda,
)
# Validation!
model.test_on_dataset(test_set, hyperparams["batch_size"], use_cuda)
metrics = model.metrics
should_continue = active_loop.step()
if not should_continue:
break
val_loss = metrics["test_loss"].value
logs = {
"val": val_loss,
"epoch": epoch,
"train": metrics["train_loss"].value,
"labeled_data": active_set.labelled,
"Next Training set size": len(active_set),
}
print(logs)
train_ds, pool_specifics={"transform": test_transform})
al_dataset.label_randomly(200) # Start with 200 items labelled.
# Creates an MLP to classify MNIST
model = nn.Sequential(
nn.Flatten(),
nn.Linear(784, 512),
nn.Dropout(),
nn.Linear(512, 512),
nn.Dropout(),
nn.Linear(512, 10),
)
model = patch_module(model) # Set dropout layers for MC-Dropout.
if use_cuda:
model = model.cuda()
wrapper = ModelWrapper(model=model, criterion=nn.CrossEntropyLoss())
optimizer = optim.SGD(model.parameters(),
lr=0.001,
momentum=0.9,
weight_decay=5e-4)
# We will use BALD as our heuristic as it is a great tradeoff between performance and efficiency.
bald = BALD()
# Setup our active learning loop for our experiments
al_loop = ActiveLearningLoop(
dataset=al_dataset,
get_probabilities=wrapper.predict_on_dataset,
heuristic=bald,
query_size=100, # We will label 100 examples per step.
# KWARGS for predict_on_dataset
iterations=20, # 20 sampling for MC-Dropout
# You might need to add the path to the list of python system paths.
al_dataset = ActiveLearningDataset(FeatureDataset("./data/CASP.csv"))
test_ds = FeatureDataset("./data/CASP.csv", split="test")
al_dataset.label_randomly(1000) # Start with 1000 items labelled.
# Creates an MLP to classify MNIST
model = nn.Sequential(nn.Flatten(), nn.Linear(9, 16), nn.Dropout(),
nn.Linear(16, 8), nn.ReLU(), nn.Linear(8, 1))
model = patch_module(model) # Set dropout layers for MC-Dropout.
model.apply(weight_init_normal)
if use_cuda:
model = model.cuda()
wrapper = ModelWrapper(model=model, criterion=nn.L1Loss())
optimizer = optim.SGD(model.parameters(),
lr=0.001,
momentum=0.9,
weight_decay=5e-4)
# We will use Variance as our heuristic for regression problems.
variance = Variance()
# Setup our active learning loop for our experiments
al_loop = ActiveLearningLoop(
dataset=al_dataset,
get_probabilities=wrapper.predict_on_dataset,
heuristic=variance,
query_size=250, # We will label 20 examples per step.
# KWARGS for predict_on_dataset