class ActiveLearning(torch.nn.Module):
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 train_on_loader(self, loader: DataLoader):
self.wrapper.load_state_dict(self.initial_weights)
if self.active_dataset is None:
self.active_dataset = loader.dataset
if self.active_dataset_settings is not None:
self.active_dataset.load_state_dict(
self.active_dataset_settings)
self.loop.dataset = self.active_dataset
self.criterion.train()
self.wrapper.train_on_dataset(self.active_dataset,
self.optimizer,
self.batch_size,
epoch=self.learning_epoch,
use_cuda=True)
metrics = self.wrapper.metrics
return self._format_metrics(metrics, 'train')
def val_on_loader(self, loader, savedir=None):
val_data = loader.dataset
self.loop.step()
self.criterion.eval()
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 on_train_end(self, savedir, epoch):
h5_path = pjoin(savedir, 'ckpt.h5')
labelled = self.active_dataset.state_dict()['labelled']
with h5py.File(h5_path, 'a') as f:
if f'epoch_{epoch}' not in f:
g = f.create_group(f'epoch_{epoch}')
g.create_dataset('labelled', data=labelled.astype(np.bool))
def _format_metrics(self, metrics, step):
mets = {k: v.value for k, v in metrics.items() if step in k}
mets_unpacked = {}
for k, v in mets.items():
if isinstance(v, float):
mets_unpacked[k] = v
elif isinstance(v, np.ndarray):
mets_unpacked[k] = v.mean()
else:
mets_unpacked.update(
{f"{k}_{ki}": np.mean(vi)
for ki, vi in v.items()})
return mets_unpacked
def get_state_dict(self):
state = {}
state["model"] = self.backbone.state_dict()
state["optimizer"] = self.optimizer.state_dict()
if self.active_dataset is None:
state['dataset'] = None
else:
state["dataset"] = self.active_dataset.state_dict()
return state
def set_state_dict(self, state_dict):
self.backbone.load_state_dict(state_dict["model"])
self.optimizer.load_state_dict(state_dict["optimizer"])
self.active_dataset_settings = state_dict["dataset"]
if self.active_dataset is not None:
self.active_dataset.load_state_dict(self.active_dataset_settings)
class DirichletCalibrator(object):
"""
Adding a linear layer to a classifier model after the model is
trained and train this new layer until convergence.
Together with the linear layer, the model is now calibrated.
Source: https://arxiv.org/abs/1910.12656
Code inspired from: https://github.com/dirichletcal/experiments_neurips
References:
@article{kullbeyond,
title={Beyond temperature scaling: Obtaining well-calibrated multi-class
probabilities with Dirichlet calibration Supplementary material},
author={Kull, Meelis and Perello-Nieto,
Miquel and K{\"a}ngsepp, Markus and Silva Filho,
Telmo and Song, Hao and Flach, Peter}
}
Args:
wrapper (ModelWrapper): Provides training and testing methods.
num_classes (int): Number of classes in classification task.
lr (float): Learning rate.
reg_factor (float): Regularization factor for the linear layer weights.
mu (float): Regularization factor for the linear layer biases.
If not given, will be initialized by "l".
"""
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 l2_reg(self):
"""Using trainable layer's parameters for l2 regularization.
Returns:
The regularization term for the linear layer.
"""
weight_p, bias_p = self.dirichlet_linear.parameters()
w_l2_factor = weight_p.norm(2)
b_l2_factor = bias_p.norm(2)
return self.reg_factor * w_l2_factor + self.mu * b_l2_factor
def calibrate(self,
train_set: Dataset,
test_set: Dataset,
batch_size: int,
epoch: int,
use_cuda: bool,
double_fit: bool = False,
**kwargs):
"""
Training the linear layer given a training set and a validation set.
The training set should be different from what model is trained on.
Args:
train_set (Dataset): The training set.
test_set (Dataset): The validation set.
batch_size (int): Batch size used.
epoch (int): Number of epochs to train the linear layer for.
use_cuda (bool): If "True", will use GPU.
double_fit (bool): If "True" would fit twice on the train set.
kwargs (dict): Rest of parameters for baal.ModelWrapper.train_and_test_on_dataset().
Returns:
loss_history (list[float]): List of loss values for each epoch.
model.state_dict (dict): Model weights.
"""
# reinitialize the dirichlet calibration layer
self.dirichlet_linear.weight.data.copy_(
torch.eye(self.dirichlet_linear.weight.shape[0]))
self.dirichlet_linear.bias.data.copy_(
torch.zeros(*self.dirichlet_linear.bias.shape))
if use_cuda:
self.dirichlet_linear.cuda()
optimizer = Adam(self.dirichlet_linear.parameters(), lr=self.lr)
loss_history, weights = self.wrapper.train_and_test_on_datasets(
train_set,
test_set,
optimizer,
batch_size,
epoch,
use_cuda,
regularizer=self.l2_reg,
return_best_weights=True,
patience=None,
**kwargs)
self.model.load_state_dict(weights)
if double_fit:
lr = self.lr / 10
optimizer = Adam(self.dirichlet_linear.parameters(), lr=lr)
loss_history, weights = self.wrapper.train_and_test_on_datasets(
train_set,
test_set,
optimizer,
batch_size,
epoch,
use_cuda,
regularizer=self.l2_reg,
return_best_weights=True,
patience=None,
**kwargs)
self.model.load_state_dict(weights)
return loss_history, self.model.state_dict()
@property
def calibrated_model(self):
return self.model
@property
def metrics(self):
return self.wrapper.metrics