SYMBOL INDEX (128 symbols across 22 files)

FILE: analytic/ACIL.py
  class ACIL (line 28) | class ACIL(torch.nn.Module):
    method __init__ (line 29) | def __init__(
    method feature_expansion (line 49) | def feature_expansion(self, X: torch.Tensor) -> torch.Tensor:
    method forward (line 53) | def forward(self, X: torch.Tensor) -> torch.Tensor:
    method fit (line 57) | def fit(self, X: torch.Tensor, y: torch.Tensor, *args, **kwargs) -> None:
    method update (line 63) | def update(self) -> None:
  class ACILLearner (line 67) | class ACILLearner(Learner):
    method __init__ (line 74) | def __init__(
    method base_training (line 90) | def base_training(
    method make_model (line 218) | def make_model(self) -> None:
    method learn (line 230) | def learn(
    method before_validation (line 242) | def before_validation(self) -> None:
    method inference (line 245) | def inference(self, X: torch.Tensor) -> torch.Tensor:
    method wrap_data_parallel (line 249) | def wrap_data_parallel(self, model: torch.nn.Module) -> torch.nn.Module:

FILE: analytic/AEFOCL.py
  class AEFOCL (line 20) | class AEFOCL(ACIL):
    method __init__ (line 30) | def __init__(
    method fit (line 60) | def fit(self, X: torch.Tensor, y: torch.Tensor, *args, **kwargs) -> None:
    method update (line 90) | def update(self) -> None:
    method proto_mean (line 124) | def proto_mean(self) -> torch.Tensor:
    method proto_std (line 128) | def proto_std(self) -> torch.Tensor:
  class AEFOCLLearner (line 137) | class AEFOCLLearner(ACILLearner):
    method make_model (line 147) | def make_model(self) -> None:

FILE: analytic/AIR.py
  class AIR (line 18) | class AIR(ACIL):
    method fit (line 19) | def fit(self, X: torch.Tensor, y: torch.Tensor, *args, **kwargs) -> None:
  class AIRLearner (line 24) | class AIRLearner(ACILLearner):
    method make_model (line 25) | def make_model(self) -> None:
  class GeneralizedAIRLearner (line 37) | class GeneralizedAIRLearner(AIRLearner):

FILE: analytic/AnalyticLinear.py
  class AnalyticLinear (line 29) | class AnalyticLinear(torch.nn.Linear, metaclass=ABCMeta):
    method __init__ (line 30) | def __init__(
    method forward (line 51) | def forward(self, X: torch.Tensor) -> torch.Tensor:
    method in_features (line 58) | def in_features(self) -> int:
    method out_features (line 64) | def out_features(self) -> int:
    method reset_parameters (line 67) | def reset_parameters(self) -> None:
    method fit (line 72) | def fit(self, X: torch.Tensor, Y: torch.Tensor) -> None:
    method update (line 75) | def update(self) -> None:
  class RecursiveLinear (line 83) | class RecursiveLinear(AnalyticLinear):
    method __init__ (line 84) | def __init__(
    method fit (line 101) | def fit(self, X: torch.Tensor, Y: torch.Tensor) -> None:
  class GeneralizedARM (line 131) | class GeneralizedARM(AnalyticLinear):
    method __init__ (line 134) | def __init__(
    method out_features (line 157) | def out_features(self) -> int:
    method fit (line 161) | def fit(self, X: torch.Tensor, y: torch.Tensor) -> None:
    method update (line 202) | def update(self):

FILE: analytic/Buffer.py
  class Buffer (line 28) | class Buffer(torch.nn.Module, metaclass=ABCMeta):
    method __init__ (line 29) | def __init__(self) -> None:
    method forward (line 33) | def forward(self, X: torch.Tensor) -> torch.Tensor:
  class RandomBuffer (line 37) | class RandomBuffer(torch.nn.Linear, Buffer):
    method __init__ (line 38) | def __init__(
    method forward (line 66) | def forward(self, X: torch.Tensor) -> torch.Tensor:
  class GaussianKernel (line 71) | class GaussianKernel(Buffer):
    method __init__ (line 72) | def __init__(
    method forward (line 86) | def forward(self, X: torch.Tensor) -> torch.Tensor:
    method init (line 90) | def init(self, X: torch.Tensor, size: Optional[int] = None) -> None:

FILE: analytic/DSAL.py
  class DSAL (line 19) | class DSAL(torch.nn.Module):
    method __init__ (line 20) | def __init__(
    method forward (line 54) | def forward(self, X: torch.Tensor) -> torch.Tensor:
    method fit (line 61) | def fit(self, X: torch.Tensor, y: torch.Tensor, increase_size: int) ->...
    method update (line 80) | def update(self) -> None:
  class DSALLearner (line 85) | class DSALLearner(ACILLearner):
    method __init__ (line 86) | def __init__(
    method make_model (line 98) | def make_model(self) -> None:

FILE: analytic/GKEAL.py
  class GKEAL (line 26) | class GKEAL(ACIL):
    method __init__ (line 27) | def __init__(
  class GKEALLearner (line 49) | class GKEALLearner(ACILLearner):
    method __init__ (line 50) | def __init__(
    method make_model (line 65) | def make_model(self) -> None:
    method learn (line 78) | def learn(

FILE: analytic/Learner.py
  class Learner (line 11) | class Learner(metaclass=ABCMeta):
    method __init__ (line 12) | def __init__(
    method base_training (line 28) | def base_training(
    method learn (line 37) | def learn(
    method before_validation (line 46) | def before_validation() -> None:
    method inference (line 50) | def inference(self, X: torch.Tensor) -> torch.Tensor:
    method save_object (line 53) | def save_object(self, model, file_name: str) -> None:
    method __call__ (line 56) | def __call__(self, X: torch.Tensor) -> torch.Tensor:

FILE: config.py
  function load_args (line 249) | def load_args() -> Dict[str, Any]:

FILE: datasets/CIFAR.py
  class CIFAR10_ (line 11) | class CIFAR10_(DatasetWrapper[Tuple[Tensor, int]]):
    method __init__ (line 37) | def __init__(
  class CIFAR100_ (line 58) | class CIFAR100_(DatasetWrapper[Tuple[Tensor, int]]):
    method __init__ (line 85) | def __init__(

FILE: datasets/DatasetWrapper.py
  class DatasetWrapper (line 15) | class DatasetWrapper(Dataset[T_co], metaclass=ABCMeta):
    method __init__ (line 19) | def __init__(
    method __getitem__ (line 51) | def __getitem__(self, index: int) -> T_co:
    method _subset (line 54) | def _subset(self, label_begin: int, label_end: int) -> Subset[T_co]:
    method subset_at_phase (line 58) | def subset_at_phase(self, phase: int) -> Subset[T_co]:
    method subset_until_phase (line 66) | def subset_until_phase(self, phase: int) -> Subset[T_co]:

FILE: datasets/Features.py
  class Features (line 10) | class Features(DatasetWrapper[tuple[torch.Tensor, torch.LongTensor]]):
    method __init__ (line 14) | def __init__(

FILE: datasets/ImageNet.py
  class ImageNet_ (line 10) | class ImageNet_(DatasetWrapper[Tuple[torch.Tensor, int]]):
    method __init__ (line 41) | def __init__(

FILE: datasets/MNIST.py
  class MNIST_ (line 10) | class MNIST_(DatasetWrapper[tuple[Tensor, int]]):
    method __init__ (line 24) | def __init__(

FILE: datasets/__init__.py
  function load_dataset (line 31) | def load_dataset(

FILE: main.py
  function make_dataloader (line 15) | def make_dataloader(
  function check_cache_features (line 44) | def check_cache_features(root: str) -> bool:
  function cache_features (line 53) | def cache_features(
  function main (line 69) | def main(args: Dict[str, Any]):

FILE: models/CifarResNet.py
  function _weights_init (line 48) | def _weights_init(m):
  class ShortcutA (line 53) | class ShortcutA(nn.Module):
    method __init__ (line 54) | def __init__(self, planes) -> None:
    method forward (line 58) | def forward(self, x: torch.Tensor) -> torch.Tensor:
  class BasicBlock (line 67) | class BasicBlock(nn.Module):
    method __init__ (line 70) | def __init__(self, in_planes, planes, stride=1, option="A"):
    method forward (line 100) | def forward(self, x):
  class CifarResNet (line 108) | class CifarResNet(nn.Module):
    method __init__ (line 109) | def __init__(self, block, num_blocks, num_classes=10):
    method _make_layer (line 122) | def _make_layer(self, block, planes, num_blocks, stride):
    method forward (line 131) | def forward(self, x):
  function resnet20 (line 142) | def resnet20(num_classes=10):
  function resnet32 (line 146) | def resnet32(num_classes=10):
  function resnet44 (line 150) | def resnet44(num_classes=10):
  function resnet56 (line 154) | def resnet56(num_classes=10):
  function resnet110 (line 158) | def resnet110(num_classes=10):
  function resnet1202 (line 162) | def resnet1202(num_classes=10):
  function calc_num_params (line 166) | def calc_num_params(model: torch.nn.Module) -> int:

FILE: models/__init__.py
  function load_backbone (line 102) | def load_backbone(

FILE: utils/metrics.py
  class ClassificationMeter (line 6) | class ClassificationMeter:
    method __init__ (line 7) | def __init__(self, num_classes: int, record_logits: bool = False) -> N...
    method record (line 17) | def record(self, y_true: torch.Tensor, logits: torch.Tensor) -> None:
    method accuracy (line 37) | def accuracy(self) -> float:
    method balanced_accuracy (line 41) | def balanced_accuracy(self) -> float:
    method f1_micro (line 48) | def f1_micro(self) -> float:
    method f1_macro (line 53) | def f1_macro(self) -> float:
    method accuracy5 (line 58) | def accuracy5(self) -> float:
    method loss (line 62) | def loss(self) -> float:

FILE: utils/set_determinism.py
  function set_determinism (line 9) | def set_determinism(seed: int) -> None:

FILE: utils/set_weight_decay.py
  function set_weight_decay (line 7) | def set_weight_decay(

FILE: utils/validate.py
  function validate (line 9) | def validate(