archai.algos.darts package¶
Submodules¶
archai.algos.darts.bilevel_arch_trainer module¶
-
class
archai.algos.darts.bilevel_arch_trainer.
BilevelArchTrainer
(conf_train: archai.common.config.Config, model: archai.nas.model.Model, checkpoint: Optional[archai.common.checkpoint.CheckPoint])[source]¶ Bases:
archai.nas.arch_trainer.ArchTrainer
-
post_epoch
(train_dl: torch.utils.data.dataloader.DataLoader, val_dl: Optional[torch.utils.data.dataloader.DataLoader]) → None[source]¶
-
post_fit
(train_dl: torch.utils.data.dataloader.DataLoader, val_dl: Optional[torch.utils.data.dataloader.DataLoader]) → None[source]¶
-
pre_epoch
(train_dl: torch.utils.data.dataloader.DataLoader, val_dl: Optional[torch.utils.data.dataloader.DataLoader]) → None[source]¶
-
pre_fit
(train_dl: torch.utils.data.dataloader.DataLoader, val_dl: Optional[torch.utils.data.dataloader.DataLoader]) → None[source]¶
-
update_checkpoint
(check_point: archai.common.checkpoint.CheckPoint) → None[source]¶
-
archai.algos.darts.bilevel_optimizer module¶
-
class
archai.algos.darts.bilevel_optimizer.
BilevelOptimizer
(conf_alpha_optim: archai.common.config.Config, w_momentum: float, w_decay: float, model: archai.nas.model.Model, lossfn: torch.nn.modules.loss._Loss, device, batch_chunks: int)[source]¶ Bases:
object
archai.algos.darts.bilevel_optimizer_slow module¶
-
class
archai.algos.darts.bilevel_optimizer_slow.
BilevelOptimizer
(conf_alpha_optim: archai.common.config.Config, w_momentum: float, w_decay: float, model: archai.nas.model.Model, lossfn: torch.nn.modules.loss._Loss)[source]¶ Bases:
object
archai.algos.darts.darts_exp_runner module¶
-
class
archai.algos.darts.darts_exp_runner.
DartsExperimentRunner
(config_filename: str, base_name: str, clean_expdir=False)[source]¶ Bases:
archai.nas.exp_runner.ExperimentRunner
-
model_desc_builder
() → archai.algos.darts.darts_model_desc_builder.DartsModelDescBuilder[source]¶
-
archai.algos.darts.darts_model_desc_builder module¶
-
class
archai.algos.darts.darts_model_desc_builder.
DartsModelDescBuilder
[source]¶ Bases:
archai.nas.model_desc_builder.ModelDescBuilder
-
build_nodes
(stem_shapes: List[List[int]], conf_cell: archai.common.config.Config, cell_index: int, cell_type: archai.nas.model_desc.CellType, node_count: int, in_shape: List[int], out_shape: List[int]) → Tuple[List[List[int]], List[archai.nas.model_desc.NodeDesc]][source]¶
-
pre_build
(conf_model_desc: archai.common.config.Config) → None[source]¶
-
archai.algos.darts.mixed_op module¶
-
class
archai.algos.darts.mixed_op.
MixedOp
(op_desc: archai.nas.model_desc.OpDesc, arch_params: Optional[archai.nas.arch_params.ArchParams], affine: bool)[source]¶ Bases:
archai.nas.operations.Op
The output of MixedOp is weighted output of all allowed primitives.
-
PRIMITIVES
= ['max_pool_3x3', 'avg_pool_3x3', 'skip_connect', 'sep_conv_3x3', 'sep_conv_5x5', 'dil_conv_3x3', 'dil_conv_5x5', 'none']¶
-
finalize
() → Tuple[archai.nas.model_desc.OpDesc, Optional[float]][source]¶ for trainable op, return final op and its rank
-
forward
(x)[source]¶ Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
-
ops
() → Iterator[Tuple[archai.nas.operations.Op, float]][source]¶ Return contituent ops, if this op is primitive just return self
-