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]
pre_step(x: torch.Tensor, y: torch.Tensor) → None[source]
restore_checkpoint() → 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

load_state_dict(state_dict) → None[source]
state_dict() → dict[source]
step(x_train: torch.Tensor, y_train: torch.Tensor, x_valid: torch.Tensor, y_valid: torch.Tensor, w_optim: torch.optim.optimizer.Optimizer) → None[source]

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

load_state_dict(state_dict) → None[source]
state_dict() → dict[source]
step(x_train: torch.Tensor, y_train: torch.Tensor, x_valid: torch.Tensor, y_valid: torch.Tensor, main_optim: torch.optim.optimizer.Optimizer) → None[source]

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]
trainer_class() → Optional[Type[ArchTrainer]][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']
can_drop_path() → bool[source]
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

Module contents