mmedit.engine.runner

Package Contents

Classes

GenTestLoop	Validation loop for generative models. This class support evaluate
GenValLoop	Validation loop for generative models. This class support evaluate
GenLogProcessor	GenLogProcessor inherits from mmengine.runner.LogProcessor and
MultiTestLoop	Loop for validation multi-datasets.
MultiValLoop	Loop for validation multi-datasets.

class mmedit.engine.runner.GenTestLoop(runner: mmengine.runner.Runner, dataloader: Union[torch.utils.data.DataLoader, Dict], evaluator: Union[mmengine.evaluator.Evaluator, Dict, List])

Bases: mmengine.runner.TestLoop

Validation loop for generative models. This class support evaluate metrics with different sample mode.

参数

• runner (Runner) – A reference of runner.

• dataloader (Dataloader or dict) – A dataloader object or a dict to build a dataloader.

• evaluator (Evaluator or dict or list) – Used for computing metrics.

run()

Launch validation. The evaluation process consists of four steps.

1. Prepare pre-calculated items for all metrics by calling self.evaluator.prepare_metrics().

2. Get a list of metrics-sampler pair. Each pair contains a list of metrics with the same sampler mode and a shared sampler.

3. Generate images for the each metrics group. Loop for elements in each sampler and feed to the model as input by calling self.run_iter().

4. Evaluate all metrics by calling self.evaluator.evaluate().

run_iter(idx, data_batch: dict, metrics: Sequence[mmengine.evaluator.BaseMetric])

Iterate one mini-batch and feed the output to corresponding metrics.

参数

• idx (int) – Current idx for the input data.

• data_batch (dict) – Batch of data from dataloader.

• metrics (Sequence[BaseMetric]) – Specific metrics to evaluate.

class mmedit.engine.runner.GenValLoop(runner: mmengine.runner.Runner, dataloader: Union[torch.utils.data.DataLoader, Dict], evaluator: Union[mmengine.evaluator.Evaluator, Dict, List])

Bases: mmengine.runner.ValLoop

Validation loop for generative models. This class support evaluate metrics with different sample mode.

参数

• runner (Runner) – A reference of runner.

• dataloader (Dataloader or dict) – A dataloader object or a dict to build a dataloader.

• evaluator (Evaluator or dict or list) – Used for computing metrics.

run()

Launch validation. The evaluation process consists of four steps.

1. Prepare pre-calculated items for all metrics by calling self.evaluator.prepare_metrics().

2. Get a list of metrics-sampler pair. Each pair contains a list of metrics with the same sampler mode and a shared sampler.

3. Generate images for the each metrics group. Loop for elements in each sampler and feed to the model as input by calling self.run_iter().

4. Evaluate all metrics by calling self.evaluator.evaluate().

run_iter(idx, data_batch: dict, metrics: Sequence[mmengine.evaluator.BaseMetric])

Iterate one mini-batch and feed the output to corresponding metrics.

参数

• idx (int) – Current idx for the input data.

• data_batch (dict) – Batch of data from dataloader.

• metrics (Sequence[BaseMetric]) – Specific metrics to evaluate.

class mmedit.engine.runner.GenLogProcessor(window_size=10, by_epoch=True, custom_cfg: Optional[List[dict]] = None, num_digits: int = 4)

Bases: mmengine.runner.LogProcessor

GenLogProcessor inherits from mmengine.runner.LogProcessor and overwrites self.get_log_after_iter().

This log processor should be used along with mmedit.engine.runner.GenValLoop and mmedit.engine.runner.GenTestLoop.

get_log_after_iter(runner, batch_idx: int, mode: str) → Tuple[dict, str]

Format log string after training, validation or testing epoch.

If mode is in ‘val’ or ‘test’, we use runner.val_loop.total_length and runner.test_loop.total_length as the total number of iterations shown in log. If you want to know how total_length is calculated, please refers to mmedit.engine.runner.GenValLoop.run() and mmedit.engine.runner.GenTestLoop.run().

参数

• runner (Runner) – The runner of training phase.

• batch_idx (int) – The index of the current batch in the current loop.

• mode (str) – Current mode of runner, train, test or val.

返回

Formatted log dict/string which will be

recorded by runner.message_hub and runner.visualizer.

返回类型

Tuple(dict, str)

get_log_after_epoch(runner, batch_idx: int, mode: str) → Tuple[dict, str]

Format log string after validation or testing epoch.

We use runner.val_loop.total_length and runner.test_loop.total_length as the total number of iterations shown in log. If you want to know how total_length is calculated, please refers to mmedit.engine.runner.GenValLoop.run() and mmedit.engine.runner.GenTestLoop.run().

参数

• runner (Runner) – The runner of validation/testing phase.

• batch_idx (int) – The index of the current batch in the current loop.

• mode (str) – Current mode of runner.

返回

Formatted log dict/string which will be recorded by runner.message_hub and runner.visualizer.

返回类型

Tuple(dict, str)

class mmedit.engine.runner.MultiTestLoop(runner, dataloader: Union[torch.utils.data.DataLoader, Dict], evaluator: Union[mmengine.evaluator.Evaluator, Dict, List], fp16: bool = False)

Bases: mmengine.runner.base_loop.BaseLoop

Loop for validation multi-datasets.

参数

• runner (Runner) – A reference of runner.

• dataloader (Dataloader or dict) – A dataloader object or a dict to build a dataloader.

• evaluator (Evaluator or dict or list) – Used for computing metrics.

• fp16 (bool) – Whether to enable fp16 validation. Defaults to False.

run()

Launch test.

run_iter(idx: int, data_batch: Sequence[dict])

Iterate one mini-batch.

参数

• idx (int) – The index of the current batch in the loop.

• data_batch (Sequence[dict]) – Batch of data from dataloader.

class mmedit.engine.runner.MultiValLoop(runner, dataloader: Union[torch.utils.data.DataLoader, Dict], evaluator: Union[mmengine.evaluator.Evaluator, Dict, List], fp16: bool = False)

Bases: mmengine.runner.base_loop.BaseLoop

Loop for validation multi-datasets.

参数

• runner (Runner) – A reference of runner.

• dataloader (list[Dataloader or dic]) – A dataloader object or a dict to build a dataloader.

• evaluator (list[]) – Used for computing metrics.

• fp16 (bool) – Whether to enable fp16 validation. Defaults to False.

run()

Launch validation.

run_iter(idx: int, data_batch: Sequence[dict])

Iterate one mini-batch.

参数

• idx (int) – The index of the current batch in the loop.

• data_batch (Sequence[dict]) – Batch of data from dataloader.