mmfewshot.classification¶

classification.apis¶

mmfewshot.classification.apis.inference_classifier(model: torch.nn.modules.module.Module, query_img: str) → Dict[源代码]¶

Inference single image with the classifier.

参数

model (nn.Module) – The loaded classifier.
query_img (str) – The image filename.

返回

The classification results that contains: pred_score of each class.

返回类型

dict

mmfewshot.classification.apis.init_classifier(config: Union[str, mmcv.utils.config.Config], checkpoint: Optional[str] = None, device: str = 'cuda:0', options: Optional[Dict] = None) → torch.nn.modules.module.Module[源代码]¶

Prepare a few shot classifier from config file.

参数

config (str or mmcv.Config) – Config file path or the config object.
checkpoint (str | None) – Checkpoint path. If left as None, the model will not load any weights. Default: None.
device (str) – Runtime device. Default: ‘cuda:0’.
options (dict | None) – Options to override some settings in the used config. Default: None.

返回

The constructed classifier.

返回类型

nn.Module

mmfewshot.classification.apis.multi_gpu_meta_test(model: mmcv.parallel.distributed.MMDistributedDataParallel, num_test_tasks: int, support_dataloader: torch.utils.data.dataloader.DataLoader, query_dataloader: torch.utils.data.dataloader.DataLoader, test_set_dataloader: Optional[torch.utils.data.dataloader.DataLoader] = None, meta_test_cfg: Optional[Dict] = None, eval_kwargs: Optional[Dict] = None, logger: Optional[object] = None, confidence_interval: float = 0.95, show_task_results: bool = False) → Dict[源代码]¶

Distributed meta testing on multiple gpus.

During meta testing, model might be further fine-tuned or added extra parameters. While the tested model need to be restored after meta testing since meta testing can be used as the validation in the middle of training. To detach model from previous phase, the model will be copied and wrapped with MetaTestParallel. And it has full independence from the training model and will be discarded after the meta testing.

In the distributed situation, the MetaTestParallel on each GPU is also independent. The test tasks in few shot leaning usually are very small and hardly benefit from distributed acceleration. Thus, in distributed meta testing, each task is done in single GPU and each GPU is assigned a certain number of tasks. The number of test tasks for each GPU is ceil(num_test_tasks / world_size). After all GPUs finish their tasks, the results will be aggregated to get the final result.

参数

model (MMDistributedDataParallel) – Model to be meta tested.
num_test_tasks (int) – Number of meta testing tasks.
support_dataloader (DataLoader) – A PyTorch dataloader of support data.
query_dataloader (DataLoader) – A PyTorch dataloader of query data.
test_set_dataloader (DataLoader) – A PyTorch dataloader of all test data. Default: None.
meta_test_cfg (dict) – Config for meta testing. Default: None.
eval_kwargs (dict) – Any keyword argument to be used for evaluation. Default: None.
logger (logging.Logger | None) – Logger used for printing related information during evaluation. Default: None.
confidence_interval (float) – Confidence interval. Default: 0.95.
show_task_results (bool) – Whether to record the eval result of each task. Default: False.

返回

Dict of meta evaluate results, containing accuracy_mean: and accuracy_std of all test tasks.

返回类型

dict | None

mmfewshot.classification.apis.process_support_images(model: torch.nn.modules.module.Module, support_imgs: List[str], support_labels: List[str]) → None[源代码]¶

Process support images.

参数

model (nn.Module) – Classifier model.
support_imgs (list[str]) – The image filenames.
support_labels (list[str]) – The class names of support images.

mmfewshot.classification.apis.show_result_pyplot(img: str, result: Dict, fig_size: Tuple[int] = (15, 10), wait_time: int = 0, out_file: Optional[str] = None) → numpy.ndarray[源代码]¶

Visualize the classification results on the image.

参数

img (str) – Image filename.
result (dict) – The classification result.
fig_size (tuple) – Figure size of the pyplot figure. Default: (15, 10).
wait_time (int) – How many seconds to display the image. Default: 0.
out_file (str | None) – Default: None

返回

pyplot figure.

返回类型

np.ndarray

mmfewshot.classification.apis.single_gpu_meta_test(model: Union[mmcv.parallel.data_parallel.MMDataParallel, torch.nn.modules.module.Module], num_test_tasks: int, support_dataloader: torch.utils.data.dataloader.DataLoader, query_dataloader: torch.utils.data.dataloader.DataLoader, test_set_dataloader: Optional[torch.utils.data.dataloader.DataLoader] = None, meta_test_cfg: Optional[Dict] = None, eval_kwargs: Optional[Dict] = None, logger: Optional[object] = None, confidence_interval: float = 0.95, show_task_results: bool = False) → Dict[源代码]¶

Meta testing on single gpu.

During meta testing, model might be further fine-tuned or added extra parameters. While the tested model need to be restored after meta testing since meta testing can be used as the validation in the middle of training. To detach model from previous phase, the model will be copied and wrapped with MetaTestParallel. And it has full independence from the training model and will be discarded after the meta testing.

参数

model (MMDataParallel | nn.Module) – Model to be meta tested.
num_test_tasks (int) – Number of meta testing tasks.
support_dataloader (DataLoader) – A PyTorch dataloader of support data and it is used to fetch support data for each task.
query_dataloader (DataLoader) – A PyTorch dataloader of query data and it is used to fetch query data for each task.
test_set_dataloader (DataLoader) – A PyTorch dataloader of all test data and it is used for feature extraction from whole dataset to accelerate the testing. Default: None.
meta_test_cfg (dict) – Config for meta testing. Default: None.
eval_kwargs (dict) – Any keyword argument to be used for evaluation. Default: None.
logger (logging.Logger | None) – Logger used for printing related information during evaluation. Default: None.
confidence_interval (float) – Confidence interval. Default: 0.95.
show_task_results (bool) – Whether to record the eval result of each task. Default: False.

返回

Dict of meta evaluate results, containing accuracy_mean: and accuracy_std of all test tasks.

返回类型

dict

mmfewshot.classification.apis.test_single_task(model: mmfewshot.classification.utils.meta_test_parallel.MetaTestParallel, support_dataloader: torch.utils.data.dataloader.DataLoader, query_dataloader: torch.utils.data.dataloader.DataLoader, meta_test_cfg: Dict)[源代码]¶

Test a single task.

A task has two stages: handling the support set and predicting the query set. In stage one, it currently supports fine-tune based and metric based methods. In stage two, it simply forward the query set and gather all the results.

参数

model (MetaTestParallel) – Model to be meta tested.
support_dataloader (DataLoader) – A PyTorch dataloader of support data.
query_dataloader (DataLoader) – A PyTorch dataloader of query data.
meta_test_cfg (dict) – Config for meta testing.

返回

results_list (list[np.ndarray]): Predict results.
gt_labels (np.ndarray): Ground truth labels.

返回类型

tuple

classification.core¶

classification.datasets¶

class mmfewshot.classification.datasets.BaseFewShotDataset(data_prefix: str, pipeline: List[Dict], classes: Optional[Union[str, List[str]]] = None, ann_file: Optional[str] = None)[源代码]¶

Base few shot dataset.

参数

data_prefix (str) – The prefix of data path.
pipeline (list) – A list of dict, where each element represents a operation defined in mmcls.datasets.pipelines.
classes (str | Sequence[str] | None) – Classes for model training and provide fixed label for each class. Default: None.
ann_file (str | None) – The annotation file. When ann_file is str, the subclass is expected to read from the ann_file. When ann_file is None, the subclass is expected to read according to data_prefix. Default: None.

property class_to_idx: Mapping¶

Map mapping class name to class index.

返回: mapping from class name to class index.
返回类型: dict

static evaluate(results: List, gt_labels: numpy.array, metric: Union[str, List[str]] = 'accuracy', metric_options: Optional[dict] = None, logger: Optional[object] = None) → Dict[源代码]¶

Evaluate the dataset.

参数

results (list) – Testing results of the dataset.
gt_labels (np.ndarray) – Ground truth labels.
metric (str | list[str]) – Metrics to be evaluated. Default value is accuracy.
metric_options (dict | None) – Options for calculating metrics. Allowed keys are ‘topk’, ‘thrs’ and ‘average_mode’. Default: None.
logger (logging.Logger | None) – Logger used for printing related information during evaluation. Default: None.

返回

evaluation results

返回类型

dict

classmethod get_classes(classes: Optional[Union[Sequence[str], str]] = None) → Sequence[str][源代码]¶

Get class names of current dataset.

参数

classes (Sequence[str] | str | None) –

Three types of input will correspond to different processing logics:

If classes is a tuple or list, it will override the CLASSES predefined in the dataset.
If classes is None, we directly use pre-defined CLASSES will be used by the dataset.
If classes is a string, it is the path of a classes file that contains the name of all classes. Each line of the file contains a single class name.

返回

Names of categories of the dataset.

返回类型

tuple[str] or list[str]

sample_shots_by_class_id(class_id: int, num_shots: int) → List[int][源代码]¶: Random sample shots of given class id.

class mmfewshot.classification.datasets.CUBDataset(classes_id_seed: Optional[int] = None, subset: typing_extensions.Literal[train, test, val] = 'train', *args, **kwargs)[源代码]¶

CUB dataset for few shot classification.

参数

classes_id_seed (int | None) – A random seed to shuffle order of classes. If seed is None, the classes will be arranged in alphabetical order. Default: None.
subset (str| list[str]) – The classes of whole dataset are split into three disjoint subset: train, val and test. If subset is a string, only one subset data will be loaded. If subset is a list of string, then all data of subset in list will be loaded. Options: [‘train’, ‘val’, ‘test’]. Default: ‘train’.

get_classes(classes: Optional[Union[Sequence[str], str]] = None) → Sequence[str][源代码]¶

Get class names of current dataset.

参数

classes (Sequence[str] | str | None) –

Three types of input will correspond to different processing logics:

If classes is a tuple or list, it will override the CLASSES predefined in the dataset.
If classes is None, we directly use pre-defined CLASSES will be used by the dataset.
If classes is a string, it is the path of a classes file that contains the name of all classes. Each line of the file contains a single class name.

返回

Names of categories of the dataset.

返回类型

tuple[str] or list[str]

load_annotations() → List[Dict][源代码]¶: Load annotation according to the classes subset.

class mmfewshot.classification.datasets.EpisodicDataset(dataset: torch.utils.data.dataset.Dataset, num_episodes: int, num_ways: int, num_shots: int, num_queries: int, episodes_seed: Optional[int] = None)[源代码]¶

A wrapper of episodic dataset.

It will generate a list of support and query images indices for each episode (support + query images). Every call of __getitem__ will fetch and return (num_ways * num_shots) support images and (num_ways * num_queries) query images according to the generated images indices. Note that all the episode indices are generated at once using a specific random seed to ensure the reproducibility for same dataset.

参数

dataset (Dataset) – The dataset to be wrapped.
num_episodes (int) – Number of episodes. Noted that all episodes are generated at once and will not be changed afterwards. Make sure setting the num_episodes larger than your needs.
num_ways (int) – Number of ways for each episode.
num_shots (int) – Number of support data of each way for each episode.
num_queries (int) – Number of query data of each way for each episode.
episodes_seed (int | None) – A random seed to reproduce episodic indices. If seed is None, it will use runtime random seed. Default: None.

class mmfewshot.classification.datasets.LoadImageFromBytes(to_float32=False, color_type='color', file_client_args={'backend': 'disk'})[源代码]¶: Load an image from bytes.

class mmfewshot.classification.datasets.MetaTestDataset(*args, **kwargs)[源代码]¶

A wrapper of the episodic dataset for meta testing.

During meta test, the MetaTestDataset will be copied and converted into three mode: test_set, support, and test. Each mode of dataset will be used in different dataloader, but they share the same episode and image information.

In test_set mode, the dataset will fetch all images from the whole test set to extract features from the fixed backbone, which can accelerate meta testing.
In support or query mode, the dataset will fetch images according to the episode_idxes with the same task_id. Therefore, the support and query dataset must be set to the same task_id in each test task.

cache_feats(feats: torch.Tensor, img_metas: Dict) → None[源代码]¶: Cache extracted feats into dataset.

set_task_id(task_id: int) → None[源代码]¶: Query and support dataset use same task id to make sure fetch data from same episode.

class mmfewshot.classification.datasets.MiniImageNetDataset(subset: typing_extensions.Literal[train, test, val] = 'train', file_format: str = 'JPEG', *args, **kwargs)[源代码]¶

MiniImageNet dataset for few shot classification.

参数

subset (str| list[str]) – The classes of whole dataset are split into three disjoint subset: train, val and test. If subset is a string, only one subset data will be loaded. If subset is a list of string, then all data of subset in list will be loaded. Options: [‘train’, ‘val’, ‘test’]. Default: ‘train’.
file_format (str) – The file format of the image. Default: ‘JPEG’

get_classes(classes: Optional[Union[Sequence[str], str]] = None) → Sequence[str][源代码]¶

Get class names of current dataset.

参数

classes (Sequence[str] | str | None) –

Three types of input will correspond to different processing logics:

If classes is a tuple or list, it will override the CLASSES predefined in the dataset.
If classes is None, we directly use pre-defined CLASSES will be used by the dataset.
If classes is a string, it is the path of a classes file that contains the name of all classes. Each line of the file contains a single class name.

返回

Names of categories of the dataset.

返回类型

tuple[str] or list[str]

load_annotations() → List[源代码]¶: Load annotation according to the classes subset.

class mmfewshot.classification.datasets.TieredImageNetDataset(subset: typing_extensions.Literal[train, test, val] = 'train', *args, **kwargs)[源代码]¶

TieredImageNet dataset for few shot classification.

参数: subset (str| list[str]) – The classes of whole dataset are split into three disjoint subset: train, val and test. If subset is a string, only one subset data will be loaded. If subset is a list of string, then all data of subset in list will be loaded. Options: [‘train’, ‘val’, ‘test’]. Default: ‘train’.

get_classes(classes: Optional[Union[Sequence[str], str]] = None) → Sequence[str][源代码]¶

Get class names of current dataset.

参数

classes (Sequence[str] | str | None) –

Three types of input will correspond to different processing logics:

If classes is a tuple or list, it will override the CLASSES predefined in the dataset.
If classes is None, we directly use pre-defined CLASSES will be used by the dataset.
If classes is a string, it is the path of a classes file that contains the name of all classes. Each line of the file contains a single class name.

返回

Names of categories of the dataset.

返回类型

tuple[str] or list[str]

get_general_classes() → List[str][源代码]¶: Get general classes of each classes.

load_annotations() → List[Dict][源代码]¶: Load annotation according to the classes subset.

mmfewshot.classification.datasets.build_dataloader(dataset: torch.utils.data.dataset.Dataset, samples_per_gpu: int, workers_per_gpu: int, num_gpus: int = 1, dist: bool = True, shuffle: bool = True, round_up: bool = True, seed: Optional[int] = None, pin_memory: bool = False, use_infinite_sampler: bool = False, **kwargs) → torch.utils.data.dataloader.DataLoader[源代码]¶

Build PyTorch DataLoader.

In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only one dataloader for all GPUs.

参数

dataset (Dataset) – A PyTorch dataset.
samples_per_gpu (int) – Number of training samples on each GPU, i.e., batch size of each GPU.
workers_per_gpu (int) – How many subprocesses to use for data loading for each GPU.
num_gpus (int) – Number of GPUs. Only used in non-distributed training.
dist (bool) – Distributed training/test or not. Default: True.
shuffle (bool) – Whether to shuffle the data at every epoch. Default: True.
round_up (bool) – Whether to round up the length of dataset by adding extra samples to make it evenly divisible. Default: True.
seed (int | None) – Random seed. Default:None.
pin_memory (bool) – Whether to use pin_memory for dataloader. Default: False.
use_infinite_sampler (bool) – Whether to use infinite sampler. Noted that infinite sampler will keep iterator of dataloader running forever, which can avoid the overhead of worker initialization between epochs. Default: False.
kwargs – any keyword argument to be used to initialize DataLoader

返回

A PyTorch dataloader.

返回类型

DataLoader

mmfewshot.classification.datasets.build_meta_test_dataloader(dataset: torch.utils.data.dataset.Dataset, meta_test_cfg: Dict, **kwargs) → torch.utils.data.dataloader.DataLoader[源代码]¶

Build PyTorch DataLoader.

In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only one dataloader for all GPUs.

参数

dataset (Dataset) – A PyTorch dataset.
meta_test_cfg (dict) – Config of meta testing.
kwargs – any keyword argument to be used to initialize DataLoader

返回

support_data_loader, query_data_loader: and test_set_data_loader.

返回类型

tuple[Dataloader]

mmfewshot.classification.datasets.label_wrapper(labels: Union[torch.Tensor, numpy.ndarray, List], class_ids: List[int]) → Union[torch.Tensor, numpy.ndarray, list][源代码]¶

Map input labels into range of 0 to numbers of classes-1.

It is usually used in the meta testing phase, in which the class ids are random sampled and discontinuous.

参数

labels (Tensor | np.ndarray | list) – The labels to be wrapped.
class_ids (list[int]) – All class ids of labels.

返回

Same type as the input labels.

返回类型

(Tensor | np.ndarray | list)

classification.models¶

classification.utils¶

class mmfewshot.classification.utils.MetaTestParallel(module: torch.nn.modules.module.Module, dim: int = 0)[源代码]¶

The MetaTestParallel module that supports DataContainer.

Note that each task is tested on a single GPU. Thus the data and model on different GPU should be independent. MMDistributedDataParallel always automatically synchronizes the grad in different GPUs when doing the loss backward, which can not meet the requirements. Thus we simply copy the module and wrap it with an MetaTestParallel, which will send data to the device model.

MetaTestParallel has two main differences with PyTorch DataParallel:

It supports a custom type DataContainer which allows more flexible control of input data during both GPU and CPU inference.

It implement three more APIs before_meta_test(), before_forward_support() and before_forward_query().

参数

module (nn.Module) – Module to be encapsulated.
dim (int) – Dimension used to scatter the data. Defaults to 0.

forward(*inputs, **kwargs)[源代码]¶

Override the original forward function.

The main difference lies in the CPU inference where the data in DataContainers will still be gathered.

mmfewshot.detection¶

detection.apis¶

mmfewshot.detection.apis.inference_detector(model: torch.nn.modules.module.Module, imgs: Union[List[str], str]) → List[源代码]¶

Inference images with the detector.

参数

model (nn.Module) – Detector.
imgs (list[str] | str) – Batch or single image file.

返回

If imgs is a list or tuple, the same length list type results: will be returned, otherwise return the detection results directly.

返回类型

list

mmfewshot.detection.apis.init_detector(config: Union[str, mmcv.utils.config.Config], checkpoint: Optional[str] = None, device: str = 'cuda:0', cfg_options: Optional[Dict] = None, classes: Optional[List[str]] = None) → torch.nn.modules.module.Module[源代码]¶

Prepare a detector from config file.

参数

config (str | mmcv.Config) – Config file path or the config object.
checkpoint (str | None) – Checkpoint path. If left as None, the model will not load any weights.
device (str) – Runtime device. Default: ‘cuda:0’.
cfg_options (dict | None) – Options to override some settings in the used config.
classes (list[str] | None) – Options to override classes name of model. Default: None.

返回

The constructed detector.

返回类型

nn.Module

mmfewshot.detection.apis.multi_gpu_model_init(model: torch.nn.modules.module.Module, data_loader: torch.utils.data.dataloader.DataLoader) → List[源代码]¶

Forward support images for meta-learning based detector initialization.

The function usually will be called before single_gpu_test in QuerySupportEvalHook. It firstly forwards support images with mode=model_init and the features will be saved in the model. Then it will call :func:model_init to process the extracted features of support images to finish the model initialization.

Noted that the data_loader should NOT use distributed sampler, all the models in different gpus should be initialized with same images.

参数

model (nn.Module) – Model used for extracting support template features.
data_loader (nn.Dataloader) – Pytorch data loader.

返回

Extracted support template features.

返回类型

list[Tensor]

mmfewshot.detection.apis.multi_gpu_test(model: torch.nn.modules.module.Module, data_loader: torch.utils.data.dataloader.DataLoader, tmpdir: Optional[str] = None, gpu_collect: bool = False) → List[源代码]¶

Test model with multiple gpus for meta-learning based detector.

The model forward function requires mode, while in mmdet it requires return_loss. And the encode_mask_results is removed. This method tests model with multiple gpus and collects the results under two different modes: gpu and cpu modes. By setting ‘gpu_collect=True’ it encodes results to gpu tensors and use gpu communication for results collection. On cpu mode it saves the results on different gpus to ‘tmpdir’ and collects them by the rank 0 worker.

参数

model (nn.Module) – Model to be tested.
data_loader (Dataloader) – Pytorch data loader.
tmpdir (str) – Path of directory to save the temporary results from different gpus under cpu mode. Default: None.
gpu_collect (bool) – Option to use either gpu or cpu to collect results. Default: False.

返回

The prediction results.

返回类型

list

mmfewshot.detection.apis.process_support_images(model: torch.nn.modules.module.Module, support_imgs: List[str], support_labels: List[List[str]], support_bboxes: Optional[List[List[float]]] = None, classes: Optional[List[str]] = None) → None[源代码]¶

Process support images for query support detector.

参数

model (nn.Module) – Detector.
support_imgs (list[str]) – Support image filenames.
support_labels (list[list[str]]) – Support labels of each bbox.
support_bboxes (list[list[list[float]]] | None) – Bbox in support images. If it set to None, it will use the [0, 0, image width, image height] as bbox. Default: None.
classes (list[str] | None) – Options to override classes name of model. Default: None.

mmfewshot.detection.apis.single_gpu_model_init(model: torch.nn.modules.module.Module, data_loader: torch.utils.data.dataloader.DataLoader) → List[源代码]¶

Forward support images for meta-learning based detector initialization.

The function usually will be called before single_gpu_test in QuerySupportEvalHook. It firstly forwards support images with mode=model_init and the features will be saved in the model. Then it will call :func:model_init to process the extracted features of support images to finish the model initialization.

参数

model (nn.Module) – Model used for extracting support template features.
data_loader (nn.Dataloader) – Pytorch data loader.

返回

Extracted support template features.

返回类型

list[Tensor]

mmfewshot.detection.apis.single_gpu_test(model: torch.nn.modules.module.Module, data_loader: torch.utils.data.dataloader.DataLoader, show: bool = False, out_dir: Optional[str] = None, show_score_thr: float = 0.3) → List[源代码]¶

Test model with single gpu for meta-learning based detector.

The model forward function requires mode, while in mmdet it requires return_loss. And the encode_mask_results is removed.

参数

model (nn.Module) – Model to be tested.
data_loader (DataLoader) – Pytorch data loader.
show (bool) – Whether to show the image. Default: False.
out_dir (str | None) – The directory to write the image. Default: None.
show_score_thr (float) – Minimum score of bboxes to be shown. Default: 0.3.

返回

The prediction results.

返回类型

list

detection.core¶

detection.datasets¶

class mmfewshot.detection.datasets.BaseFewShotDataset(ann_cfg: List[Dict], classes: Optional[Union[str, Sequence[str]]], pipeline: Optional[List[Dict]] = None, multi_pipelines: Optional[Dict[str, List[Dict]]] = None, data_root: Optional[str] = None, img_prefix: str = '', seg_prefix: Optional[str] = None, proposal_file: Optional[str] = None, test_mode: bool = False, filter_empty_gt: bool = True, min_bbox_size: Optional[Union[float, int]] = None, ann_shot_filter: Optional[Dict] = None, instance_wise: bool = False, dataset_name: Optional[str] = None)[源代码]¶

Base dataset for few shot detection.

The main differences with normal detection dataset fall in two aspects.

It allows to specify single (used in normal dataset) or multiple
(used in query-support dataset) pipelines for data processing.

It supports to control the maximum number of instances of each class
when loading the annotation file.

The annotation format is shown as follows. The ann field is optional for testing.

[
    {
        'id': '0000001'
        'filename': 'a.jpg',
        'width': 1280,
        'height': 720,
        'ann': {
            'bboxes': <np.ndarray> (n, 4) in (x1, y1, x2, y2) order.
            'labels': <np.ndarray> (n, ),
            'bboxes_ignore': <np.ndarray> (k, 4), (optional field)
            'labels_ignore': <np.ndarray> (k, 4) (optional field)
        }
    },
    ...
]

参数

ann_cfg (list[dict]) –
Annotation config support two type of config.
- loading annotation from common ann_file of dataset with or without specific classes. example:dict(type=’ann_file’, ann_file=’path/to/ann_file’, ann_classes=[‘dog’, ‘cat’])
- loading annotation from a json file saved by dataset. example:dict(type=’saved_dataset’, ann_file=’path/to/ann_file’)
classes (str | Sequence[str] | None) – Classes for model training and provide fixed label for each class.
pipeline (list[dict] | None) – Config to specify processing pipeline. Used in normal dataset. Default: None.
multi_pipelines (dict[list[dict]]) –
Config to specify data pipelines for corresponding data flow. For example, query and support data can be processed with two different pipelines, the dict should contain two keys like:
- query (list[dict]): Config for query-data process pipeline.
- support (list[dict]): Config for support-data process pipeline.
data_root (str | None) – Data root for ann_cfg, img_prefix`, seg_prefix, proposal_file if specified. Default: None.
test_mode (bool) – If set True, annotation will not be loaded. Default: False.
filter_empty_gt (bool) – If set true, images without bounding boxes of the dataset’s classes will be filtered out. This option only works when test_mode=False, i.e., we never filter images during tests. Default: True.
min_bbox_size (int | float | None) – The minimum size of bounding boxes in the images. If the size of a bounding box is less than min_bbox_size, it would be added to ignored field. Default: None.
ann_shot_filter (dict | None) – Used to specify the class and the corresponding maximum number of instances when loading the annotation file. For example: {‘dog’: 10, ‘person’: 5}. If set it as None, all annotation from ann file would be loaded. Default: None.
instance_wise (bool) – If set true, self.data_infos would change to instance-wise, which means if the annotation of single image has more than one instance, the annotation would be split to num_instances items. Often used in support datasets, Default: False.
dataset_name (str | None) – Name of dataset to display. For example: ‘train_dataset’ or ‘query_dataset’. Default: None.

ann_cfg_parser(ann_cfg: List[Dict]) → List[Dict][源代码]¶

Parse annotation config to annotation information.

参数

ann_cfg (list[dict]) –

Annotation config support two type of config.

’ann_file’: loading annotation from common ann_file of
dataset. example: dict(type=’ann_file’, ann_file=’path/to/ann_file’, ann_classes=[‘dog’, ‘cat’])
’saved_dataset’: loading annotation from saved dataset.
example:dict(type=’saved_dataset’, ann_file=’path/to/ann_file’)

返回

Annotation information.

返回类型

list[dict]

get_ann_info(idx: int) → Dict[源代码]¶

Get annotation by index.

When override this function please make sure same annotations are used during the whole training.

参数: idx (int) – Index of data.
返回: Annotation info of specified index.
返回类型: dict

load_annotations_saved(ann_file: str) → List[Dict][源代码]¶: Load data_infos from saved json.

prepare_train_img(idx: int, pipeline_key: Optional[str] = None, gt_idx: Optional[List[int]] = None) → Dict[源代码]¶

Get training data and annotations after pipeline.

参数

idx (int) – Index of data.
pipeline_key (str) – Name of pipeline
gt_idx (list[int]) – Index of used annotation.

返回

Training data and annotation after pipeline with new keys introduced by pipeline.

返回类型

dict

save_data_infos(output_path: str) → None[源代码]¶: Save data_infos into json.

class mmfewshot.detection.datasets.CropResizeInstance(num_context_pixels: int = 16, target_size: Tuple[int] = (320, 320))[源代码]¶

Crop and resize instance according to bbox form image.

参数

num_context_pixels (int) – Padding pixel around instance. Default: 16.
target_size (tuple[int, int]) – Resize cropped instance to target size. Default: (320, 320).

class mmfewshot.detection.datasets.FewShotCocoDataset(classes: Optional[Union[Sequence[str], str]] = None, num_novel_shots: Optional[int] = None, num_base_shots: Optional[int] = None, ann_shot_filter: Optional[Dict[str, int]] = None, min_bbox_area: Optional[Union[float, int]] = None, dataset_name: Optional[str] = None, test_mode: bool = False, **kwargs)[源代码]¶

COCO dataset for few shot detection.

参数

classes (str | Sequence[str] | None) – Classes for model training and provide fixed label for each class. When classes is string, it will load pre-defined classes in FewShotCocoDataset. For example: ‘BASE_CLASSES’, ‘NOVEL_CLASSES` or ALL_CLASSES.
num_novel_shots (int | None) – Max number of instances used for each novel class. If is None, all annotation will be used. Default: None.
num_base_shots (int | None) – Max number of instances used for each base class. If is None, all annotation will be used. Default: None.
ann_shot_filter (dict | None) – Used to specify the class and the corresponding maximum number of instances when loading the annotation file. For example: {‘dog’: 10, ‘person’: 5}. If set it as None, ann_shot_filter will be created according to num_novel_shots and num_base_shots.
min_bbox_area (int | float | None) – Filter images with bbox whose area smaller min_bbox_area. If set to None, skip this filter. Default: None.
dataset_name (str | None) – Name of dataset to display. For example: ‘train dataset’ or ‘query dataset’. Default: None.
test_mode (bool) – If set True, annotation will not be loaded. Default: False.

evaluate(results: List[Sequence], metric: Union[str, List[str]] = 'bbox', logger: Optional[object] = None, jsonfile_prefix: Optional[str] = None, classwise: bool = False, proposal_nums: Sequence[int] = (100, 300, 1000), iou_thrs: Optional[Union[float, Sequence[float]]] = None, metric_items: Optional[Union[str, List[str]]] = None, class_splits: Optional[List[str]] = None) → Dict[源代码]¶

Evaluation in COCO protocol and summary results of different splits of classes.

参数

results (list[list | tuple]) – Testing results of the dataset.
metric (str | list[str]) – Metrics to be evaluated. Options are ‘bbox’, ‘proposal’, ‘proposal_fast’. Default: ‘bbox’
logger (logging.Logger | None) – Logger used for printing related information during evaluation. Default: None.
jsonfile_prefix (str | None) – The prefix of json files. It includes the file path and the prefix of filename, e.g., “a/b/prefix”. If not specified, a temp file will be created. Default: None.
classwise (bool) – Whether to evaluating the AP for each class.
proposal_nums (Sequence[int]) – Proposal number used for evaluating recalls, such as recall@100, recall@1000. Default: (100, 300, 1000).
iou_thrs (Sequence[float] | float | None) – IoU threshold used for evaluating recalls/mAPs. If set to a list, the average of all IoUs will also be computed. If not specified, [0.50, 0.55, 0.60, 0.65, 0.70, 0.75, 0.80, 0.85, 0.90, 0.95] will be used. Default: None.
metric_items (list[str] | str | None) – Metric items that will be returned. If not specified, ['AR@100', 'AR@300', 'AR@1000', 'AR_s@1000', 'AR_m@1000', 'AR_l@1000' ] will be used when metric=='proposal', ['mAP', 'mAP_50', 'mAP_75', 'mAP_s', 'mAP_m', 'mAP_l'] will be used when metric=='bbox'.
class_splits – (list[str] | None): Calculate metric of classes split in COCO_SPLIT. For example: [‘BASE_CLASSES’, ‘NOVEL_CLASSES’]. Default: None.

返回

COCO style evaluation metric.

返回类型

dict[str, float]

get_cat_ids(idx: int) → List[int][源代码]¶

Get category ids by index.

Overwrite the function in CocoDataset.

参数: idx (int) – Index of data.
返回: All categories in the image of specified index.
返回类型: list[int]

get_classes(classes: Union[str, Sequence[str]]) → List[str][源代码]¶

Get class names.

It supports to load pre-defined classes splits. The pre-defined classes splits are: [‘ALL_CLASSES’, ‘NOVEL_CLASSES’, ‘BASE_CLASSES’]

参数: classes (str | Sequence[str]) – Classes for model training and provide fixed label for each class. When classes is string, it will load pre-defined classes in FewShotCocoDataset. For example: ‘NOVEL_CLASSES’.
返回: list of class names.
返回类型: list[str]

load_annotations(ann_cfg: List[Dict]) → List[Dict][源代码]¶

Support to Load annotation from two type of ann_cfg.

type of ‘ann_file’: COCO-style annotation file.

type of ‘saved_dataset’: Saved COCO dataset json.

参数: ann_cfg (list[dict]) – Config of annotations.
返回: Annotation infos.
返回类型: list[dict]

load_annotations_coco(ann_file: str) → List[Dict][源代码]¶

Load annotation from COCO style annotation file.

参数: ann_file (str) – Path of annotation file.
返回: Annotation info from COCO api.
返回类型: list[dict]

class mmfewshot.detection.datasets.FewShotVOCDataset(classes: Optional[Union[Sequence[str], str]] = None, num_novel_shots: Optional[int] = None, num_base_shots: Optional[int] = None, ann_shot_filter: Optional[Dict] = None, use_difficult: bool = False, min_bbox_area: Optional[Union[float, int]] = None, dataset_name: Optional[str] = None, test_mode: bool = False, coordinate_offset: List[int] = [- 1, - 1, 0, 0], **kwargs)[源代码]¶

VOC dataset for few shot detection.

参数

classes (str | Sequence[str]) – Classes for model training and provide fixed label for each class. When classes is string, it will load pre-defined classes in FewShotVOCDataset. For example: ‘NOVEL_CLASSES_SPLIT1’.
num_novel_shots (int | None) – Max number of instances used for each novel class. If is None, all annotation will be used. Default: None.
num_base_shots (int | None) – Max number of instances used for each base class. When it is None, all annotations will be used. Default: None.
ann_shot_filter (dict | None) – Used to specify the class and the corresponding maximum number of instances when loading the annotation file. For example: {‘dog’: 10, ‘person’: 5}. If set it as None, ann_shot_filter will be created according to num_novel_shots and num_base_shots. Default: None.
use_difficult (bool) – Whether use the difficult annotation or not. Default: False.
min_bbox_area (int | float | None) – Filter images with bbox whose area smaller min_bbox_area. If set to None, skip this filter. Default: None.
dataset_name (str | None) – Name of dataset to display. For example: ‘train dataset’ or ‘query dataset’. Default: None.
test_mode (bool) – If set True, annotation will not be loaded. Default: False.
coordinate_offset (list[int]) – The bbox annotation will add the coordinate offsets which corresponds to [x_min, y_min, x_max, y_max] during training. For testing, the gt annotation will not be changed while the predict results will minus the coordinate offsets to inverse data loading logic in training. Default: [-1, -1, 0, 0].

evaluate(results: List[Sequence], metric: Union[str, List[str]] = 'mAP', logger: Optional[object] = None, proposal_nums: Sequence[int] = (100, 300, 1000), iou_thr: Optional[Union[float, Sequence[float]]] = 0.5, class_splits: Optional[List[str]] = None) → Dict[源代码]¶

Evaluation in VOC protocol and summary results of different splits of classes.

参数

results (list[list | tuple]) – Predictions of the model.
metric (str | list[str]) – Metrics to be evaluated. Options are ‘mAP’, ‘recall’. Default: mAP.
logger (logging.Logger | None) – Logger used for printing related information during evaluation. Default: None.
proposal_nums (Sequence[int]) – Proposal number used for evaluating recalls, such as recall@100, recall@1000. Default: (100, 300, 1000).
iou_thr (float | list[float]) – IoU threshold. Default: 0.5.
class_splits – (list[str] | None): Calculate metric of classes split defined in VOC_SPLIT. For example: [‘BASE_CLASSES_SPLIT1’, ‘NOVEL_CLASSES_SPLIT1’]. Default: None.

返回

AP/recall metrics.

返回类型

dict[str, float]

get_classes(classes: Union[str, Sequence[str]]) → List[str][源代码]¶

Get class names.

It supports to load pre-defined classes splits. The pre-defined classes splits are: [‘ALL_CLASSES_SPLIT1’, ‘ALL_CLASSES_SPLIT2’, ‘ALL_CLASSES_SPLIT3’,

‘BASE_CLASSES_SPLIT1’, ‘BASE_CLASSES_SPLIT2’, ‘BASE_CLASSES_SPLIT3’, ‘NOVEL_CLASSES_SPLIT1’,’NOVEL_CLASSES_SPLIT2’,’NOVEL_CLASSES_SPLIT3’]

参数: classes (str | Sequence[str]) – Classes for model training and provide fixed label for each class. When classes is string, it will load pre-defined classes in FewShotVOCDataset. For example: ‘NOVEL_CLASSES_SPLIT1’.
返回: List of class names.
返回类型: list[str]

load_annotations(ann_cfg: List[Dict]) → List[Dict][源代码]¶

Support to load annotation from two type of ann_cfg.

参数

ann_cfg (list[dict]) – Support two type of config.
loading annotation from common ann_file of dataset (-) – with or without specific classes. example:dict(type=’ann_file’, ann_file=’path/to/ann_file’, ann_classes=[‘dog’, ‘cat’])
loading annotation from a json file saved by dataset. (-) – example:dict(type=’saved_dataset’, ann_file=’path/to/ann_file’)

返回

Annotation information.

返回类型

list[dict]

load_annotations_xml(ann_file: str, classes: Optional[List[str]] = None) → List[Dict][源代码]¶

Load annotation from XML style ann_file.

It supports using image id or image path as image names to load the annotation file.

参数

ann_file (str) – Path of annotation file.
classes (list[str] | None) – Specific classes to load form xml file. If set to None, it will use classes of whole dataset. Default: None.

返回

Annotation info from XML file.

返回类型

list[dict]

class mmfewshot.detection.datasets.GenerateMask(target_size: Tuple[int] = (224, 224))[源代码]¶

Resize support image and generate a mask.

参数: target_size (tuple[int, int]) – Crop and resize to target size. Default: (224, 224).

class mmfewshot.detection.datasets.NWayKShotDataloader(query_data_loader: torch.utils.data.dataloader.DataLoader, support_data_loader: torch.utils.data.dataloader.DataLoader)[源代码]¶

A dataloader wrapper.

It Create a iterator to generate query and support batch simultaneously. Each batch contains query data and support data, and the lengths are batch_size and (num_support_ways * num_support_shots) respectively.

参数

query_data_loader (DataLoader) – DataLoader of query dataset
support_data_loader (DataLoader) – DataLoader of support datasets.

class mmfewshot.detection.datasets.NWayKShotDataset(query_dataset: mmfewshot.detection.datasets.base.BaseFewShotDataset, support_dataset: Optional[mmfewshot.detection.datasets.base.BaseFewShotDataset], num_support_ways: int, num_support_shots: int, one_support_shot_per_image: bool = False, num_used_support_shots: int = 200, repeat_times: int = 1)[源代码]¶

A dataset wrapper of NWayKShotDataset.

Building NWayKShotDataset requires query and support dataset, the behavior of NWayKShotDataset is determined by mode. When dataset in ‘query’ mode, dataset will return regular image and annotations. While dataset in ‘support’ mode, dataset will build batch indices firstly and each batch indices contain (num_support_ways * num_support_shots) samples. In other words, for support mode every call of __getitem__ will return a batch of samples, therefore the outside dataloader should set batch_size to 1. The default mode of NWayKShotDataset is ‘query’ and by using convert function convert_query_to_support the mode will be converted into ‘support’.

参数

query_dataset (BaseFewShotDataset) – Query dataset to be wrapped.
support_dataset (BaseFewShotDataset | None) – Support dataset to be wrapped. If support dataset is None, support dataset will copy from query dataset.
num_support_ways (int) – Number of classes for support in mini-batch.
num_support_shots (int) – Number of support shot for each class in mini-batch.
one_support_shot_per_image (bool) – If True only one annotation will be sampled from each image. Default: False.
num_used_support_shots (int | None) – The total number of support shots sampled and used for each class during training. If set to None, all shots in dataset will be used as support shot. Default: 200.
shuffle_support (bool) – If allow generate new batch indices for each epoch. Default: False.
repeat_times (int) – The length of repeated dataset will be times larger than the original dataset. Default: 1.

convert_query_to_support(support_dataset_len: int) → None[源代码]¶

Convert query dataset to support dataset.

参数: support_dataset_len (int) – Length of pre sample batch indices.

generate_support_batch_indices(dataset_len: int) → List[List[Tuple[int]]][源代码]¶

Generate batch indices from support dataset.

Batch indices is in the shape of [length of datasets * [support way * support shots]]. And the dataset_len will be the length of support dataset.

参数: dataset_len (int) – Length of batch indices.
返回: Pre-sample batch indices.
返回类型: list[list[(data_idx, gt_idx)]]

get_support_data_infos() → List[Dict][源代码]¶: Get support data infos from batch indices.

save_data_infos(output_path: str) → None[源代码]¶: Save data infos of query and support data.

save_support_data_infos(support_output_path: str) → None[源代码]¶: Save support data infos.

class mmfewshot.detection.datasets.NumpyEncoder(*, skipkeys=False, ensure_ascii=True, check_circular=True, allow_nan=True, sort_keys=False, indent=None, separators=None, default=None)[源代码]¶

Save numpy array obj to json.

default(obj: object) → object[源代码]¶

Implement this method in a subclass such that it returns a serializable object for o, or calls the base implementation (to raise a TypeError).

For example, to support arbitrary iterators, you could implement default like this:

def default(self, o):
    try:
        iterable = iter(o)
    except TypeError:
        pass
    else:
        return list(iterable)
    # Let the base class default method raise the TypeError
    return JSONEncoder.default(self, o)

class mmfewshot.detection.datasets.QueryAwareDataset(query_dataset: mmfewshot.detection.datasets.base.BaseFewShotDataset, support_dataset: Optional[mmfewshot.detection.datasets.base.BaseFewShotDataset], num_support_ways: int, num_support_shots: int, repeat_times: int = 1)[源代码]¶

A wrapper of QueryAwareDataset.

Building QueryAwareDataset requires query and support dataset. Every call of __getitem__ will firstly sample a query image and its annotations. Then it will use the query annotations to sample a batch of positive and negative support images and annotations. The positive images share same classes with query, while the annotations of negative images don’t have any category from query.

参数

query_dataset (BaseFewShotDataset) – Query dataset to be wrapped.
support_dataset (BaseFewShotDataset | None) – Support dataset to be wrapped. If support dataset is None, support dataset will copy from query dataset.
num_support_ways (int) – Number of classes for support in mini-batch, the first one always be the positive class.
num_support_shots (int) – Number of support shots for each class in mini-batch, the first K shots always from positive class.
repeat_times (int) – The length of repeated dataset will be times larger than the original dataset. Default: 1.

generate_support(idx: int, query_class: int, support_classes: List[int]) → List[Tuple[int]][源代码]¶

Generate support indices of query images.

参数

idx (int) – Index of query data.
query_class (int) – Query class.
support_classes (list[int]) – Classes of support data.

返回

A mini-batch (num_support_ways *: num_support_shots) of support data (idx, gt_idx).

返回类型

list[tuple(int)]

get_support_data_infos() → List[Dict][源代码]¶: Return data_infos of support dataset.

sample_support_shots(idx: int, class_id: int, allow_same_image: bool = False) → List[Tuple[int]][源代码]¶

Generate support indices according to the class id.

参数

idx (int) – Index of query data.
class_id (int) – Support class.
allow_same_image (bool) – Allow instance sampled from same image as query image. Default: False.

返回

Support data (num_support_shots): of specific class.

返回类型

list[tuple[int]]

save_data_infos(output_path: str) → None[源代码]¶: Save data_infos into json.

mmfewshot.detection.datasets.build_dataloader(dataset: torch.utils.data.dataset.Dataset, samples_per_gpu: int, workers_per_gpu: int, num_gpus: int = 1, dist: bool = True, shuffle: bool = True, seed: Optional[int] = None, data_cfg: Optional[Dict] = None, use_infinite_sampler: bool = False, **kwargs) → torch.utils.data.dataloader.DataLoader[源代码]¶

Build PyTorch DataLoader.

In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only one dataloader for all GPUs.

参数

dataset (Dataset) – A PyTorch dataset.
samples_per_gpu (int) – Number of training samples on each GPU, i.e., batch size of each GPU.
workers_per_gpu (int) – How many subprocesses to use for data loading for each GPU.
num_gpus (int) – Number of GPUs. Only used in non-distributed training. Default:1.
dist (bool) – Distributed training/test or not. Default: True.
shuffle (bool) – Whether to shuffle the data at every epoch. Default: True.
seed (int) – Random seed. Default:None.
data_cfg (dict | None) – Dict of data configure. Default: None.
use_infinite_sampler (bool) – Whether to use infinite sampler. Noted that infinite sampler will keep iterator of dataloader running forever, which can avoid the overhead of worker initialization between epochs. Default: False.
kwargs – any keyword argument to be used to initialize DataLoader

返回

A PyTorch dataloader.

返回类型

DataLoader

mmfewshot.detection.datasets.get_copy_dataset_type(dataset_type: str) → str[源代码]¶: Return corresponding copy dataset type.

detection.models¶

mmfewshot.detection.models.build_backbone(cfg)[源代码]¶: Build backbone.

mmfewshot.detection.models.build_detector(cfg: mmcv.utils.config.ConfigDict, logger: Optional[object] = None)[源代码]¶: Build detector.

mmfewshot.detection.models.build_head(cfg)[源代码]¶: Build head.

mmfewshot.detection.models.build_loss(cfg)[源代码]¶: Build loss.

mmfewshot.detection.models.build_neck(cfg)[源代码]¶: Build neck.

mmfewshot.detection.models.build_roi_extractor(cfg)[源代码]¶: Build roi extractor.

mmfewshot.detection.models.build_shared_head(cfg)[源代码]¶: Build shared head.

detection.utils¶

class mmfewshot.detection.utils.ContrastiveLossDecayHook(decay_steps: Sequence[int], decay_rate: float = 0.5)¶

Hook for contrast loss weight decay used in FSCE.

参数

decay_steps (list[int] | tuple[int]) – Each item in the list is the step to decay the loss weight.
decay_rate (float) – Decay rate. Default: 0.5.

mmfewshot.utils¶

class mmfewshot.utils.DistributedInfiniteGroupSampler(dataset: Iterable, samples_per_gpu: int = 1, num_replicas: Optional[int] = None, rank: Optional[int] = None, seed: int = 0, shuffle: bool = True)[源代码]¶

Similar to InfiniteGroupSampler but in distributed version.

The length of sampler is set to the actual length of dataset, thus the length of dataloader is still determined by the dataset. The implementation logic is referred to https://github.com/facebookresearch/detectron2/blob/main/detectron2/data/samplers/grouped_batch_sampler.py

参数

dataset (Iterable) – The dataset.
samples_per_gpu (int) – Number of training samples on each GPU, i.e., batch size of each GPU. Default: 1.
num_replicas (int | None) – Number of processes participating in distributed training. Default: None.
rank (int | None) – Rank of current process. Default: None.
seed (int) – Random seed. Default: 0.
shuffle (bool) – Whether shuffle the indices of a dummy epoch, it should be noted that shuffle can not guarantee that you can generate sequential indices because it need to ensure that all indices in a batch is in a group. Default: True.

class mmfewshot.utils.DistributedInfiniteSampler(dataset: Iterable, num_replicas: Optional[int] = None, rank: Optional[int] = None, seed: int = 0, shuffle: bool = True)[源代码]¶

Similar to InfiniteSampler but in distributed version.

The length of sampler is set to the actual length of dataset, thus the length of dataloader is still determined by the dataset. The implementation logic is referred to https://github.com/facebookresearch/detectron2/blob/main/detectron2/data/samplers/grouped_batch_sampler.py

参数

dataset (Iterable) – The dataset.
num_replicas (int | None) – Number of processes participating in distributed training. Default: None.
rank (int | None) – Rank of current process. Default: None.
seed (int) – Random seed. Default: 0.
shuffle (bool) – Whether shuffle the dataset or not. Default: True.

class mmfewshot.utils.InfiniteEpochBasedRunner(model, batch_processor=None, optimizer=None, work_dir=None, logger=None, meta=None, max_iters=None, max_epochs=None)[源代码]¶

Epoch-based Runner supports dataloader with InfiniteSampler.

The workers of dataloader will re-initialize, when the iterator of dataloader is created. InfiniteSampler is designed to avoid these time consuming operations, since the iterator with InfiniteSampler will never reach the end.

class mmfewshot.utils.InfiniteGroupSampler(dataset: Iterable, samples_per_gpu: int = 1, seed: int = 0, shuffle: bool = True)[源代码]¶

Similar to InfiniteSampler, but all indices in a batch should be in the same group of flag.

The length of sampler is set to the actual length of dataset, thus the length of dataloader is still determined by the dataset. The implementation logic is referred to https://github.com/facebookresearch/detectron2/blob/main/detectron2/data/samplers/grouped_batch_sampler.py

参数

dataset (Iterable) – The dataset.
samples_per_gpu (int) – Number of training samples on each GPU, i.e., batch size of each GPU. Default: 1.
seed (int) – Random seed. Default: 0.
shuffle (bool) – Whether shuffle the indices of a dummy epoch, it should be noted that shuffle can not guarantee that you can generate sequential indices because it need to ensure that all indices in a batch is in a group. Default: True.

class mmfewshot.utils.InfiniteSampler(dataset: Iterable, seed: int = 0, shuffle: bool = True)[源代码]¶

Return a infinite stream of index.

The length of sampler is set to the actual length of dataset, thus the length of dataloader is still determined by the dataset. The implementation logic is referred to https://github.com/facebookresearch/detectron2/blob/main/detectron2/data/samplers/grouped_batch_sampler.py

参数

dataset (Iterable) – The dataset.
seed (int) – Random seed. Default: 0.
shuffle (bool) – Whether shuffle the dataset or not. Default: True.

mmfewshot.utils.local_numpy_seed(seed: Optional[int] = None) → None[源代码]¶

Run numpy codes with a local random seed.

If seed is None, the default random state will be used.

mmfewshot.utils.multi_pipeline_collate_fn(batch, samples_per_gpu: int = 1)[源代码]¶

Puts each data field into a tensor/DataContainer with outer dimension batch size. This is designed to support the case that the __getitem__() of dataset return more than one images, such as query_support dataloader. The main difference with the collate_fn() in mmcv is it can process list[list[DataContainer]].

Extend default_collate to add support for :type:`~mmcv.parallel.DataContainer`. There are 3 cases:

cpu_only = True, e.g., meta data.
cpu_only = False, stack = True, e.g., images tensors.
cpu_only = False, stack = False, e.g., gt bboxes.

:param batch (list[list[mmcv.parallel.DataContainer]] |: list[mmcv.parallel.DataContainer]): Data of: single batch.

参数: samples_per_gpu (int) – The number of samples of single GPU.