Source code for mmaction.datasets.base

import copy
import os.path as osp
from abc import ABCMeta, abstractmethod

import mmcv
import torch
from torch.utils.data import Dataset

from .pipelines import Compose


[docs]class BaseDataset(Dataset, metaclass=ABCMeta): """Base class for datasets. All datasets to process video should subclass it. All subclasses should overwrite: - Methods:`load_annotations`, supporting to load information from an annotation file. - Methods:`prepare_train_frames`, providing train data. - Methods:`prepare_test_frames`, providing test data. Args: ann_file (str): Path to the annotation file. pipeline (list[dict | callable]): A sequence of data transforms. data_prefix (str): Path to a directory where videos are held. Default: None. test_mode (bool): Store True when building test or validation dataset. Default: False. multi_class (bool): Determines whether the dataset is a multi-class dataset. Default: False. num_classes (int): Number of classes of the dataset, used in multi-class datasets. Default: None. start_index (int): Specify a start index for frames in consideration of different filename format. However, when taking videos as input, it should be set to 0, since frames loaded from videos count from 0. Default: 1. modality (str): Modality of data. Support 'RGB', 'Flow'. Default: 'RGB'. """ def __init__(self, ann_file, pipeline, data_prefix=None, test_mode=False, multi_class=False, num_classes=None, start_index=1, modality='RGB'): super().__init__() self.ann_file = ann_file self.data_prefix = osp.realpath(data_prefix) if osp.isdir( data_prefix) else data_prefix self.test_mode = test_mode self.multi_class = multi_class self.num_classes = num_classes self.start_index = start_index self.modality = modality self.pipeline = Compose(pipeline) self.video_infos = self.load_annotations()
[docs] @abstractmethod def load_annotations(self): """Load the annotation according to ann_file into video_infos.""" pass
# json annotations already looks like video_infos, so for each dataset, # this func should be the same
[docs] def load_json_annotations(self): """Load json annotation file to get video information.""" video_infos = mmcv.load(self.ann_file) num_videos = len(video_infos) path_key = 'frame_dir' if 'frame_dir' in video_infos[0] else 'filename' for i in range(num_videos): if self.data_prefix is not None: path_value = video_infos[i][path_key] path_value = osp.join(self.data_prefix, path_value) video_infos[i][path_key] = path_value if self.multi_class: assert self.num_classes is not None onehot = torch.zeros(self.num_classes) onehot[video_infos[i]['label']] = 1. video_infos[i]['label'] = onehot else: assert len(video_infos[i]['label']) == 1 video_infos[i]['label'] = video_infos[i]['label'][0] return video_infos
[docs] @abstractmethod def evaluate(self, results, metrics, logger): """Evaluation for the dataset. Args: results (list): Output results. metrics (str | sequence[str]): Metrics to be performed. logger (logging.Logger | None): Logger for recording. Returns: dict: Evaluation results dict. """ pass
[docs] def dump_results(self, results, out): """Dump data to json/yaml/pickle strings or files.""" return mmcv.dump(results, out)
[docs] def prepare_train_frames(self, idx): """Prepare the frames for training given the index.""" results = copy.deepcopy(self.video_infos[idx]) results['modality'] = self.modality results['start_index'] = self.start_index return self.pipeline(results)
[docs] def prepare_test_frames(self, idx): """Prepare the frames for testing given the index.""" results = copy.deepcopy(self.video_infos[idx]) results['modality'] = self.modality results['start_index'] = self.start_index return self.pipeline(results)
def __len__(self): """Get the size of the dataset.""" return len(self.video_infos) def __getitem__(self, idx): """Get the sample for either training or testing given index.""" if self.test_mode: return self.prepare_test_frames(idx) else: return self.prepare_train_frames(idx)