spikingjelly.datasets.hardvs module#

class spikingjelly.datasets.hardvs.HARDVS(root: str, train_test_val: str = None, data_type: str = 'event', frames_number: int = None, split_by: str = None, duration: int = None, custom_integrate_function: Callable = None, custom_integrated_frames_dir_name: str = None, transform: Callable | None = None, target_transform: Callable | None = None)[源代码]#

基类：NeuromorphicDatasetFolder

API Language: 中文 | English

  • 中文

HARDVS 数据集，由 HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors. 提出。

有关参数的更多详细信息，请参考 NeuromorphicDatasetFolder

  • English

The HARDVS dataset, which is proposed by HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors..

Refer to NeuromorphicDatasetFolder for more details about params information.

参数:

  • root (Union[str, Path]) -- 数据集的根路径

  • train_test_val (str) -- "train"、"val" 或 "test"

  • data_type (str) -- "event" 或 "frame"

  • frames_number (Optional[int]) -- 积分帧的数量

  • split_by (Optional[str]) -- "time" 或 "number"

  • duration (Optional[int]) -- 每帧的时间时长

  • custom_integrate_function (Optional[Callable]) -- 用户自定义积分函数

  • custom_integrated_frames_dir_name (Optional[str]) -- 自定义积分帧目录名

  • transform (Optional[Callable]) -- 数据变换

  • target_transform (Optional[Callable]) -- 标签变换

  • root -- Root directory of the dataset

  • train_test_val -- "train", "val", or "test"

  • data_type -- "event" or "frame"

  • frames_number -- Number of frames to integrate

  • split_by -- "time" or "number"

  • duration -- Time duration per frame

  • custom_integrate_function -- User-defined integrate function

  • custom_integrated_frames_dir_name -- Custom frames directory name

  • transform -- Transform function

  • target_transform -- Target transform function

返回:

None

返回类型:

None

get_root_when_train_is_none(_root: Path)[源代码]#
classmethod get_H_W() → Tuple[源代码]#
返回:

(260, 346)

classmethod resource_url_md5() → list[源代码]#
classmethod downloadable() → bool[源代码]#
返回:

False

classmethod extract_downloaded_files(download_root: Path, extract_root: Path)[源代码]#
classmethod create_raw_from_extracted(extract_root: Path, raw_root: Path)[源代码]#