o
    Vh                     @   s   d dl Z d dlmZ d dlmZmZmZmZmZm	Z	m
Z
 d dlmZ ddlmZmZ ddlmZ ddlmZ G d	d
 d
eZdS )    N)Path)AnyCallableDictListOptionalTupleUnion)Tensor   )find_classesmake_dataset)
VideoClips)VisionDatasetc                !       s  e Zd ZdZ												d#deeef ded	ed
edee dede	dee
 deeeef  dededededededdf  fddZedeeef fddZdee dedede	dee f
ddZdefddZd edeeeef fd!d"Z  ZS )$UCF101a  
    `UCF101 <https://www.crcv.ucf.edu/data/UCF101.php>`_ dataset.

    UCF101 is an action recognition video dataset.
    This dataset consider every video as a collection of video clips of fixed size, specified
    by ``frames_per_clip``, where the step in frames between each clip is given by
    ``step_between_clips``. The dataset itself can be downloaded from the dataset website;
    annotations that ``annotation_path`` should be pointing to can be downloaded from `here
    <https://www.crcv.ucf.edu/data/UCF101/UCF101TrainTestSplits-RecognitionTask.zip>`_.

    To give an example, for 2 videos with 10 and 15 frames respectively, if ``frames_per_clip=5``
    and ``step_between_clips=5``, the dataset size will be (2 + 3) = 5, where the first two
    elements will come from video 1, and the next three elements from video 2.
    Note that we drop clips which do not have exactly ``frames_per_clip`` elements, so not all
    frames in a video might be present.

    Internally, it uses a VideoClips object to handle clip creation.

    Args:
        root (str or ``pathlib.Path``): Root directory of the UCF101 Dataset.
        annotation_path (str): path to the folder containing the split files;
            see docstring above for download instructions of these files
        frames_per_clip (int): number of frames in a clip.
        step_between_clips (int, optional): number of frames between each clip.
        fold (int, optional): which fold to use. Should be between 1 and 3.
        train (bool, optional): if ``True``, creates a dataset from the train split,
            otherwise from the ``test`` split.
        transform (callable, optional): A function/transform that takes in a TxHxWxC video
            and returns a transformed version.
        output_format (str, optional): The format of the output video tensors (before transforms).
            Can be either "THWC" (default) or "TCHW".

    Returns:
        tuple: A 3-tuple with the following entries:

            - video (Tensor[T, H, W, C] or Tensor[T, C, H, W]): The `T` video frames
            -  audio(Tensor[K, L]): the audio frames, where `K` is the number of channels
               and `L` is the number of points
            - label (int): class of the video clip
    r   NTr   THWCrootannotation_pathframes_per_clipstep_between_clips
frame_ratefoldtrain	transform_precomputed_metadatanum_workers_video_width_video_height_video_min_dimension_audio_samplesoutput_formatreturnc                    s   t  | d|  krdksn td| d}|| _|| _t| j\| _}t| j||d d| _	dd | j	D }t
|||||	|
|||||d}|| _| ||||| _|| j| _|| _d S )	Nr      z$fold should be between 1 and 3, got )avi)is_valid_filec                 S   s   g | ]}|d  qS )r    .0xr%   r%   O/var/www/vscode/kcb/lib/python3.10/site-packages/torchvision/datasets/ucf101.py
<listcomp>R   s    z#UCF101.__init__.<locals>.<listcomp>)r   r   r   r   r   r    )super__init__
ValueErrorr   r   r   r   classesr   samplesr   full_video_clips_select_foldindicessubsetvideo_clipsr   )selfr   r   r   r   r   r   r   r   r   r   r   r   r   r   r    
extensionsclass_to_idx
video_listr4   	__class__r%   r)   r,   6   s4   
zUCF101.__init__c                 C   s   | j jS N)r0   metadatar5   r%   r%   r)   r<   h   s   zUCF101.metadatar8   c           
         s   |rdnd}| d|dd}t j||}t  t|!}| }dd |D }fdd|D } | W d    n1 sAw   Y   fd	dttD }	|	S )
Nr   testlist02dz.txtc                 S   s   g | ]}|  d d qS ) r   )stripsplitr&   r%   r%   r)   r*   s   s    z'UCF101._select_fold.<locals>.<listcomp>c                    s(   g | ]}t jj jg|d R  qS )/)ospathjoinr   rC   r&   r=   r%   r)   r*   t   s   ( c                    s   g | ]
}|  v r|qS r%   r%   )r'   i)selected_filesr8   r%   r)   r*   v   s    )	rE   rF   rG   setopen	readlinesupdaterangelen)
r5   r8   r   r   r   nameffiddatar2   r%   )rI   r5   r8   r)   r1   l   s   
zUCF101._select_foldc                 C   s
   | j  S r;   )r4   	num_clipsr=   r%   r%   r)   __len__y   s   
zUCF101.__len__idxc                 C   sF   | j |\}}}}| j| j|  d }| jd ur| |}|||fS )Nr   )r4   get_clipr/   r2   r   )r5   rV   videoaudioinfo	video_idxlabelr%   r%   r)   __getitem__|   s
   


zUCF101.__getitem__)r   Nr   TNNr   r   r   r   r   r   )__name__
__module____qualname____doc__r	   strr   intr   boolr   r   r   r,   propertyr<   r   r1   rU   r   r
   r]   __classcell__r%   r%   r9   r)   r      sh    .
	
2&$r   )rE   pathlibr   typingr   r   r   r   r   r   r	   torchr
   folderr   r   video_utilsr   visionr   r   r%   r%   r%   r)   <module>   s    $