a PSic4@sddlZddlZddlZddlZddlZddlmZddlmZddlm Z ddl m Z m Z m Z mZmZddlmZddlmZmZdd lmZmZmZmZdd lmZdd lmZeeedd d dZGdddeZ Gddde Z!dS)N)partial)Pool)path)AnyCallableDictOptionalTuple)Tensor) find_classes make_dataset)download_and_extract_archive download_urlverify_str_argcheck_integrity) VideoClips) VisionDataset)tarpath videopathlinereturncCst|||dSN)r)rrrrY/var/www/html/django/DPS/env/lib/python3.9/site-packages/torchvision/datasets/kinetics.py_dl_wrapsrcseZdZdZddddZddddZd#eeeeeeeee e edfe eeee ee feeeeee ed dfdd Zd dddZd dddZd dddZee ee fdddZedddZee eeefd d!d"ZZS)$Kineticsuz `Generic Kinetics `_ dataset. Kinetics-400/600/700 are action recognition video datasets. 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``. 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. Args: root (string): Root directory of the Kinetics Dataset. Directory should be structured as follows: .. code:: root/ ├── split │ ├── class1 │ │ ├── clip1.mp4 │ │ ├── clip2.mp4 │ │ ├── clip3.mp4 │ │ ├── ... │ ├── class2 │ │ ├── clipx.mp4 │ │ └── ... Note: split is appended automatically using the split argument. frames_per_clip (int): number of frames in a clip num_classes (int): select between Kinetics-400 (default), Kinetics-600, and Kinetics-700 split (str): split of the dataset to consider; supports ``"train"`` (default) ``"val"`` ``"test"`` frame_rate (float): If omitted, interpolate different frame rate for each clip. step_between_clips (int): number of frames between each clip transform (callable, optional): A function/transform that takes in a TxHxWxC video and returns a transformed version. download (bool): Download the official version of the dataset to root folder. num_workers (int): Use multiple workers for VideoClips creation num_download_workers (int): Use multiprocessing in order to speed up download. output_format (str, optional): The format of the output video tensors (before transforms). Can be either "THWC" or "TCHW" (default). Note that in most other utils and datasets, the default is actually "THWC". Returns: tuple: A 3-tuple with the following entries: - video (Tensor[T, C, H, W] or Tensor[T, H, W, C]): the `T` video frames in torch.uint8 tensor - audio(Tensor[K, L]): the audio frames, where `K` is the number of channels and `L` is the number of points in torch.float tensor - label (int): class of the video clip Raises: RuntimeError: If ``download is True`` and the video archives are already extracted. zChttps://s3.amazonaws.com/kinetics/400/{split}/k400_{split}_path.txtzChttps://s3.amazonaws.com/kinetics/600/{split}/k600_{split}_path.txtzMhttps://s3.amazonaws.com/kinetics/700_2020/{split}/k700_2020_{split}_path.txt400Z600Z700z=https://s3.amazonaws.com/kinetics/400/annotations/{split}.csvz=https://s3.amazonaws.com/kinetics/600/annotations/{split}.csvzBhttps://s3.amazonaws.com/kinetics/700_2020/annotations/{split}.csvrtrainNr avimp4FrTCHW.)rootframes_per_clip num_classessplit frame_ratestep_between_clips transform extensionsdownloadnum_download_workers num_workers_precomputed_metadata _video_width _video_height_video_min_dimension_audio_samples_audio_channels_legacy output_formatrcst|dgdd|_||_| |_||_||_|rVtd||_d|_d}| rxt dn"t |||_t|dgd d|_| r| t |jt|j\|_}t|j||dd |_d d |jD}t||||| | | |||||d |_||_dS)Nr&r)arg valid_valueszUsing legacy structureunknownTHWCz2Cannot download the videos using legacy_structure.r')rvaltest) is_valid_filecSsg|] }|dqS)rr).0xrrr z%Kinetics.__init__..)r.r0r1r2r3r4r6)rr&r+r-r$r5print split_folderr' ValueErrorrjoindownload_and_process_videossuper__init__r classesr samplesr video_clipsr*)selfr$r%r&r'r(r)r*r+r,r-r.r/r0r1r2r3r4r5r6 class_to_idx video_list __class__rrrH\sF zKinetics.__init__)rcCsbt}|t}td||d|t}td||dtd||ddS)zEDownloads all the videos to the _root_ folder in the expected format.z%Elapsed time for downloading in mins <z$Elapsed time for processing in mins zElapsed time overall in mins N)time_download_videosrB_make_ds_structure)rLticZtocZtoc2rrrrFsz$Kinetics.download_and_process_videosc Cst|jrtd|jdt|jd}t|jd}|j|jj|j d}t|t |}t |stt ||t |&}dd|D}Wdn1s0Y|jd kr|D]}t|||jqn$tt||j}t|j} | ||dS) adownload tarballs containing the video to "tars" folder and extract them into the _split_ folder where split is one of the official dataset splits. Raises: RuntimeError: if download folder exists, break to prevent downloading entire dataset again. zThe directory z[ already exists. If you want to re-download or re-extract the images, delete the directory.Ztarsfilesr'cSsg|]}tjj|ddqS)z/,:)safe)urllibparsequote)r>rrrrr@rAz-Kinetics._download_videos..Nr )rexistsrC RuntimeErrorrEr$ _TAR_URLSr&formatr'basenamerropenread splitlinesr-rrrrmap) rLZtar_pathZfile_list_path split_urlZsplit_url_filepathfileZlist_video_urlsrpartZpoolprocrrrrSs$    4  zKinetics._download_videosc Cs0t|jd}tt||jdsBt|j|jj|jd|t||jd}d}t |}t |}|D]}|j|dt |dt |dd}|d  d d  d d  dd  dd }tjt|j|ddt|j|} t| rrt | t|j||qrWdn1s"0YdS)umove videos from split_folder/ ├── clip1.avi ├── clip2.avi to the correct format as described below: split_folder/ ├── class1 │ ├── clip1.avi annotationsz.csvrWz{ytid}_{start:06}_{end:06}.mp4Z youtube_idZ time_startZtime_end)Zytidstartendlabel _'()T)exist_okN)rrEr$rr'r_ANNOTATION_URLSr&r_racsv DictReaderintreplaceosmakedirsrCisfile) rLannotation_pathrhZ file_fmtstrZcsvfilereaderrowfrkZdownloaded_filerrrrTs*     ( zKinetics._make_ds_structurecCs|jjSr)rKmetadatarLrrrrszKinetics.metadatacCs |jSr)rK num_clipsrrrr__len__szKinetics.__len__)idxrcCs@|j|\}}}}|j|d}|jdur6||}|||fS)Nr )rKget_cliprJr*)rLrvideoaudioinfo video_idxrkrrr __getitem__s   zKinetics.__getitem__)rrNr Nr Fr r NrrrrrFr#)__name__ __module__ __qualname____doc__r^rsstrrvrrr boolrrrHrFrSrTpropertyrrr r __classcell__rrrOrrsn:  B #rc s6eZdZdZdeeeeeeeddfdd ZZS) Kinetics400u `Kinetics-400 `_ dataset. .. warning:: This class was deprecated in ``0.12`` and will be removed in ``0.14``. Please use ``Kinetics(..., num_classes='400')`` instead. Kinetics-400 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``. 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 (string): Root directory of the Kinetics-400 Dataset. Should be structured as follows: .. code:: root/ ├── class1 │ ├── clip1.avi │ ├── clip2.avi │ ├── clip3.mp4 │ └── ... └── class2 ├── clipx.avi └── ... frames_per_clip (int): number of frames in a clip step_between_clips (int): number of frames between each clip transform (callable, optional): A function/transform that takes in a TxHxWxC video and returns a transformed version. Returns: tuple: A 3-tuple with the following entries: - video (Tensor[T, H, W, C]): 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 N)r$r%r&r'r,r-kwargsrc sJtdtdd||||fDr,tdtjf||dd|dS)NzThe Kinetics400 class is deprecated since 0.12 and will be removed in 0.14.Please use Kinetics(..., num_classes='400') instead.Note that Kinetics(..., num_classes='400') returns video in a Tensor[T, C, H, W] format.css|]}|duVqdSrr)r>valuerrr =rAz'Kinetics400.__init__..zUsage of 'num_classes', 'split', 'download', or 'num_download_workers' is not supported in Kinetics400. Please use Kinetics instead.T)r$r%r5)warningswarnanyr]rGrH)rLr$r%r&r'r,r-rrOrrrH.s zKinetics400.__init__)NNNN) rrrrrrvrrHrrrrOrrs6r)"rtrxrRrYr functoolsrmultiprocessingrrtypingrrrrr torchr folderr r utilsrrrr video_utilsrvisionrrrrrrrrrs"      e