a d:= @s(ddlZddlZddlZddlZddlZddlmZddlmZm Z m Z m Z m Z m Z ddlZddlZddlmZddlmZz4ddlZejejjeejjjdsed ZWneyed ZYn0dd d d Zed ddZ da!da"d,e#ej$e%e#e e e#efe ej$e e%e e#e e e#efdd ddZ&de%e%e#de e#e e e'e e'dfe e'ffe ddddZ(ej$e de'e%ej$dddZ)d-e#e e%efe e e%efe#e#e ej$ej$e e#effd!d"d#Z*ded$d%d&Z+de e'd$d'd(Z,d.e#e#e e e'e e%fd)d*d+Z-dS)/N)Fraction)AnyDictListOptionalTupleUnion)_log_api_usage_once) _video_opt pict_typea+Your version of PyAV is too old for the necessary video operations in torchvision. If you are on Python 3.5, you will have to build from source (the conda-forge packages are not up-to-date). See https://github.com/mikeboers/PyAV#installation for instructions on how to install PyAV on your system. zPyAV is not installed, and is necessary for the video operations in torchvision. See https://github.com/mikeboers/PyAV#installation for instructions on how to install PyAV on your system. )returncCstttrtdSN isinstanceav Exceptionrr]/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/torchvision/io/video.py_check_av_available's rcCs ttt Srrrrrr _av_available,sr libx264) filename video_arrayfps video_codecoptions audio_array audio_fps audio_codec audio_optionsrc  Cstjstjsttttj|tjd }t |t rJt |}tj|dd} | j||d} |jd| _|jd| _|dkrdnd | _|pi| _|d urtd d d d d d ddddd } | j||d} |pi| _|jd} | dkrdnd}| jjdjj}t | |}t| |}tjj|||d}||_| |D]}| |qH| D]}| |qb|D]8}tj!j|d d}d|_"| |D]}| |qqx| D]}| |qWd n1s0Yd S)a| Writes a 4d tensor in [T, H, W, C] format in a video file Args: filename (str): path where the video will be saved video_array (Tensor[T, H, W, C]): tensor containing the individual frames, as a uint8 tensor in [T, H, W, C] format fps (Number): video frames per second video_codec (str): the name of the video codec, i.e. "libx264", "h264", etc. options (Dict): dictionary containing options to be passed into the PyAV video stream audio_array (Tensor[C, N]): tensor containing the audio, where C is the number of channels and N is the number of samples audio_fps (Number): audio sample rate, typically 44100 or 48000 audio_codec (str): the name of the audio codec, i.e. "mp3", "aac", etc. audio_options (Dict): dictionary containing options to be passed into the PyAV audio stream dtypew)mode)rater r Z libx264rgbZyuv420pZrgb24Nzz%_read_from_stream..csg|]}|kr|qSrrrQ)rErrrVrW) _CALLED_TIMES_GC_COLLECTION_INTERVALgcZcollectintmathfloor time_baser4ceilwarningswarntype codec_context extradatafindresearchgroupmaxseekrAVError enumeratedecoderPsortedleninsert)r@rErFrGrArHZ should_buffermax_buffer_sizerdposdoZ seek_offsetZ buffer_countZ_idxrBresultZpreceding_framesZfirst_frame_ptsrrTr_read_from_streams^            "rv)aframes audio_frames ref_startref_endrc Cs||dj|dj}}|jd}||d|}d}|} ||krPt|||}||krht|||} |dd|| fS)Nrr )rPr8r[) rwrxryrzstartendZ total_aframesZstep_per_aframeZs_idxZe_idxrrr_align_audio_framess r~rPTHWC)r start_ptsend_ptsrG output_formatrc Cstjstjstt|}|dvrt| |||| jjdddi} | jjdj} | dur>t| |d<| jjrxt| |||| jjdddi} | jjdj|d<Wdn1s0YWntjyYn0dd| D}dd| D}|rtt|}ntj dtj!d}|rft"|d}t|}|dkrVt#t$%|d| }|td krVt#t$&|d| }t'|| ||}ntj dtj(d}|dkr|)dddd}|||fS)a Reads a video from a file, returning both the video frames and the audio frames Args: filename (str): path to the video file start_pts (int if pts_unit = 'pts', float / Fraction if pts_unit = 'sec', optional): The start presentation time of the video end_pts (int if pts_unit = 'pts', float / Fraction if pts_unit = 'sec', optional): The end presentation time pts_unit (str, optional): unit in which start_pts and end_pts values will be interpreted, either 'pts' or 'sec'. Defaults to 'pts'. output_format (str, optional): The format of the output video tensors. Can be either "THWC" (default) or "TCHW". Returns: vframes (Tensor[T, H, W, C] or Tensor[T, C, H, W]): the `T` video frames aframes (Tensor[K, L]): the audio frames, where `K` is the number of channels and `L` is the number of points info (Dict): metadata for the video and audio. Can contain the fields video_fps (float) and audio_fps (int) )rTCHWz5output_format should be either 'THWC' or 'TCHW', got .rget_video_backendzFile not found: pyavNrJz7end_pts should be larger than start_pts, got start_pts=z and end_pts=ignoreZmetadata_errorsrL video_fpsr<r cSsg|]}|qSr)Zto_rgb to_ndarrayrRrBrrrrVDrWzread_video..cSsg|] }|qSr)rrrrrrVErW)rr r rMr#r rI)r rrrMr )*r,r-r.r/r read_videoupper ValueError torchvisionrospathexists RuntimeErrorr Z _read_videorr4Zdefault_timebaserr7r;r<r^rLrv average_rater'rkr1r5stackemptyr2Z concatenater[r\r]r_r~float32Zpermute)rrrrGrrZvframesrwinfoZ video_framesrxZaudio_timebaser@rZ vframes_listZ aframes_listrrrrs         6    r)r@rcCs*|jdjj}|durdSd|vr&dSdS)NrFsLavcT)r;rcrd)r@rdrrr!_can_read_timestamps_from_packets^s rcCs8t|rdd|jddDSdd|jddDSdS)NcSsg|]}|jdur|jqSrrOrRxrrrrVjrWz,_decode_video_timestamps..r)rLcSsg|]}|jdur|jqSrrOrrrrrVlrW)rZdemuxrm)r@rrr_decode_video_timestampsgsr)rrGrc sFtjstjsttddlm}|dkr>t ||St d}g}zt j |ddf}|j jr|j jd}|jz t|}Wn$t jytd|Yn0t|j}Wdn1s0YWnDt jy}z(d|d |}t|tWYd}~n d}~00||d kr>fd d |D}||fS) a  List the video frames timestamps. Note that the function decodes the whole video frame-by-frame. Args: filename (str): path to the video file pts_unit (str, optional): unit in which timestamp values will be returned either 'pts' or 'sec'. Defaults to 'pts'. Returns: pts (List[int] if pts_unit = 'pts', List[Fraction] if pts_unit = 'sec'): presentation timestamps for each one of the frames in the video. video_fps (float, optional): the frame rate for the video rrrNrrz Failed decoding frames for file zFailed to open container for z; Caught error: rIcsg|] }|qSrrrZvideo_time_baserrrVrWz)read_video_timestamps..)r,r-r.r/r read_video_timestampsrrr Z_read_video_timestampsrrr7r;rLr^rrkr`rar4rRuntimeWarningsort) rrGrrrPr@Z video_streamemsgrrrros2     ," r)rNNNNN)rNrPr)rP).rZr\rrfr`Z fractionsrtypingrrrrrrr3r5r,utilsr r rloggingZ set_levelERRORhasattrrLrBr? ImportErrorrboolrrXrYstrZTensorr4r0r[rvr~rrrrrrrrs       Y$ Q   r