cCiSrSSKJrJr SSKrSSKJr SSKJ r SSK J r J r J r Jr SSKJrJr SS KJr SS KJr SS KJrJrJr "S S \5r"SS\5rS/rg)z(Fast Video processor class for InternVL.)OptionalUnionN) functional) BatchFeature)OPENAI_CLIP_MEANOPENAI_CLIP_STDPILImageResamplingSizeDict)Unpack VideosKwargs) TensorType)BaseVideoProcessor) VideoMetadatagroup_videos_by_shapereorder_videosc,\rSrSr%\\\\4\S'Sr g) InternVLVideoProcessorInitKwargs initial_shiftN) __name__ __module__ __qualname____firstlineno__rboolfloatint__annotations____static_attributes__rp/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/internvl/video_processing_internvl.pyrrsuc)**r!rc^^\rSrSr\R r\r\ r SSS.r Sr Sr SrSrSrSr\rS/rS\\4U4SjjrS S \S \\S \\\\4S \\\\\44S jjrS!S\SS\S\S\S\SS\S\S\S\S\S\\\\\4S\\\\\4S\\\ \!4S\"4Sjjr#Sr$U=r%$)"InternVLVideoProcessor"i)heightwidthTFpixel_values_videoskwargsc &>[TU]"S0UD6 g)Nr)super__init__)selfr) __class__s r"r,InternVLVideoProcessor.__init__0s "6"r!metadata num_framesfpsrc lUbUO URnUbUO URnURnUc8Ub5Ub URc [ S5e[ XaR- U-5nUSLaXb- S- nX&:a[ SUSUS35e[ R"XFXb- 5R 5nU$)a Default sampling function which uniformly samples the desired number of frames between 0 and total number of frames. If `fps` is passed along with metadata, `fps` frames per second are sampled uniformty. Arguments `num_frames` and `fps` are mutually exclusive. Args: metadata (`VideoMetadata`): Metadata of the video containing information about total duration, fps and total number of frames. num_frames (`int`, *optional*): Maximum number of frames to sample. Defaults to `self.num_frames`. fps (`int` or `float`, *optional*): Target frames to sample per second. Defaults to `self.fps`. initial_shift (`bool`, `float` or `int`, defaults to `self.initial_shift`): The initial shift to apply when sampling frames. If `True`, the shift is set so that frames are sampled from the middle of the video. Returns: np.ndarray: Indices to sample video frames. zAsked to sample `fps` frames per second but no video metadata was provided which is required when sampling with `fps`. Please pass in `VideoMetadata` object or use a fixed `num_frames` per input videoTz(Video can't be sampled. The `num_frames=z` exceeds `total_num_frames=z`. )r1rtotal_num_framesr2 ValueErrorrtorcharange)r-r0r1r2rr)r5indicess r" sample_frames$InternVLVideoProcessor.sample_frames3s6$.#9Zt )6)B HZHZ #44  #/8<<#7 h- r?r@rArBrCrDrErFrGrHr)grouped_videosgrouped_videos_indexresized_videos_groupedshapestacked_videosresized_videosprocessed_videos_groupedprocessed_videoss r" _preprocess"InternVLVideoProcessor._preprocessfs $0EV/L,,!#%3%9%9%; !E>!%!4!4^!D!%^$!d,: "5 ) &< ((>@TU0E^/T,,#% %3%9%9%; !E>!%!1!1.)!L!77 LV_N/= $U +&<**BDXYCQ5;;'7Q?Wg"79I!JXfggr!r)NNN)N)&rrrrr BICUBICresamplerrFr rGr?r>rCrEr=rdo_sample_framesr valid_kwargsmodel_input_namesr r,rrrrrrr:listr strrrr\r __classcell__)r.s@r"r$r$"s!))H!JIC (DIJLNM3L./#(H!I# %)+/;? 11SM1eCJ' ( 1  dE3&6 78 1B<@,h^$,h,h ,h  ,h  56 ,h,h,h,h,h,hU5$u+#567,hE%e"456,h!sJ!78,h !,h,hr!r$)__doc__typingrrr7torchvision.transforms.v2rFimage_processing_utilsr image_utilsrr r r processing_utilsr r utilsrvideo_processing_utilsr video_utilsrrrrr$__all__rr!r"rqsS/" 52ZZ48OO+|+ph/phf $ $r!