o V h@sbddlZddlZedddZddZddZdd d Zd d ZddZdddZ ddZ dS)NzThe 'torchvision.transforms._functional_video' module is deprecated since 0.12 and will be removed in the future. Please use the 'torchvision.transforms.functional' module instead.cCs:t|s tdt||dkstd|dS)Nzclip should be Tensor. Got %szclip should be 4D. Got %dDT)torch is_tensor TypeErrortype ndimension ValueErrordimclipr \/var/www/vscode/kcb/lib/python3.10/site-packages/torchvision/transforms/_functional_video.py_is_tensor_video_clip s  rcCs6t|dkr td|d||||||fS)z[ Args: clip (torch.tensor): Video clip to be cropped. Size is (C, T, H, W) rzclip should be a 4D tensor.)lensizer)r ijhwr r r cropsrcCs0t|dkr td|tjjj|||ddS)Nz9target size should be tuple (height, width), instead got F)rmode align_corners)rrrnn functional interpolate)r target_sizeinterpolation_moder r r resize s rbilinearcCs0t|stdt|||||}t|||}|S)a Do spatial cropping and resizing to the video clip Args: clip (torch.tensor): Video clip to be cropped. Size is (C, T, H, W) i (int): i in (i,j) i.e coordinates of the upper left corner. j (int): j in (i,j) i.e coordinates of the upper left corner. h (int): Height of the cropped region. w (int): Width of the cropped region. size (tuple(int, int)): height and width of resized clip Returns: clip (torch.tensor): Resized and cropped clip. Size is (C, T, H, W) clip should be a 4D torch.tensor)rrrr)r rrrrrrr r r resized_crop&s   r!cCs~t|std|d|d}}|\}}||ks||kr#tdtt||d}tt||d}t|||||S)Nr z2height and width must be no smaller than crop_sizeg@)rrrintroundr)r crop_sizerrthtwrrr r r center_crop:sr)cCs>t||jtjkstdt|j|dddddS)a Convert tensor data type from uint8 to float, divide value by 255.0 and permute the dimensions of clip tensor Args: clip (torch.tensor, dtype=torch.uint8): Size is (T, H, W, C) Return: clip (torch.tensor, dtype=torch.float): Size is (C, T, H, W) z/clip tensor should have data type uint8. Got %srrgo@)rdtyperuint8rstrfloatpermuter r r r to_tensorGs r1FcCsxt|std|s|}tj||j|jd}tj||j|jd}||dddddf|dddddf|S)a Args: clip (torch.tensor): Video clip to be normalized. Size is (C, T, H, W) mean (tuple): pixel RGB mean. Size is (3) std (tuple): pixel standard deviation. Size is (3) Returns: normalized clip (torch.tensor): Size is (C, T, H, W) r )r,deviceN) rrcloner as_tensorr,r2sub_div_)r meanstdinplacer r r normalizeVs 0r:cCst|std|dS)z Args: clip (torch.tensor): Video clip to be normalized. Size is (C, T, H, W) Returns: flipped clip (torch.tensor): Size is (C, T, H, W) r r#)rrflipr r r r hflipis r<)r)F) warningsrwarnrrrr!r)r1r:r<r r r r s