:jF \ddlZddlmZdeddfdZdedeeeffdZdedeeeffdZy)N)Tensorimgreturnct|tstdt||jdk7rt d|jdy)z*Validate whether img is a 4D torch Tensor.z3The `img` expects a value of type but got z&The `img` expects a 4D tensor but got zD tensorN) isinstancer TypeErrortypendim RuntimeErrorrs |/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/torchmetrics/functional/image/gradients.py_image_gradients_validatersM c6 "MdSVi[YZZ xx1}CCHH:XVWWc |j\}}}}|dddddf|dddddfz }|dddddf|dddddfz }||d|g}tj|tj||j|j gd}|j |j}|||dg}tj|tj||j|j gd}|j |j}||fS) z2Compute image gradients (dy/dx) for a given image..N)devicedtype)dim)shapetorchcatzerosrrview) r batch_sizechannelsheightwidthdydxshapeyshapexs r_compute_image_gradientsr&s*-))'J&% S!"aZ3sCRC{+ +B S!QRZ3sAss{+ +B(Au -F B F3::SYYOPVW XB  B(FA .F B F3::SYYOPVW XB  B r6Mrc.t|t|S)aCompute `Gradient Computation of Image`_ of a given image using finite difference. Args: img: An ``(N, C, H, W)`` input tensor where ``C`` is the number of image channels Return: Tuple of ``(dy, dx)`` with each gradient of shape ``[N, C, H, W]`` Raises: TypeError: If ``img`` is not of the type :class:`~torch.Tensor`. RuntimeError: If ``img`` is not a 4D tensor. Example: >>> from torchmetrics.functional.image import image_gradients >>> image = torch.arange(0, 1*1*5*5, dtype=torch.float32) >>> image = torch.reshape(image, (1, 1, 5, 5)) >>> dy, dx = image_gradients(image) >>> dy[0, 0, :, :] tensor([[5., 5., 5., 5., 5.], [5., 5., 5., 5., 5.], [5., 5., 5., 5., 5.], [5., 5., 5., 5., 5.], [0., 0., 0., 0., 0.]]) .. note:: The implementation follows the 1-step finite difference method as followed by the TF implementation. The values are organized such that the gradient of [I(x+1, y)-[I(x, y)]] are at the (x, y) location )rr&r s rimage_gradientsr(-sBc" #C ((r)rrrtupler&r(rrr+s[ X6XdX&U66>-B$#)#)E&&.$9#)r