ёis4BSSKJr SSKJr SSKrSSKJrJr SSKJr SSK J r J r SSK J r SS KJr SS KJr SS KJrJr \(aSS KJr SS KJrJr /rSSSjjrSSSjjrSSSjjrSSSjjrg)) annotations) TYPE_CHECKINGN)_C_opsin_dynamic_mode) grid_sample)in_dynamic_or_pir_mode in_pir_mode)check_variable_and_dtype) LayerHelper)Variable)get_cudnn_versionis_compiled_with_rocm)Tensor) DataLayout2D ShapeLikec [U[[RR45(d [ S5e[ 5nUbUS:a U(aSnOSnURSS:XaSn[5(aSn[R"S/5RSS5(aSn[5(a[U[5(aUR5OUn[U[R5(aURS :Xa [S 5eUR!U5n["R$"XU5$['5(a["R$"UUU5$[)S0[+5D6n[-US S S/S 5 UR/UR0S9nSU0n X%S.n [U[5(aXS'[-USS/S 5 OXS'UR3S U SU0[5U 5S :XaSOU S9 U$)a It generates a grid of (x,y) or (x,y,z) coordinates using the parameters of the affine transformation that correspond to a set of points where the input feature map should be sampled to produce the transformed output feature map. Args: theta (Tensor): A tensor with shape [N, 2, 3] or [N, 3, 4]. It contains a batch of affine transform parameters. The data type can be float32 or float64. out_shape (Tensor | list | tuple): Type can be a 1-D Tensor, list, or tuple. It is used to represent the shape of the output in an affine transformation, in the format ``[N, C, H, W]`` or ``[N, C, D, H, W]``. When the format is ``[N, C, H, W]``, it represents the batch size, number of channels, height and width. When the format is ``[N, C, D, H, W]``, it represents the batch size, number of channels, depth, height and width. The data type must be int32. align_corners(bool, optional): if True, aligns the centers of the 4 (4D) or 8 (5D) corner pixels of the input and output tensors, and preserves the value of the corner pixels. Default: True name(str|None, optional): The default value is None. Normally there is no need for user to set this property. For more information, please refer to :ref:`api_guide_Name`. Returns: Tensor, A Tensor with shape [batch_size, H, W, 2] or [batch, D, H, W, 3] while ('D')'H', 'W' are the (depth)height, width of feature map in affine transformation. The data type is the same as `theta`. Examples: .. code-block:: python >>> import paddle >>> import paddle.nn.functional as F >>> # theta.shape = [1, 2, 3] >>> theta = paddle.to_tensor([[[-0.7, -0.4, 0.3], ... [ 0.6, 0.5, 1.5]]], dtype="float32") >>> y_t = F.affine_grid( ... theta, ... [1, 2, 3, 3], ... align_corners=False ... ) >>> print(y_t) Tensor(shape=[1, 3, 3, 2], dtype=float32, place=Place(cpu), stop_gradient=True, [[[[ 1.03333330, 0.76666665], [ 0.56666672, 1.16666663], [ 0.10000002, 1.56666672]], [[ 0.76666665, 1.09999990], [ 0.30000001, 1.50000000], [-0.16666666, 1.90000010]], [[ 0.50000000, 1.43333328], [ 0.03333333, 1.83333337], [-0.43333334, 2.23333335]]]]) zThe theta should be a Tensor.NipTFr $FLAGS_use_accuracy_compatible_kernelrzThe out_shape cannot be empty. affine_gridthetafloat32float64dtypeTheta) align_corners use_cudnn OutputShape out_shapeint32 output_shapeOutputtypeinputsoutputsattrs)r) isinstancer paddlepirValue TypeErrorrshaper get_flagsgetrtolistrsize ValueError _use_gpudnnrrr r localsr "create_variable_for_type_inferencer append_oplen) rr rname cudnn_versionr _out_shapehelperoutr&r(s [/var/www/html/banglarbhumi/venv/lib/python3.13/site-packages/paddle/nn/functional/vision.pyrr'sd eh (8(89 : :788%'M ]d%:}   {{1~   ?@AEE. ",Y"A"AI   y  j&-- 0 0Z__5I=> >!!),!!%]CC !!     7fh7 7Y 2M 77ekk7J5!"/H i * *$-= ! $; = %.. !sOe*/$u   cf[U[5(d [S5eUS;a[SUS35e[ 5(a[ R "XU5$[S 0[5D6n[US/SQS5 URURS9nURSS U0S U0UUS .S 9 U$)a This API implements pixel shuffle operation. See more details in :ref:`PixelShuffle ` . Parameters: x(Tensor): 4-D tensor, the data type should be float32 or float64. upscale_factor(int): factor to increase spatial resolution. data_format (str, optional): The data format of the input and output data. An optional string from: ``"NCHW"``, ``"NHWC"``. When it is ``"NCHW"``, the data is stored in the order of: [batch_size, input_channels, input_height, input_width]. Default: ``"NCHW"``. name (str|None, optional): Name for the operation (optional, default is None). For more information, please refer to :ref:`api_guide_Name`. Returns: Out(tensor): Reshaped tensor according to the new dimension. Examples: .. code-block:: pycon >>> import paddle >>> import paddle.nn.functional as F >>> x = paddle.randn(shape=[2, 9, 4, 4]) >>> out_var = F.pixel_shuffle(x, 3) >>> print(out_var.shape) paddle.Size([2, 1, 12, 12]) zupscale factor must be int typeNCHWNHWCLAttr(data_format) should be 'NCHW' or 'NHWC'.But receive Attr(data_format):  pixel_shufflex)float16rrrXOut)upscale_factor data_formatr$)rF) r)intr-r3rrrFr r5r r6rr7)rGrKrLr9r<r=s r>rFrFs> nc * *9::** ..9]! =  ##A{CC99 s5 77agg7F 8CL"0*   r?c[UR5S:wa[SUR35e[U[5(d [ S5eUS::a [S5eUS;a[SUS35e[ 5(a[R"XU5$[S0[5D6n[US /S QS 5 URURS 9nURS S U0SU0UUS.S9 U$)a2 This API implements pixel unshuffle operation. See more details in :ref:`PixelUnShuffle ` . Parameters: x (Tensor): 4-D tensor, the data type should be float32 or float64. downscale_factor (int): Factor to decrease spatial resolution. data_format (str, optional): The data format of the input and output data. An optional string of ``'NCHW'`` or ``'NHWC'``. When it is ``'NCHW'``, the data is stored in the order of [batch_size, input_channels, input_height, input_width]. Default: ``'NCHW'``. name (str|None, optional): Name for the operation (optional, default is None). Normally there is no need for user to set this property. For more information, please refer to :ref:`api_guide_Name`. Returns: Out (Tensor): Reshaped tensor according to the new dimension. Examples: .. code-block:: pycon >>> import paddle >>> import paddle.nn.functional as F >>> x = paddle.randn([2, 1, 12, 12]) >>> out = F.pixel_unshuffle(x, 3) >>> print(out.shape) paddle.Size([2, 9, 4, 4]) >Input x should be 4D tensor, but received x with the shape of z!Downscale factor must be int typerz!Downscale factor must be positiverArDrEpixel_unshufflerG)rHrruint16rrIrJ)downscale_factorrLr$)rQ)r8r.r3r)rMr-rrrQr r5r r6rr7)rGrSrLr9r<r=s r>rQrQs: 177|qLQWWI V   & , ,;<<1<==** ..9]! =  %%a;GG  7fh 7F 3;=N  3 3!'' 3 BC  Qx 0&  Jr?c[UR5S:wa[SUR35e[U[5(d [ S5eUS::a [S5eUS;a[SUS35e[ 5(a[R"XU5$[S0[5D6n[US S S /S 5 URURS 9nURS SU0SU0XS.S9 U$)a This API implements channel shuffle operation. See more details in :ref:`api_paddle_nn_ChannelShuffle`. Parameters: x (Tensor): 4-D tensor, the data type should be float32 or float64. groups (int): Number of groups to divide channels in. data_format (str, optional): The data format of the input and output data. An optional string of NCHW or NHWC. The default is NCHW. When it is NCHW, the data is stored in the order of [batch_size, input_channels, input_height, input_width]. name (str|None, optional): Name for the operation (optional, default is None). Normally there is no need for user to set this property. For more information, please refer to :ref:`api_guide_Name`. Returns: Out (Tensor): Rearranged tensor keeping the original tensor shape. Examples: .. code-block:: python >>> import paddle >>> import paddle.nn.functional as F >>> x = paddle.arange(0, 0.6, 0.1, 'float32') >>> x = paddle.reshape(x, [1, 6, 1, 1]) >>> print(x) Tensor(shape=[1, 6, 1, 1], dtype=float32, place=Place(cpu), stop_gradient=True, [[[[0. ]], [[0.10000000]], [[0.20000000]], [[0.30000001]], [[0.40000001]], [[0.50000000]]]]) >>> y = F.channel_shuffle(x, 3) >>> print(y) Tensor(shape=[1, 6, 1, 1], dtype=float32, place=Place(cpu), stop_gradient=True, [[[[0. ]], [[0.20000000]], [[0.40000001]], [[0.10000000]], [[0.30000001]], [[0.50000000]]]]) rOrPzgroups must be int typerzgroups must be positiverArDrEchannel_shufflerGrrrrIrJ)groupsrLr$)rU)r8r.r3r)rMr-rrrUr r5r r6rr7)rGrVrLr9r<r=s r>rUrUsX 177|qLQWWI V   fc " "122 {233** ..9]! =  %%a==  7fh 7FQi%;=NO  3 3!'' 3 BC  Qx <  Jr?)TN) rrr rrboolr9 str | Nonereturnr)rBN) rGrrKrMrLrr9rXrYr) rGrrSrMrLrr9rXrYr) rGrrVrMrLrr9rXrYr) __future__rtypingrr*rr paddle._C_opsrpaddle.base.frameworkrr base.data_feederr base.layer_helperr common_ops_importr devicerrrpaddle._typingrr__all__rrFrQrUr?r>res2# *% 9,)>6   j jjj  j  j`!' 8 888  8  8|!' ? ???  ?  ?J!' I I II  I  Ir?