ёihSSKJr SSKJrJr /rSSKJr SSKJ r SSK J r SSK J r SSKJr SS KJr \(a"SS KJr SS KJr SS KJrJrJrJrJrJr SS KJr SSSjjrSSSjjrSSSjjr SS Sjjr!S!S"Sjjr"S#S$Sjjr#S#S$Sjjr$S%S&Sjjr%S'S(Sjjr&S'S(Sjjr'g))) annotations) TYPE_CHECKINGLiteral)_C_ops) LayerHelper)in_dynamic_or_pir_mode)_update_padding_nd)convert_to_list)add)Sequence)Tensor) DataLayout2D DataLayout3DSize2Size3Size4Size6)_PaddingSizeModeNc US:XdS5eSn U S;a[SU S35e[UR5S:wa[SUR35eU S :Hn U (aS OSn URU n[XLU 5upO[ X;S 5n[ X[S 5n[ 5(a3[ R"UUUUUUUUbUOS 5nUb [UU5$U$XS.nUUUUUUS.nSn[U40[5D6nURSSS9nURSSS9nURUR5nUUUS.nURUUUUS9 Ub [UU5$U$)N Currently, only support groups=1r NDHWCAAttr(data_format) should be 'NDHWC'. Received Attr(data_format): .>Input x should be 5D tensor, but received x with the shape of rstridedilationxkernelpaddings dilationsstridesgroupssubmkey sparse_conv3dint32Tdtype stop_gradientoutrulebookcountertypeinputsoutputsattrs) ValueErrorlenshaper r rrr-r rlocals"create_variable_for_type_inference)create_sparse_variable_for_type_inferencer0 append_opr$weightbiasr paddingr!r*r+r, data_formatnamedims channel_last channel_dim num_channelspadding_algorithmpre_biasr8r:op_typehelperr4r5r9s `/var/www/html/banglarbhumi/venv/lib/python3.13/site-packages/paddle/sparse/nn/functional/conv.py_conv3drQ,s Q;:::; D)# ""-a 1   177|qLQWWI V  ')L$"!K77;'L!3G4!PG V8 4Fxz:H''      ?C    x& &O+!  "W11<<= ;;< CCAGGL"WM    x& &Oc  US:XdS5eSn U S;a[SU S35e[UR5S:wa[SUR35eU S :Hn U (aS OSn [UR5S:wa[SUR35eURU n[XLU 5upO[ X;S 5n[ X[S 5n[ 5(a#[ R"UUUUUUUUbUOS 5nOvXS.nUUUUUUS.nSn[U40[5D6nURSSS9nURSSS9nURUR5nUUUS.nURUUUUS9 Ub [UU5$U$)NrrNHWC@Attr(data_format) should be 'NHWC'. Received Attr(data_format): r>Input x should be 4D tensor, but received x with the shape of rVrr r!r"r#r&r-r.Tr/r2r6)r;r<r=r r rrr-rr>r?r@r0rAr rBs rP_conv2drZ|s Q;:::; D(" ""-a 1   177|qLQWWI V  &(L$"!K 177|qLQWWI V  77;'L!3G4!PG V8 4Fxz:H''      ?C  +!  "W11<<= ;;< CCAGGL"WM   8T""rRc US:XdS5eUSLdS5eSn U S;a[SU S35e[UR5S :wa[S UR35eU S :Hn U (aS OSn [UR5S :wa[S UR35eURU n[XLU 5upO[ X;S 5n[ X[S5n[ 5(a3[ R"UUUUUUUUbUOS5nUb [UU5$U$XS.nUUUUUUS.nSn[U40[5D6nURUR5nSU0nURUUUUS9 Ub [UU5$U$)NrrT3Currently, only support subm=True for implicit gemmr rrrrrrrr r!r"r#r&sparse_conv3d_implicit_gemmr3r6r;r<r=r r rrr]r rr>r@r0rAr$rCrDr rEr!r*r+r,rFrGrHrIrJrKrLrMr8r:rNrOr9s rP _conv3d_igemmr`s Q;:::; 4<NNN< D)# ""-a 1   177|qLQWWI V  ')L$"!K 177|qLQWWI V  77;'L!3G4!PG V8 4Fxz:H55      ?C    x& &O+!  0W11CCAGGL(#    x& &OrRc US:XdS5eUSLdS5eSn U S;a[SU S35e[UR5S :wa[S UR35eU S :Hn U (aS OSn [UR5S :wa[S UR35eURU n[XLU 5upO[ X;S5n[ X[S5n[ 5(a3[ R"UUUUUUUUbUOS5nUb [UU5$U$XS.nUUUUUUS.nSn[U40[5D6nURUR5nSU0nURUUUUS9 Ub [UU5$U$)NrrTr\rTrUrWrrXrrVrrYr r!r"r#r&r]r3r6r^r_s rP _conv2d_igemmrbs Q;:::; 4<NNN< D(" ""-a 1   177|qLQWWI V  &(L$"!K 177|qLQWWI V  77;'L!3G4!PG V8 4Fxz:H55      ?C    x& &O+!  0W11CCAGGL(#    x& &OrRc ,[UUUUUUUSSUU5 $)aQ The sparse convolution3d functional calculates the output based on the input, filter and strides, paddings, dilations, groups parameters. Input(Input) and Output(Output) are multidimensional SparseCooTensors with a shape of :math:`[N, D, H, W, C]` . Where N is batch size, C is the number of channels, D is the depth of the feature, H is the height of the feature, and W is the width of the feature. If bias attribution is provided, bias is added to the output of the convolution. For each input :math:`X`, the equation is: .. math:: Out = \sigma (W \ast X + b) In the above equation: * :math:`X`: Input value, a tensor with NCDHW or NDHWC format. * :math:`W`: Filter value, a tensor with MCDHW format. * :math:`\\ast`: Convolution operation. * :math:`b`: Bias value, a 1-D tensor with shape [M]. * :math:`Out`: Output value, the shape of :math:`Out` and :math:`X` may be different. Args: x (Tensor): The input is 5-D SparseCooTensor with shape [N, D, H, W, C], the data type of input is float16 or float32 or float64. weight (Tensor): The convolution kernel, a Tensor with shape [kD, kH, kW, C/g, M], where M is the number of filters(output channels), g is the number of groups, kD, kH, kW are the filter's depth, height and width respectively. bias (Tensor|None, optional): The bias, a Tensor of shape [M]. stride (int|list|tuple, optional): The stride size. It means the stride in convolution. If stride is a list/tuple, it must contain three integers, (stride_depth, stride_height, stride_width). Otherwise, stride_depth = stride_height = stride_width = stride. Default: stride = 1. padding (string|int|list|tuple, optional): The padding size. It means the number of zero-paddings on both sides for each dimension. If `padding` is a string, either 'VALID' or 'SAME' which is the padding algorithm. If padding size is a tuple or list, it could be in three forms: `[pad_depth, pad_height, pad_width]` or `[pad_depth_front, pad_depth_back, pad_height_top, pad_height_bottom, pad_width_left, pad_width_right]`, and when `data_format` is `"NCDHW"`, `padding` can be in the form `[[0,0], [0,0], [pad_depth_front, pad_depth_back], [pad_height_top, pad_height_bottom], [pad_width_left, pad_width_right]]`. when `data_format` is `"NDHWC"`, `padding` can be in the form `[[0,0], [pad_depth_front, pad_depth_back], [pad_height_top, pad_height_bottom], [pad_width_left, pad_width_right], [0,0]]`. Default: padding = 0. dilation (int|list|tuple, optional): The dilation size. It means the spacing between the kernel points. If dilation is a list/tuple, it must contain three integers, (dilation_depth, dilation_height, dilation_width). Otherwise, dilation_depth = dilation_height = dilation_width = dilation. Default: dilation = 1. groups (int, optional): The groups number of the Conv3D Layer. According to grouped convolution in Alex Krizhevsky's Deep CNN paper: when group=2, the first half of the filters is only connected to the first half of the input channels, while the second half of the filters is only connected to the second half of the input channels. Default: groups=1. Currently, only support groups=1. data_format (str, optional): Specify the data format of the input, and the data format of the output will be consistent with that of the input. An optional string from: `"NCDHW"`, `"NDHWC"`. The default is `"NDHWC"`. When it is `"NDHWC"`, the data is stored in the order of: `[batch_size, input_depth, input_height, input_width, input_channels]`. name(str|None, optional): For detailed information, please refer to :ref:`api_guide_Name`. Usually name is no need to set and None by default. Returns: A SparseCooTensor representing the conv3d, whose data type is the same with input. Examples: .. code-block:: pycon >>> import paddle >>> indices = [ ... [0, 0, 0, 0], ... [0, 0, 0, 0], ... [0, 0, 1, 2], ... [1, 3, 2, 3], ... ] >>> values = [[1], [2], [3], [4]] >>> indices = paddle.to_tensor(indices, dtype='int32') >>> values = paddle.to_tensor(values, dtype='float32') >>> dense_shape = [1, 1, 3, 4, 1] >>> sparse_x = paddle.sparse.sparse_coo_tensor(indices, values, dense_shape, stop_gradient=True) >>> weight = paddle.randn((1, 3, 3, 1, 1), dtype='float32') >>> y = paddle.sparse.nn.functional.conv3d(sparse_x, weight) >>> print(y.shape) paddle.Size([1, 1, 1, 2, 1]) FNrQ r$rCrDr rEr!r*rFrGs rPconv3drfjs3~        rRc ,[UUUUUUUSUUU 5 $a The sparse submanifold convolution3d functional calculates the output based on the input, filter and strides, paddings, dilations, groups parameters. Input(Input) and Output(Output) are multidimensional SparseCooTensors with a shape of :math:`[N, D, H, W, C]` . Where N is batch size, C is the number of channels, D is the depth of the feature, H is the height of the feature, and W is the width of the feature. If bias attribution is provided, bias is added to the output of the convolution. For each input :math:`X`, the equation is: .. math:: Out = W \ast X + b In the above equation: * :math:`X`: Input value, a tensor with NCDHW or NDHWC format. * :math:`W`: Filter value, a tensor with DHWCM format. * :math:`\\ast`: Submanifold Convolution operation, refer to the paper: https://arxiv.org/abs/1706.01307. * :math:`b`: Bias value, a 1-D tensor with shape [M]. * :math:`Out`: Output value, the shape of :math:`Out` and :math:`X` may be different. Args: x (Tensor): The input is 5-D SparseCooTensor with shape [N, D, H, W, C], the data type of input is float16 or float32 or float64. weight (Tensor): The convolution kernel, a Tensor with shape [kD, kH, kW, C/g, M], where M is the number of filters(output channels), g is the number of groups, kD, kH, kW are the filter's depth, height and width respectively. bias (Tensor|None, optional): The bias, a Tensor of shape [M]. stride (int|list|tuple, optional): The stride size. It means the stride in convolution. If stride is a list/tuple, it must contain three integers, (stride_depth, stride_height, stride_width). Otherwise, stride_depth = stride_height = stride_width = stride. Default: stride = 1. padding (string|int|list|tuple): The padding size. It means the number of zero-paddings on both sides for each dimension. If `padding` is a string, either 'VALID' or 'SAME' which is the padding algorithm. If padding size is a tuple or list, it could be in three forms: `[pad_depth, pad_height, pad_width]` or `[pad_depth_front, pad_depth_back, pad_height_top, pad_height_bottom, pad_width_left, pad_width_right]`, and when `data_format` is `"NCDHW"`, `padding` can be in the form `[[0,0], [0,0], [pad_depth_front, pad_depth_back], [pad_height_top, pad_height_bottom], [pad_width_left, pad_width_right]]`. when `data_format` is `"NHWC"`, `padding` can be in the form `[[0,0], [pad_depth_front, pad_depth_back], [pad_height_top, pad_height_bottom], [pad_width_left, pad_width_right], [0,0]]`. Default: padding = 0. dilation (int|list|tuple, optional): The dilation size. It means the spacing between the kernel points. If dilation is a list/tuple, it must contain three integers, (dilation_depth, dilation_height, dilation_width). Otherwise, dilation_depth = dilation_height = dilation_width = dilation. Default: dilation = 1. groups (int, optional): The groups number of the Conv3D Layer. According to grouped convolution in Alex Krizhevsky's Deep CNN paper: when group=2, the first half of the filters is only connected to the first half of the input channels, while the second half of the filters is only connected to the second half of the input channels. Currently, only support groups=1. data_format (str, optional): Specify the data format of the input, and the data format of the output will be consistent with that of the input. An optional string from: `"NCDHW"`, `"NDHWC"`. The default is `"NDHWC"`. When it is `"NDHWC"`, the data is stored in the order of: `[batch_size, input_depth, input_height, input_width, input_channels]`. key(str|None, optional): the key is used to save or use the same rulebook, the definition and role of rulebook refers to https://pdfs.semanticscholar.org/5125/a16039cabc6320c908a4764f32596e018ad3.pdf. The default value is None. name(str|None, optional): For detailed information, please refer to :ref:`api_guide_Name`. Usually name is no need to set and None by default. Returns: A SparseCooTensor representing the conv3d, whose data type is the same with input. Examples: .. code-block:: pycon >>> import paddle >>> indices = [ ... [0, 0, 0, 0], ... [0, 0, 0, 0], ... [0, 0, 1, 2], ... [1, 3, 2, 3], ... ] >>> values = [[1], [2], [3], [4]] >>> indices = paddle.to_tensor(indices, dtype='int32') >>> values = paddle.to_tensor(values, dtype='float32') >>> dense_shape = [1, 1, 3, 4, 1] >>> sparse_x = paddle.sparse.sparse_coo_tensor(indices, values, dense_shape, stop_gradient=True) >>> weight = paddle.randn((1, 3, 3, 1, 1), dtype='float32') >>> y = paddle.sparse.nn.functional.subm_conv3d(sparse_x, weight) >>> print(y.shape) paddle.Size([1, 1, 3, 4, 1]) Trd r$rCrDr rEr!r*rFr,rGs rP subm_conv3drjs3L        rRc ,[UUUUUUUSUUU 5 $rh)r`ris rPsubm_conv3d_igemmrlMs3L        rRc ,[UUUUUUUSSUU5 $)a5 The sparse convolution2d functional calculates the output based on the input, filter and strides, paddings, dilations, groups parameters. Input(Input) and Output(Output) are multidimensional SparseCooTensors with a shape of :math:`[N, H, W, C]` . Where N is batch size, C is the number of channels, H is the height of the feature, and W is the width of the feature. If bias attribution is provided, bias is added to the output of the convolution. For each input :math:`X`, the equation is: .. math:: Out = \sigma (W \ast X + b) In the above equation: * :math:`X`: Input value, a tensor with NHWC format. * :math:`W`: Filter value, a tensor with HWCM format. * :math:`\\ast`: Convolution operation. * :math:`b`: Bias value, a 1-D tensor with shape [M]. * :math:`Out`: Output value, the shape of :math:`Out` and :math:`X` may be different. Args: x (Tensor): The input is 4-D SparseCooTensor with shape [N, H, W, C], the data type of input is float16 or float32 or float64. weight (Tensor): The convolution kernel, a Tensor with shape [kH, kW, C/g, M], where M is the number of filters(output channels), g is the number of groups, kD, kH, kW are the filter's height and width respectively. bias (Tensor|None, optional): The bias, a Tensor of shape [M]. stride (int|list|tuple, optional): The stride size. It means the stride in convolution. If stride is a list/tuple, it must contain two integers, (stride_height, stride_width). Otherwise, stride_height = stride_width = stride. Default: stride = 1. padding (string|int|list|tuple, optional): The padding size. It means the number of zero-paddings on both sides for each dimension. If `padding` is a string, either 'VALID' or 'SAME' which is the padding algorithm. If padding size is a tuple or list, it could be in three forms: `[pad_height, pad_width]` or `[pad_height_top, pad_height_bottom, pad_width_left, pad_width_right]`, when `data_format` is `"NHWC"`, `padding` can be in the form `[[0,0], [pad_height_top, pad_height_bottom], [pad_width_left, pad_width_right], [0,0]]`. Default: padding = 0. dilation (int|list|tuple, optional): The dilation size. It means the spacing between the kernel points. If dilation is a list/tuple, it must contain two integers, (dilation_height, dilation_width). Otherwise, dilation_height = dilation_width = dilation. Default: dilation = 1. groups (int, optional): The groups number of the Conv2D Layer. According to grouped convolution in Alex Krizhevsky's Deep CNN paper: when group=2, the first half of the filters is only connected to the first half of the input channels, while the second half of the filters is only connected to the second half of the input channels. Default: groups=1. Currently, only support groups=1. data_format (str, optional): Specify the data format of the input, and the data format of the output will be consistent with that of the input. An optional string from: `"NHWC"`. The default is `"NHWC"`. When it is `"NHWC"`, the data is stored in the order of: `[batch_size, input_height, input_width, input_channels]`. name(str|None, optional): For detailed information, please refer to :ref:`api_guide_Name`. Usually name is no need to set and None by default. Returns: A SparseCooTensor representing the conv2d, whose data type is the same with input. Examples: .. code-block:: pycon >>> import paddle >>> indices = [[0, 0, 0, 0], [0, 0, 1, 2], [1, 3, 2, 3]] >>> values = [[1], [2], [3], [4]] >>> indices = paddle.to_tensor(indices, dtype='int32') >>> values = paddle.to_tensor(values, dtype='float32') >>> dense_shape = [1, 3, 4, 1] >>> sparse_x = paddle.sparse.sparse_coo_tensor(indices, values, dense_shape, stop_gradient=True) >>> weight = paddle.randn((3, 3, 1, 1), dtype='float32') >>> y = paddle.sparse.nn.functional.conv2d(sparse_x, weight) >>> print(y.shape) paddle.Size([1, 1, 2, 1]) FNrZres rPconv2dros3r        rRc ,[UUUUUUUSUUU 5 $a The sparse submanifold convolution2d functional calculates the output based on the input, filter and strides, paddings, dilations, groups parameters. Input(Input) and Output(Output) are multidimensional SparseCooTensors with a shape of :math:`[N, H, W, C]` . Where N is batch size, C is the number of channels, H is the height of the feature, and W is the width of the feature. If bias attribution is provided, bias is added to the output of the convolution. For each input :math:`X`, the equation is: .. math:: Out = \sigma (W \ast X + b) In the above equation: * :math:`X`: Input value, a tensor with NHWC format. * :math:`W`: Filter value, a tensor with HWCM format. * :math:`\\ast`: Submanifold Convolution operation, refer to the paper: https://arxiv.org/abs/1706.01307. * :math:`b`: Bias value, a 1-D tensor with shape [M]. * :math:`Out`: Output value, the shape of :math:`Out` and :math:`X` may be different. Args: x (Tensor): The input is 4-D SparseCooTensor with shape [N, H, W, C], the data type of input is float16 or float32 or float64. weight (Tensor): The convolution kernel, a Tensor with shape [kH, kW, C/g, M], where M is the number of filters(output channels), g is the number of groups, kD, kH, kW are the filter's height and width respectively. bias (Tensor|None, optional): The bias, a Tensor of shape [M]. stride (int|list|tuple, optional): The stride size. It means the stride in convolution. If stride is a list/tuple, it must contain two integers, (stride_height, stride_width). Otherwise, stride_height = stride_width = stride. Default: stride = 1. padding (string|int|list|tuple, optional): The padding size. It means the number of zero-paddings on both sides for each dimension. If `padding` is a string, either 'VALID' or 'SAME' which is the padding algorithm. If padding size is a tuple or list, it could be in three forms: `[pad_height, pad_width]` or `[pad_height_top, pad_height_bottom, pad_width_left, pad_width_right]`, when `data_format` is `"NHWC"`, `padding` can be in the form `[[0,0], [pad_height_top, pad_height_bottom], [pad_width_left, pad_width_right], [0,0]]`. Default: padding = 0. dilation (int|list|tuple, optional): The dilation size. It means the spacing between the kernel points. If dilation is a list/tuple, it must contain two integers, (dilation_height, dilation_width). Otherwise, dilation_height = dilation_width = dilation. Default: dilation = 1. groups (int, optional): The groups number of the Conv2D Layer. According to grouped convolution in Alex Krizhevsky's Deep CNN paper: when group=2, the first half of the filters is only connected to the first half of the input channels, while the second half of the filters is only connected to the second half of the input channels. Default: groups=1. Currently, only support groups=1. data_format (str, optional): Specify the data format of the input, and the data format of the output will be consistent with that of the input. An optional string from: `"NHWC"`. The default is `"NHWC"`. When it is `"NHWC"`, the data is stored in the order of: `[batch_size, input_height, input_width, input_channels]`. key(str|None, optional): the key is used to save or use the same rulebook, the definition and role of rulebook refers to https://pdfs.semanticscholar.org/5125/a16039cabc6320c908a4764f32596e018ad3.pdf. The default value is None. name(str|None, optional): For detailed information, please refer to :ref:`api_guide_Name`. Usually name is no need to set and None by default. Returns: A SparseCooTensor representing the conv2d, whose data type is the same with input. Examples: .. code-block:: pycon >>> import paddle >>> indices = [[0, 0, 0, 0], [0, 0, 1, 2], [1, 3, 2, 3]] >>> values = [[1], [2], [3], [4]] >>> indices = paddle.to_tensor(indices, dtype='int32') >>> values = paddle.to_tensor(values, dtype='float32') >>> dense_shape = [1, 3, 4, 1] >>> sparse_x = paddle.sparse.sparse_coo_tensor(indices, values, dense_shape, stop_gradient=True) >>> weight = paddle.randn((3, 3, 1, 1), dtype='float32') >>> y = paddle.sparse.nn.functional.subm_conv2d(sparse_x, weight) >>> print(y.shape) paddle.Size([1, 3, 4, 1]) Trnris rP subm_conv2drr*s3|        rRc ,[UUUUUUUSUUU 5 $rq)rbris rPsubm_conv2d_igemmrts3|        rR) NrrrrFNrN)r$rrCrrD Tensor | Noner rrE2_PaddingSizeMode | Size3 | Size6 | Sequence[Size2]r!rr* Literal[1]r+boolr, str | NonerFLiteral['NDHWC']rGryreturnr) NrrrrFNrVN)r$rrCrrDrur rrE2_PaddingSizeMode | Size2 | Size4 | Sequence[Size2]r!rr*rwr+rxr,ryrFLiteral['NHWC']rGryr{r) NrrrrTNrN)r$rrCrrDrur rrErvr!rr*rwr+ Literal[True]r,ryrFrzrGryr{r) NrrrrTNrVN)r$rrCrrDrur rrEr|r!rr*rwr+r~r,ryrFr}rGryr{r)NrrrrrN)r$rrCrrDrur rrErvr!rr*rwrFrrGryr{r)NrrrrrNN)r$rrCrrDrur rrErvr!rr*rwrFrr,ryrGryr{r)NrrrrrVN)r$rrCrrDrur rrEr|r!rr*rwrFrrGryr{r)NrrrrrVNN)r$rrCrrDrur rrEr|r!rr*rwrFrr,ryrGryr{r)( __future__rtypingrr__all__paddlerpaddle.base.layer_helperrpaddle.frameworkrpaddle.nn.functional.convr paddle.utilsr binaryr collections.abcr rpaddle._typingrrrrrrpaddle.nn.functional.commonrrQrZr`rbrfrjrlrorrrtrRrPrs=#) 038((= BC$+M M M M  M @ M  M M M M"M M MfBC#)M M M M  M @ M  M M M M!M M MfBC$+L L L L  L @ L  L L L L"L L LdBC#)L L L L  L @ L  L L L L!L L LdBC 'k k k k  k @ k  k kk k kbBC 'r r r r  r @ r  r rr r r rpBC 'r r r r  r @ r  r rr r r rpBC &e e e e  e @ e  e ee e eVBC &j j j j  j @ j  j jj j j j`BC &j j j j  j @ j  j jj j j jrR