6biNSrSSKrSSKrSSKJs Jr SSKJ r Sr SSjr SSjr Sr SSjrS rS rS rS rS rSrSrg)z%Utilities used by convolution layers.N)backendcUS:Xa$US:XagUS:XagUS:Xag[SUS 35eUS :Xa$US:Xag US:Xag US:Xag [SUS 35e[SUS35e)N channels_lastNWCNHWCNDHWCzInput rank not supported: z. Expected values are [3, 4, 5]channels_firstNCWNCHWNCDHWzInvalid data_format: z9. Expected values are ["channels_first", "channels_last"]) ValueError) data_formatndims W/home/james-whalen/.local/lib/python3.13/site-packages/tf_keras/src/utils/conv_utils.pyconvert_data_formatrso% 19 QY QY,TF300  ( ( 19 QY QY,TF300  #K=1F F  c .SUSUSU3n[U[5(aU4U-nO;[U5n[ U5U:wa [ U5eUHn[U5 M U(aUVs1sH owS:dM UiM nnSn OUVs1sH owS::dM UiM nnSn U(aUS US U S 3- n[ U5eU$![a [ U5ef=f![[4a USUS[ U53- n[ U5ef=fs snfs snf) a[Transforms non-negative/positive integer/integers into an integer tuple. Args: value: The value to validate and convert. Could an int, or any iterable of ints. n: The size of the tuple to be returned. name: The name of the argument being validated, e.g. "strides" or "kernel_size". This is only used to format error messages. allow_zero: A ValueError will be raised if zero is received and this param is False. Defaults to `False`. Returns: A tuple of n integers. Raises: ValueError: If something else than an int/long or iterable thereof or a negative value is passed. zThe `z` argument must be a tuple of z integers. Received: zincluding element z of type rz>= 0z> 0z including z( that does not satisfy the requirement `z`.) isinstanceinttuple TypeErrorrlentype) valuenname allow_zero error_msg value_tuple single_valuevunqualified_valuesreq_msgs rnormalize_tupler'9sf* v3A37$g ' %hl  (,K { q Y' ''L ,L!()4>AAa>)4?AQa?,-6wir C ## 9 (Y' ' ( * ,(7 ./1 !++  ,?@s/ C C. D ;D  DDC0D cUcgUS;deXS- US- --nUS;aUnOUS:XaX- S-nO US:XaX-S- nWU-S- U-$)aDetermines output length of a convolution given input length. Args: input_length: integer. filter_size: integer. padding: one of "same", "valid", "full", "causal" stride: integer. dilation: dilation rate, integer. Returns: The output length (integer). N>fullsamevalidcausal)r*r,r+r)) input_length filter_sizepaddingstridedilationdilated_filter_size output_lengths rconv_output_lengthr6vs 9 99 9%qX\(JJ$$$ G $:Q> F $:Q> F "Q &6 11rc|UcgUS;deUS:XaUS-nOUS:XaSnO US:XaUS- nUS- U-SW-- U-$) zDetermines input length of a convolution given output length. Args: output_length: integer. filter_size: integer. padding: one of "same", "valid", "full". stride: integer. Returns: The input length (integer). N>r)r*r+r*r+rr)r-r.)r5r0r1r2pads rconv_input_lengthr:sj / // /&Q G  F Ao A  '!c' 1K ??rcUS;deUcgXS- US- --nUc;US:XaX-[X- S5-nU$US:XaX-XA-S- - nU$US:XaX-nW$US:XaUS-nOUS:XaSnO US:XaUS- nUS- U-U-SW-- U-nU$) aDetermines output length of a transposed convolution given input length. Args: input_length: Integer. filter_size: Integer. padding: one of `"same"`, `"valid"`, `"full"`. output_padding: Integer, amount of padding along the output dimension. Can be set to `None` in which case the output length is inferred. stride: Integer. dilation: Integer. Returns: The output length (integer). >r)r*r+Nr-r+rr)r8r*)max)r/r0r1output_paddingr2r3lengthr9s rdeconv_output_lengthr?s, / // /qX\ BBK g !*S1Eq-IIF" M! !*f.BQ.FGF M !*F M f "C  C  /CA  '+ 5C ?. P  Mrc~Uc[R"5nUR5nUS;a[SU35eU$)N>rr zWThe `data_format` argument must be one of "channels_first", "channels_last". Received: )rimage_data_formatlowerr)rrs rnormalize_data_formatrCsN }))+++-K== <r*r+r,zqThe `padding` argument must be a list/tuple or one of "valid", "same" (or "causal", only for `Conv1D). Received: )rlistrrBr)rr1s rnormalize_paddingrFsO%$'' kkmG11   #  Nrc@US;a[SUS35e[U5n[U[5(aU4U-n[U[5(aU4U-n[U5n[U5nXT:wdXd:wa[ SUSUSU35e[ XX#5nX-n[ R"U[5n UV s/sHn [U 5PM n n [R"U 6H1n [XXU5n [R"U 6H nSXU -'M M3 U $s sn f)aCompute a mask representing the connectivity of a convolution operation. Assume a convolution with given parameters is applied to an input having N spatial dimensions with `input_shape = (d_in1, ..., d_inN)` to produce an output with shape `(d_out1, ..., d_outN)`. This method returns a boolean array of shape `(d_in1, ..., d_inN, d_out1, ..., d_outN)` with `True` entries indicating pairs of input and output locations that are connected by a weight. Example: >>> input_shape = (4,) >>> kernel_shape = (2,) >>> strides = (1,) >>> padding = "valid" >>> conv_kernel_mask(input_shape, kernel_shape, strides, padding) array([[ True, False, False], [ True, True, False], [False, True, True], [False, False, True]]) where rows and columns correspond to inputs and outputs respectively. Args: input_shape: tuple of size N: `(d_in1, ..., d_inN)`, spatial shape of the input. kernel_shape: tuple of size N, spatial shape of the convolutional kernel / receptive field. strides: tuple of size N, strides along each spatial dimension. padding: type of padding, string `"same"` or `"valid"`. `"valid"` means no padding. `"same"` results in padding evenly to the left/right or up/down of the input such that output has the same height/width dimension as the input. Returns: A boolean 2N-D `np.ndarray` of shape `(d_in1, ..., d_inN, d_out1, ..., d_outN)`, where `(d_out1, ..., d_outN)` is the spatial shape of the output. `True` entries in the mask represent pairs of input-output locations that are connected by a weight. Raises: ValueError: if `input_shape`, `kernel_shape` and `strides` don't have the same number of dimensions. NotImplementedError: if `padding` is not in {`"same"`, `"valid"`}. >r*r+ Padding type 8 not supported. Only "valid" and "same" are implemented.UNumber of strides, input and kernel dimensions must all match. Received: stride_dims= , in_dims=, kernel_dims=T) NotImplementedErrorrrrrconv_output_shapenpzerosboolrange itertoolsproductconv_connected_inputs) input_shape kernel_shapestridesr1in_dims kernel_dims stride_dims output_shape mask_shapemaskdimoutput_axes_ticksoutput_positioninput_axes_ticksinput_positions rconv_kernel_maskrdsS^''!G9%7 7  +G,$$$0 '3*w&l#Kg,K!7 ,,7=9i~k] <  %7L+J 88J %D/;<|s|<$,,.?@0  (//1ABN59D/1 2C A K=s:Dc ## US;a[SUS35e[U5n[U[5(aU4U-n[U[5(aU4U-n[U5n[U5n X:wdX:wa[ SU SUSU35e[ XX#5n U V s/sHn [ U 5PM n n US:XaSn OUS :XaS n O[ S US 35e[R"U 6Hn[XXU5n[R"U6Hqn[ U5H_n[ U5HMn[R"U "UU5U "X5S 9n[R"U "UU5U "X5S 9nUU4v MO Ma Ms M gs sn f7f)aYields output-input tuples of indices in a CNN layer. The generator iterates over all `(output_idx, input_idx)` tuples, where `output_idx` is an integer index in a flattened tensor representing a single output image of a convolutional layer that is connected (via the layer weights) to the respective single input image at `input_idx` Example: >>> input_shape = (2, 2) >>> kernel_shape = (2, 1) >>> strides = (1, 1) >>> padding = "valid" >>> filters_in = 1 >>> filters_out = 1 >>> data_format = "channels_last" >>> list(conv_kernel_idxs(input_shape, kernel_shape, strides, padding, ... filters_in, filters_out, data_format)) [(0, 0), (0, 2), (1, 1), (1, 3)] Args: input_shape: tuple of size N: `(d_in1, ..., d_inN)`, spatial shape of the input. kernel_shape: tuple of size N, spatial shape of the convolutional kernel / receptive field. strides: tuple of size N, strides along each spatial dimension. padding: type of padding, string `"same"` or `"valid"`. `"valid"` means no padding. `"same"` results in padding evenly to the left/right or up/down of the input such that output has the same height/width dimension as the input. filters_in: `int`, number if filters in the input to the layer. filters_out: `int', number if filters in the output of the layer. data_format: string, "channels_first" or "channels_last". Yields: The next tuple `(output_idx, input_idx)`, where `output_idx` is an integer index in a flattened tensor representing a single output image of a convolutional layer that is connected (via the layer weights) to the respective single input image at `input_idx`. Raises: ValueError: if `data_format` is neither `"channels_last"` nor `"channels_first"`, or if number of strides, input, and kernel number of dimensions do not match. NotImplementedError: if `padding` is neither `"same"` nor `"valid"`. )r*r+rHrIrJrKrLr cU4U-$Nr. spatial_idx filter_idxs r"conv_kernel_idxs..s ZMK,GrrcUU4-$rgr.rhs rrkrlsk E 7 rz Data format `zK` not recognized.`data_format` must be "channels_first" or "channels_last".) multi_indexdimsN) rMrrrrrNrRrSrTrUrOravel_multi_index)rVrWrXr1 filters_in filters_outrrYrZr[r\r_r` concat_idxsrarbrcf_inf_outout_idxin_idxs rconv_kernel_idxsrxKsp''!G9%7 7  +G,$$$0 '3*w&l#Kg,K!7 ,,7=9i~k] <  %7L0<<|s|<&& G   ' K=)I I  %,,.?@0  (//1ABNj)";/E 22$/$G(CG 11$/$E(AF#F++0*C A!=sBF F2CF c/n[U5n[U5Hen[XS- 5nXU- n X'X7-n US:XaX- n [SX- 5n [ XX-5n UR [X55 Mg U$)aReturn locations of the input connected to an output position. Assume a convolution with given parameters is applied to an input having N spatial dimensions with `input_shape = (d_in1, ..., d_inN)`. This method returns N ranges specifying the input region that was convolved with the kernel to produce the output at position `output_position = (p_out1, ..., p_outN)`. Example: >>> input_shape = (4, 4) >>> kernel_shape = (2, 1) >>> output_position = (1, 1) >>> strides = (1, 1) >>> padding = "valid" >>> conv_connected_inputs(input_shape, kernel_shape, output_position, ... strides, padding) [range(1, 3), range(1, 2)] Args: input_shape: tuple of size N: `(d_in1, ..., d_inN)`, spatial shape of the input. kernel_shape: tuple of size N, spatial shape of the convolutional kernel / receptive field. output_position: tuple of size N: `(p_out1, ..., p_outN)`, a single position in the output of the convolution. strides: tuple of size N, strides along each spatial dimension. padding: type of padding, string `"same"` or `"valid"`. `"valid"` means no padding. `"same"` results in padding evenly to the left/right or up/down of the input such that output has the same height/width dimension as the input. Returns: N ranges `[[p_in_left1, ..., p_in_right1], ..., [p_in_leftN, ..., p_in_rightN]]` specifying the region in the input connected to output_position. r8r+r)rrRrr<minappend) rVrWrarXr1rangesndimsd left_shift right_shiftcenterstartends rrUrUsPF  E 5\1,- "o 2  #gj0 g   FAv*++.&"67 eE'( Mrc [[U55nUVs/sHn[XXX2U5PM nn[UVs/sHoPUS:XaSOXePM sn5nU$s snfs snf)aReturn the output shape of an N-D convolution. Forces dimensions where input is empty (size 0) to remain empty. Args: input_shape: tuple of size N: `(d_in1, ..., d_inN)`, spatial shape of the input. kernel_shape: tuple of size N, spatial shape of the convolutional kernel / receptive field. strides: tuple of size N, strides along each spatial dimension. padding: type of padding, string `"same"` or `"valid"`. `"valid"` means no padding. `"same"` results in padding evenly to the left/right or up/down of the input such that output has the same height/width dimension as the input. Returns: tuple of size N: `(d_out1, ..., d_outN)`, spatial shape of the output. r)rRrr6r)rVrWrXr1ror~r\s rrNrNs& \" #DA ;>> 2 2::cB4+2E2E2G+GHL::RYYk2<L,' &,,j[\://11 hh|4j[\BOjj "))[$BL  cii *- :+,0GGH; - , ,s FF00 F>)F)r-)Nrr-)__doc__rSnumpyrOtensorflow.compat.v2compatv2r tf_keras.srcrrr'r6r:r?rCrFrdrxrUrNrr.rrrsi,!!  @:z24@8  1h  Slo,d9x<.r