0hNdZddlZddlZddlmcmZddlm Z dZ ddZ ddZ dZ ddZd Zd Zd Zd Zd ZdZdZy)z%Utilities used by convolution layers.N)backendc|dk(r!|dk(ry|dk(ry|dk(rytd|d |d k(r!|dk(ry |dk(ry |dk(ry td|d td|d)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/var/www/html/engine/venv/lib/python3.12/site-packages/tf_keras/src/utils/conv_utils.pyconvert_data_formatrso% 19 QY QY,TF300  ( ( 19 QY QY,TF300  #K=1F F  c d|d|d|}t|tr|f|z}n8 t|}t ||k7r t ||D]} t||r|Dchc] }|dks | }}d} n|Dchc] }|dks | }}d} |r|d |d | d z }t ||S#t$r t |wxYw#ttf$r |d|dt |z }t |wxYwcc}wcc}w) aTransforms 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'9sj* v3A37$g ' %hl  (,K { q Y' '' ,L ,L! ,)4>AAa>>)4?AQa??,-6wir C ## 9 (Y' ' ( * ,(7 ./1 !++  ,?@s/ B' B?! C1,C19 C6C6'B<?/C.c|y|dvsJ||dz |dz zz}|dvr|}n|dk(r ||z dz}n |dk(r||zdz }|zdz |zS)a:Determines 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 11rcp|y|dvsJ|dk(r|dz}n|dk(rd}n |dk(r|dz }|dz |zdzz |zS) aDetermines 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 ??rc|dvsJ|y||dz |dz zz}|=|dk(r||zt||z dz}|S|dk(r||z||zdz z }|S|dk(r||z}S|dk(r|dz}n|dk(rd}n |dk(r|dz }|dz |z|zdzz |z}|S) 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 !F*Sv1Eq-IIF" M! !F*f{.BQ.FGF M !F*F M f "C  C  /CA  '+ 5C ?. P  Mrcv|tj}|j}|dvrtd||S)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_paddingrFsL%$' kkmG11   #  Nrc |dvrtd|dt|}t|tr|f|z}t|tr|f|z}t|}t|}||k7s||k7rt d|d|d|t ||||}||z}t j|t} |D cgc] } t| } } tj| D]0} t||| ||} tj| D] }d| || z< 2| Scc} w)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_maskrdsd^''!G9%7 7  +G,$$0 '3*w&l#Kg,Kg!7 ,,7=9i~k] <  %\7GL|+J 88J %D/;<s<<$,,.?@:0  (//1AB :N59D/1 2 : : K=s0D c #K|dvrtd|dt|}t|tr|f|z}t|tr|f|z}t|}t|} ||k7s| |k7rt d| d|d|t ||||} | D cgc] } t | } } |dk(rd} n|d k(rd } nt d |d tj| D]}t|||||}tj|D]r}t |D]b}t |D]R}tj| ||| | | }tj| ||| || }||fTdtycc} ww)a'Yields 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 c|f|zSNr. spatial_idx filter_idxs rz"conv_kernel_idxs..s ZMK,Grrc||fzSrgr.rhs rrkz"conv_kernel_idxs..sk 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_idxsrwKsp''!G9%7 7  +G,$$0 '3*w&l#Kg,Kg!7 ,,7=9i~k] <  %\7GL0<<s<<&& G   ' K=)I I  %,,.?@,0  (//1AB ,Nj) ,";/ ,E 22$/$G({CG 11$/$E(jAF#F++ , , , ,!=sBE;E6%CE;cg}t|}t|D]l}t||dz }|||z } ||||z} |dk(r| |z } td| |z } t ||| | z} |j t| | n|S)a%Return 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\ )a1,- "1o 2  #gaj0 g  j FAv *++a.&;"67 eE3'( ) Mrc tt|}|Dcgc]}t|||||||}}t|Dcgc]}||dk(rdn||c}}|Scc}wcc}w)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)rVrWrXr1rnr}r\s rrNrNs& \" #D  ;q><?GWQZPL@DE1k!n!|A 6EL  Fs A!A&cNtjd5|j}|| d}|jstj|| d}|d| }|jstj|d| }t |tj r)tj |dg|jz}n.tj |tjdg|fd}||}|j| d}|jstj|| d}tj |tj||fd} | j|jd| | j| dz| cdddS#1swYyxYw)a.Returns `unsqueeze_batch(op(squeeze_batch(inp)))`. Where `squeeze_batch` reshapes `inp` to shape `[prod(inp.shape[:-inner_rank])] + inp.shape[-inner_rank:]` and `unsqueeze_batch` does the reverse reshape but on the output. Args: inp: A tensor with dims `batch_shape + inner_shape` where `inner_shape` is length `inner_rank`. op: A callable that takes a single input tensor and returns a single. output tensor. inner_rank: A python integer. Returns: `unsqueeze_batch_op(squeeze_batch(inp))`. squeeze_batch_dimsN)axis) tf name_scopeshapeis_fully_definedr TensorShapereshapeas_listconcat set_shape) inpop inner_rankr inner_shape batch_shape inp_reshaped out_reshapedout_inner_shapeouts rrrsx" + , ZKL) ++-((3- 5KLj[) ++-((3- *5K k2>> 2::cB4+2E2E2G+GHL::RYYk2<L,' &,,j[\://1 hh|4j[\BOjj "))[/$BL  cii *- :+,0GGH;s E;FF$)F)r-)Nrr-)__doc__rSnumpyrOtensorflow.compat.v2compatv2r tf_keras.srcrrr'r6r:r?rCrFrdrwrUrNrr.rrrsi,!!  @:z24@8  1h  Slo,d9x<.r