2VhB8ddlZddlZddlmZddlmZddlmZddlm Z dZ dZ ddZ dd Z d Zd Zd Zd ZddZeddZy)N)tree) keras_export)canonicalize_axis)to_tuple_or_listc $t|}t|}|}|}t|t|kDrdgt|t|z z|z}t|t|krdgt|t|z z|z}t|}tt|D]i}||dk(r ||||<||||dk(rdn||||<,||dk(s|| ||||k(r ||||<Mtd||d||d|d|d |S)aSBroadcast input shapes to a unified shape. Convert to list for mutability. Args: shape1: A tuple or list of integers. shape2: A tuple or list of integers. Returns: output_shape (list of integers or `None`): The broadcasted shape. Example: >>> broadcast_shapes((5, 3), (1, 3)) [5, 3] Nz2Cannot broadcast shape, the failure dim has value z!, which cannot be broadcasted to z. Input shapes are:  and .)listlenrange ValueError)shape1shape2 origin_shape1 origin_shape2 output_shapeis M/home/dcms/DCMS/lib/python3.12/site-packages/keras/src/ops/operation_utils.pybroadcast_shapesr sM &\F &\FMM 6{S[ F c&k12V; 6{S[ F c&k12V;$QiLO AY &,Qi1nd&)LOayA~!2fQi6!96L"() Q Hayk!B6!9+N))6u]O1N  c6t|}| t|}t|}t|t|z}|Dcgc]}t||}}t |}t |Dcgc]}||vrdn t |}}t|Scc}wcc}w)aCompute the output shape for the `expand_dims` operation. Args: input_shape: Input shape. axis: int or sequence of ints for the axis to expand. Returns: Tuple of ints: The output shape after the `expand_dims` operation. r)r r rriterr nexttuple) input_shapeaxisout_ndima shape_iterax new_shapes r compute_expand_dims_output_shaper#7s{#K |; D !D4y3{++H48 9q a * 9D 9k"J8=h24R4ZT*--I   :s B,Bc||n|}t|}tj|}|dk(r|dd}n|dd}g}tt |D]}|| d||<|j | tj|}|dk(rWtj ||z |z dz} tt | D]!}||vs| |dkstd|d |d n2|d k(rtj |dz |z dz} ntd || Dcgc] }t|} }|D]}d| |< t| } |dk(r|df| z|dfz} | S|d|df| z} | Scc}w) a3Computes the output shape of pooling operations. Args: input_shape: Input shape. Must be a tuple of integers. pool_size: Size of the pooling operation. Must be a tuple of integers. strides: Stride of the pooling operation. Must be a tuple of integers. Defaults to `pool_size`. padding: Padding method. Available methods are `"valid"` or `"same"`. Defaults to `"valid"`. data_format: String, either `"channels_last"` or `"channels_first"`. The ordering of the dimensions in the inputs. `"channels_last"` corresponds to inputs with shape `(batch, height, width, channels)` while `"channels_first"` corresponds to inputs with shape `(batch, channels, height, weight)`. Defaults to `"channels_last"`. Returns: Tuple of ints: The output shape of the pooling operation. Examples: # Basic usage with square pooling on a single image >>> compute_pooling_output_shape((1, 4, 4, 1), (2, 2)) (1, 2, 2, 1) # Strided pooling on a single image with strides different from pool_size >>> compute_pooling_output_shape((1, 4, 4, 1), (2, 2), strides=(1, 1)) (1, 3, 3, 1) # Pooling on a batch of images >>> compute_pooling_output_shape((32, 4, 4, 3), (2, 2)) (32, 2, 2, 3) N channels_lastrvalidrz@Computed output size would be negative. Received: `inputs.shape=z` and `pool_size=`.samezGArgument `padding` must be either 'valid' or 'same'. Received: padding=) r nparrayr r appendfloorrintr) r pool_sizestridespadding data_formatinput_shape_origin spatial_shape none_dimsroutput_spatial_shapers rcompute_pooling_output_shaper8NsN#?iGk*((;'Ko%#Ab) #AB I 3}% &    # "M!    Q   #I' HHmi/7: ;a ? s/01 A !&:1&=&A %%0M1B9+RQ  F !xx):g(EFJ i !  -AAqCFAA '"&Q' !56o%  " $" #!"%' (   q ! q !  !!  BsE&c P|dk(r|dd}||d|fz}n|dd}||d|fz}t|t|k7rtd|d|dt|tr|ft|z}t|tr|ft|z}t|t|k7rtd |d |dg} t j |}t t|D]} ||  d|| <| j|  t j |dd } t j |}|d k(rct j||| dz zz dz |z dz} t t| D]$} | | vs| | d kstd|d|d|dn8|dk(s|dk(rt j|dz |z dz} ntd|d| D cgc] } t| } } | D]} d| | < t| } |dk(r|d f| z|dfz} | S|d |df| z} | Scc} w)z%Compute the output shape of conv ops.r%rr&r'NzNKernel shape must have the same length as input, but received kernel of shape z and input of shape r zlDilation must be None, scalar or tuple/list of length of inputs' spatial shape, but received `dilation_rate=z` and input of shape r(rz?Computed output size would be negative. Received `inputs shape=z`, `kernel shape=z`, `dilation_rate=r)r*causalz9`padding` must be either `'valid'` or `'same'`. Received ) r r isinstancer/r+r,r r-r.r)rfilters kernel_sizer1r2r3 dilation_rater5 kernel_shaper6rkernel_spatial_shaper7rs rcompute_conv_output_shaperBso%#Ab) "k"ow%?? #AB "k!ng%>>  <C ,, +n-)]! -  -%&(3}+== '3*s=11 =S// +_-)]! -  IHH]+M 3}% &    # "M!    Q   88L"$56HH]+M' HH2F2J!KKaO    s/01 A !&:1&=&A %%0M2%%1N3&&3_B8  F g1!xx):g(EFJ Giq   -AAqCFAA '"&Q' !56o% ^  4 4 R8H7J J  $A R(89MVBZ0 #44L 6{a   6{a    rc |jd}|dkDrtd|d|d|dd|vrtd|DStj|}|d k(r.|tj|k7rtd |d |d||Sd}d}t |D]\}}|dk(r|}||z}|d k(s||zd k7rtd |d |d |d|t |} ||z| |<t| S)zConverts `-1` in `newshape` to either an actual dimension or `None`. This utility does not special case the 0th dimension (batch size). r&rz4There must be at most one unknown dimension (-1) in z . Received: =r Nc3.K|] }|dk7r|ndyw)r&N).0dims r z/compute_reshape_output_shape..(sDCC2IS4/DsrzFThe total size of the tensor must be unchanged. Received: input_shape=z, zyThe total size of the tensor must be unchanged, however, the input size cannot by divided by the specified dimensions in z. Received: input_shape=)countrrmathprod enumerater ) rnewshapenewshape_arg_nameunknown_dim_count input_sizeknown_output_sizeunknown_dim_indexindexrLrs rcompute_reshape_output_shaperYsj !r*1 B !.?-@(1 N   {D8DDD;'JA 8, ,*m2.?-@(M )% s "9 %   $  % A.?!?1!D K !!9+b !8* .  >L&04E&EL"#  rct|tdddSt|tk7r$tdtdt|dtfd|DS)a Compute the output shape for the `transpose` operation. Args: input_shape: Input shape. axes: Permutation of the dimensions for the `transpose` operation. Returns: Tuple of ints: The output shape after the `transpose` operation. Nr&zDaxis must be a list of the same length as the input shape, expected z, but received r c3(K|] }| ywNrJ)rKr!rs rrMz1compute_transpose_output_shape..]s0RR0s)r rr r)raxess` rcompute_transpose_output_shaper^Js{{#K |[2&'' 4yC $$ K()T 1 F   040 00rct|}t|}|&d|vrdgnttj|g}t |t |k7rt d|d|d||||<t ||}|S)NzM`x` and `indices` must have the same number of dimensions, but receive shape r r )r r/r+rPr rr)r indices_shaperrs r$compute_take_along_axis_output_shapera`s{#K'M |k)TFBGGK4H0I/J  ;3}-- !!, U=/ D  &d+K#K?L rct|}|&|rt|Dcgc]}dc}StgS|r|D]}d||< t|St|dD]}||=t|Scc}w)NrT)reverse)r rsorted)shaperkeepdims_r!s r reduce_shaperhss KE | U+!+, ,9  BE"I U|t, Bb  U|,s A-zkeras.utils.get_source_inputscpt|ds|S|j\}}}|r |js|gS|j|}|jrt j |j Sg}|jD]:}t|}|D](tfd|Ds|j*<|S)zReturns the list of input tensors necessary to compute `tensor`. Output will always be a list of tensors (potentially with 1 element). Args: tensor: The tensor to start from. Returns: List of input tensors. _keras_historyc3&K|]}|u ywr\rJ)rKtxs rrMz$get_source_inputs..s>!1A:>s) hasattrrj_inbound_nodesis_inputrflattenoutput_tensors input_tensorsget_source_inputsallr-)tensor operation node_indexrgnodesource_tensorsprevious_sourcesrms @rrtrts 6+ , %44Iz1 I44x'' 3 ==<< 3 34 4N,, 1#4V#< )1A>~>>&--a01 1 " !r)r(r%)rr(r%r)NF)rOnumpyr+ keras.srcrkeras.src.api_exportr&keras.src.backend.common.backend_utilsrrrr#r8rBrFrYr^rarhrtrJrrrs{ -DC)X6  Vz  M` F-`1,&$-."/"r