ijCddlZddlZddlmZddlmZddlmZddlm Z ddl m Z ddl m Z dZ d Z dd Z dd Zd Zdd ZdZdZdZddZeddZy)N)backend)tree) keras_export) KerasTensor)canonicalize_axis)to_tuple_or_listc $t|}t|}|}|}t|t|kDrdgt|t|z z|z}t|t|krdgt|t|z z|z}t|}tt|D]i}||dk(r ||||<||||dk(rdn||||<,||dk(s|| ||||k(r ||||<Mtd||d||d|d|d |S)aSBroadcast input shapes to a unified shape. Convert to list for mutability. Args: shape1: A tuple or list of integers. shape2: A tuple or list of integers. Returns: output_shape (list of integers or `None`): The broadcasted shape. Example: >>> broadcast_shapes((5, 3), (1, 3)) [5, 3] Nz2Cannot broadcast shape, the failure dim has value z!, which cannot be broadcasted to z. Input shapes are:  and .)listlenrange ValueError)shape1shape2 origin_shape1 origin_shape2 output_shapeis r/var/www/html/emotional.easysim.app/public_html/venv/lib/python3.12/site-packages/keras/src/ops/operation_utils.pybroadcast_shapesr sM &\F &\FMM 6{S[ F c&k12V; 6{S[ F c&k12V;$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 rrriterrnexttuple) input_shapeaxisout_ndima shape_iterax new_shapes r compute_expand_dims_output_shaper%9s{#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(r]tj ||z |z dz} tt | D]'}||vs| |dkstd|d |d |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_lastr validrzHComputed output size would be zero or negative. Received: `inputs.shape=z`, `pool_size= `, `strides= `, `padding=`.samezGArgument `padding` must be either 'valid' or 'same'. Received: padding=) r nparrayrrappendfloorrintr) r pool_sizestridespadding data_formatinput_shape_origin spatial_shape none_dimsroutput_spatial_shapers rcompute_pooling_output_shaper<PsN#?iGk*((;'Ko%#Ab) #AB I 3}% &    # "M!    Q   #I' HHmi/7: ;a ? s/01 A !&:1&=&B //:m<""+L B 'y,  F !xx):g(EFJ i !  -AAqCFAA '"&Q' !56o%  " $" #!"%' (   q ! q !  !!  BsE,cP|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(rit j||| dz zz dz |z dz} t t| D]*} | | vs| | d kstd|d|d|d|d|d n2|dvrt 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'r r(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*rzGComputed output size would be zero or negative. Received `inputs shape=z`, `kernel shape=z`, `dilation_rate=r+r,r-)r.causalz9`padding` must be either `'valid'` or `'same'`. Received ) rr isinstancer3r/r0rr1r2r)rfilters kernel_sizer5r6r7 dilation_rater9 kernel_shaper:rkernel_spatial_shaper;rs rcompute_conv_output_shaperFso%#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&=&B %%0M2%%1N3&&3_5 'y) 'y ,  & &!xx):g(EFJ Giq   -AAqCFAA '"&Q' !56o% ^  4 4 R8H7J J  $A R(89z[Inner dimensions (`x1.shape[-1]` and `x2.shape[-2]`) must be equal, but received `x1.shape=z` and `x2.shape=r-)rrrr)rrx1_is_1dx2_is_1d leading_shapelast_2_dims_shapers rcompute_matmul_output_shaperLs6{aH6{aHVAY)Qr  2J " 2J&* $ --3H5 $  %VCR[&"+>MVBZ0 #44L      rc "tj|st|tryd}|D]H}t|tt j fs$|dkrtd|d|d|d|dk(sD|dz }J|dkDrtd |d |d|dy) a9Validate the `newshape` argument of `reshape`. Each dimension that is a concrete Python int must be either non-negative or `-1` (with at most one `-1`). Dynamic dimensions (e.g. backend tensor scalars resolved at runtime, such as `torch.SymInt` under `torch.compile`) are not validated here. Nrr(zEach dimension in `zT` must be a non-negative integer, or `-1` for a single unknown dimension. Received: =r r z5There must be at most one unknown dimension (-1) in `z `. Received: )r is_tensorr@rr3r/integerr)newshapenewshape_arg_name neg_one_countdims rvalidate_reshape_shaperU&s"j;&GM #RZZ01  8%&7%89((9':!H:QH  BY Q M q !"- !8*A /  rc t||tj|st|tr+t |dd}|rt |dk(r |dd|dzSytd|D}|jd}d|vsd|vrtd|DStj|}|dk(r.|tj|k7rtd |d |d ||Sd}d}t|D]\}} | dk(r|}|| z}|dk(s||zdk7rtd |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). shapeNr rNc3dK|](}t|ttjfr|nd*ywrX)r@r3r/rP.0rTs r z/compute_reshape_output_shape..Vs,@Cz#RZZ01t;s.0r(c3.K|] }|dk7r|ndyw)r(NrZs rr\z/compute_reshape_output_shape..^sDCC2IS4/DszFThe total size of the tensor must be unchanged. Received: input_shape=, rNzyThe total size of the tensor must be unchanged, however, the input size cannot by divided by the specified dimensions in z. Received: input_shape=)rUrrOr@rgetattrrrcountmathprodr enumerater ) rrQrRrWunknown_dim_count input_sizeknown_output_sizeunknown_dim_indexindexrTrs rcompute_reshape_output_shaperjFs 8%67"j;&G'40 SZ1_q)=U1X% %GOH!r* {dh.D8DDD;'JA 8, ,*m2.?-@(M )% s "9 %   $  % A.?!?1!D K !!9+b !8* .  >L&04E&EL"#  rc t|tdddSt}t||k7rtd|dt|dg}|D]O}t |t r || ks||k\rtd|d|dt|d|j ||zQtt||k7rtd t|d |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 z,Each axis in `axes` must be an integer in [-r_z). Received: axes=z[`axes` must be a valid permutation of the input dimensions (no duplicates). Received: axes=z for input of rank c3(K|] }| ywrXr^)r[r#rs rr\z1compute_transpose_output_shape..s;RR;s)r rrrr@r3r1set)raxesndimnormalized_axesr#s` rcompute_transpose_output_shaperqs+{#K |[2&'' { D 4yD v_SYKq :  O*"c"bD5jB$JF"TF"4T$ZLC  rDy) * 3  D( //3Dzl;6   ;?; ;;rct|}t|}|d|vrdgntj|g}t|t|k7rt d|d|d|t |t|}nd}||||<t ||}|S)NzM`x` and `indices` must have the same number of dimensions, but receive shape r r r)r rbrcrrrr)r indices_shaperrs r$compute_take_along_axis_output_shaperts{#K'M |k)TF +0F/G  ;3}-- !!, U=/ D    s;'78%d+K#K?L rc4t|&|rtDcgc]}dc}StgSt|tr|f}tfd|D}|r|D]}d|< tSt |dD]}|=tScc}w)Nr c3HK|]}t|tywrX)rr)r[r!rWs rr\zreduce_shape..s@a"1c%j1@s"T)reverse)r rr@r3sorted)rWrkeepdims_r#s` r reduce_shaper{s KE | U+!+, ,9  D# w @4@ @D BE"I U|t, Bb  U|,s Bzkeras.utils.get_source_inputscpt|ds|S|j\}}}|r |js|gS|j|}|jrt j |j Sg}|jD]:}t|}|D](tfd|Ds|j*<|S)zReturns the list of input tensors necessary to compute `tensor`. Output will always be a list of tensors (potentially with 1 element). Args: tensor: The tensor to start from. Returns: List of input tensors. _keras_historyc3&K|]}|u ywrXr^)r[txs rr\z$get_source_inputs..s>!1A:>s) hasattrr}_inbound_nodesis_inputrflattenoutput_tensors input_tensorsget_source_inputsallr1)tensor operation node_indexrznodesource_tensorsprevious_sourcesrs @rrrs 6+ , %44Iz1 I44x'' 3 ==<< 3 34 4N,, 1#4V#< )1A>~>>&--a01 1 " !r)r*r')r r*r'r )rQ)NF)rbnumpyr/ keras.srcrrkeras.src.api_exportrkeras.src.backendr&keras.src.backend.common.backend_utilsrrrr%r<rFrLrUrjrqrtr{rr^rrrs -)DC)X6  X~  Pf%P @7t"