6bi SrSSKJs Jr SSKJr SSKJr SSK J r SSK J r SSK Jr \"S5"S S \ 55r\"S 5S S j5rg)z7Layer that computes the dot product between two inputs.N)backend)base_layer_utils)_Merge)tf_utils) keras_exportzkeras.layers.Dotc^\rSrSrSrS U4Sjjr\RS5rSr \RS5r S Sjr U4Sjr S r U=r$) Dota8Layer that computes a dot product between samples in two tensors. E.g. if applied to a list of two tensors `a` and `b` of shape `(batch_size, n)`, the output will be a tensor of shape `(batch_size, 1)` where each entry `i` will be the dot product between `a[i]` and `b[i]`. >>> x = np.arange(10).reshape(1, 5, 2) >>> print(x) [[[0 1] [2 3] [4 5] [6 7] [8 9]]] >>> y = np.arange(10, 20).reshape(1, 2, 5) >>> print(y) [[[10 11 12 13 14] [15 16 17 18 19]]] >>> tf.keras.layers.Dot(axes=(1, 2))([x, y]) >>> x1 = tf.keras.layers.Dense(8)(np.arange(10).reshape(5, 2)) >>> x2 = tf.keras.layers.Dense(8)(np.arange(10, 20).reshape(5, 2)) >>> dotted = tf.keras.layers.Dot(axes=1)([x1, x2]) >>> dotted.shape TensorShape([5, 1]) c >[TU]"S 0UD6 [U[5(d[U[[ 45(d[ SU35e[U5S:wa[SU35e[US[5(a[US[5(d[SU35eXl X l SUl SUl g ) aInitializes a layer that computes the element-wise dot product. >>> x = np.arange(10).reshape(1, 5, 2) >>> print(x) [[[0 1] [2 3] [4 5] [6 7] [8 9]]] >>> y = np.arange(10, 20).reshape(1, 2, 5) >>> print(y) [[[10 11 12 13 14] [15 16 17 18 19]]] >>> tf.keras.layers.Dot(axes=(1, 2))([x, y]) Args: axes: Integer or tuple of integers, axis or axes along which to take the dot product. If a tuple, should be two integers corresponding to the desired axis from the first input and the desired axis from the second input, respectively. Note that the size of the two selected axes must match. normalize: Whether to L2-normalize samples along the dot product axis before taking the dot product. If set to True, then the output of the dot product is the cosine proximity between the two samples. **kwargs: Standard layer keyword arguments. zPInvalid type for argument `axes`: it should be a list or an int. Received: axes=zSInvalid format for argument `axes`: it should contain two elements. Received: axes=rzUInvalid format for argument `axes`: list elements should be integers. Received: axes=TFN) super__init__ isinstanceintlisttuple TypeErrorlen ValueErroraxes normalizesupports_masking_reshape_required)selfrrkwargs __class__s Y/home/james-whalen/.local/lib/python3.13/site-packages/tf_keras/src/layers/merging/dot.pyr Dot.__init__?s> "6"$$$dT5M2288V^  dii % %yy1} CK/S[1HI {Q99D q'?f!Wo -%1g/z$q'%q'?#:d1gY7&&,XRx9  .r!c[R"XR5 [U5S:wa[ SU35eUSnUSn[ UR [5(ahUR S:aGUR [R"U5-UR [R"U5-/nOUR /S-nO/n[[UR 55HmnUR US:a9URUR U[R"X5-5 MOURUR U5 Mo UR(a@[RRX$SS9n[RRX4SS9n[R "X#U5nU$)Nr zEA `Dot` layer should be called on exactly 2 inputs. Received: inputs=rr )axis)rno_ragged_supportnamerrrrrrndimrangeappendrtflinalg l2_normalize batch_dot)rinputsx1x2rioutputs r_merge_functionDot._merge_functionsh**699= v;! $$*8- AY AY dii % %yy1}II R 00II R 00  {QD3tyy>*99Q>''a'9B''a'9B""240 r!c^[U[[45(a[U5S:wa[ SU35e[US5n[US5n[UR [ 5(aRUR S:a1UR [U5-UR [U5-/nOUR /S-nO UR nURUS5 URUS5 URS5 X#-n[U5S:XaUS/- n[U5$)Nr r#rr )rrrrrrrpop)rr$r%r&r output_shapes rcompute_output_shapeDot.compute_output_shapes+t}55[9IQ9N))4 7 k!n%k!n% dii % %yy1} CK/S[1HI {Q99D 47 47 1  |  ! QC L\""r!cgNr)rr4masks r compute_maskDot.compute_masksr!c>URURS.n[TU] 5n[ [ UR 55[ UR 55-5$)Nrr)rrr get_configdictritems)rconfig base_configrs rrGDot.get_configsPII g(* D**,-V\\^0DDEEr!)rrrrFrA)__name__ __module__ __qualname____firstlineno____doc__rrshape_type_conversionr'r9r>rCrG__static_attributes__ __classcell__)rs@rr r sY@3'j##$4<###$#.FFr!r zkeras.layers.dotc ([SXS.UD6"U5$)a!Functional interface to the `Dot` layer. Args: inputs: A list of input tensors (at least 2). axes: Integer or tuple of integers, axis or axes along which to take the dot product. normalize: Whether to L2-normalize samples along the dot product axis before taking the dot product. If set to True, then the output of the dot product is the cosine proximity between the two samples. **kwargs: Standard layer keyword arguments. Returns: A tensor, the dot product of the samples from the inputs. rFr)r )r4rrrs rdotrWs"  8D 8 8 @@r!rM)rRtensorflow.compat.v2compatv2r0 tf_keras.srcrtf_keras.src.enginer&tf_keras.src.layers.merging.base_mergertf_keras.src.utilsr tensorflow.python.util.tf_exportrr rWrr!rr`sg>"! 09': !pF&pF"pFf !A"Ar!