2VhL+zddlmZddlmZddlmZedGddZd dZed d gd Zy) )tree) keras_export) auto_namezkeras.KerasTensorceZdZdZ d9dZedZejdZedZejdZedZ e jd Z ed Z e jd Z ed Z d Z d:dZ dZdZdZdZd;dZdZdZdZdZdZdZdZdZdZdZdZdZd Zd!Z d"Z!d#Z"d$Z#d%Z$d&Z%d'Z&d(Z'd)Z(d*Z)d+Z*d,Z+d-Z,d.Z-d/Z.d0Z/d1Z0d2Z1d3Z2d4Z3d5Z4d6Z5d7Z6d:d8Z7y)< KerasTensoraSymbolic tensor -- encapsulates a shape and a dtype. You can use `KerasTensor` instances to build computation graphs of Keras operations, such as `keras.Function` objects or Functional `keras.models.Model` objects. Example: >>> x = keras.KerasTensor(shape=(3, 4), dtype="float32") >>> x.shape (3, 4) >>> x.dtype float32 Calling a Keras operation (including a layer or a model) on a `KerasTensor` instance will return another `KerasTensor` instance with the appropriate shape and dtype. This is called a "symbolic call" (since there is no actual data involved). The computation of the correct output shape and dtype is called "static shape inference". NcLddlm}|j||_|j ||_t ||_t ||_|jr|jr td|xst|jj|_ ||_y)Nr)backendzIKerasTensor cannot have `sparse=True` and `ragged=True` at the same time.) keras.srcr standardize_shape_shapestandardize_dtype_dtypebool_sparse_ragged ValueErrorr __class____name__namerecord_history)selfshapedtypesparseraggedrrr s U/home/dcms/DCMS/lib/python3.12/site-packages/keras/src/backend/common/keras_tensor.py__init__zKerasTensor.__init__s &//6 //6 F| F| <Idnn&=&=> ,c|jSN)r rs rrzKerasTensor.shape5 {{rctd)NzlThe `shape` attribute of KerasTensor is immutable. One should create a new instance of KerasTensor for this.AttributeErrorrvalues rrzKerasTensor.shape9 =  rc|jSr )rr!s rrzKerasTensor.dtype@r"rctd)NzlThe `dtype` attribute of KerasTensor is immutable. One should create a new instance of KerasTensor for this.r$r&s rrzKerasTensor.dtypeDr(rc|jSr )rr!s rrzKerasTensor.sparseK ||rctd)NzmThe `sparse` attribute of KerasTensor is immutable. One should create a new instance of KerasTensor for this.r$r&s rrzKerasTensor.sparseOr(rc|jSr )rr!s rrzKerasTensor.raggedVr,rctd)NzmThe `ragged` attribute of KerasTensor is immutable. One should create a new instance of KerasTensor for this.r$r&s rrzKerasTensor.raggedZr(rc,t|jSr )lenrr!s rndimzKerasTensor.ndimas4::rc<ddlm}|j||SNrops)r r6Reshape)rnewshaper6s rreshapezKerasTensor.reshapees!$s{{8$T**rc<ddlm}|j||Sr4)r r6Squeeze)raxisr6s rsqueezezKerasTensor.squeezejs! s{{4 &&rctd)NzA KerasTensor is symbolic: it's a placeholder for a shape an a dtype. It doesn't have any actual numerical value. You cannot convert it to an int.rr!s r__int__zKerasTensor.__int__os /  rctd)NzA KerasTensor is symbolic: it's a placeholder for a shape an a dtype. It doesn't have any actual numerical value. You cannot convert it to a float.r?r!s r __float__zKerasTensor.__float__vs 0  rctd)NzA KerasTensor is symbolic: it's a placeholder for a shape an a dtype. It doesn't have any actual numerical value. You cannot convert it to a NumPy array.r?r!s r __array__zKerasTensor.__array__}s 6  rctd)Na%A KerasTensor cannot be used as input to a JAX function. A KerasTensor is a symbolic placeholder for a shape and dtype, used when constructing Keras Functional models or Keras Functions. You can only use it as input to a Keras layer or a Keras operation (from the namespaces `keras.layers` and `keras.ops`). You are likely doing something like: ``` x = Input(...) ... jax_fn(x) # Invalid. ``` What you should do instead is wrap `jax_fn` in a layer: ``` class MyLayer(Layer): def call(self, x): return jax_fn(x) x = MyLayer()(x) ``` r?r!s r __jax_array__zKerasTensor.__jax_array__   rctd)Na)A KerasTensor cannot be used as input to a TensorFlow function. A KerasTensor is a symbolic placeholder for a shape and dtype, used when constructing Keras Functional models or Keras Functions. You can only use it as input to a Keras layer or a Keras operation (from the namespaces `keras.layers` and `keras.ops`). You are likely doing something like: ``` x = Input(...) ... tf_fn(x) # Invalid. ``` What you should do instead is wrap `tf_fn` in a layer: ``` class MyLayer(Layer): def call(self, x): return tf_fn(x) x = MyLayer()(x) ``` r?)rrrs r __tf_tensor__zKerasTensor.__tf_tensor__rGrc d|jd|jd|jd|jd|jd S)Nz)rrrrrr!s r__repr__zKerasTensor.__repr__sG!$**Xdjj\Bkk])DKK= {! M rctd)Nz7Iterating over a symbolic KerasTensor is not supported.)NotImplementedErrorr!s r__iter__zKerasTensor.__iter__s! E  rctd)Nz3A symbolic KerasTensor cannot be used as a boolean.) TypeErrorr!s r__bool__zKerasTensor.__bool__sMNNrcNddlm}|jj||Sr4r r6Add symbolic_callrotherr6s r__add__zKerasTensor.__add__!wwy&&tU33rcNddlm}|jj||Sr4rTrWs r__radd__zKerasTensor.__radd__!wwy&&ud33rcNddlm}|jj||Sr4r r6SubtractrVrWs r__sub__zKerasTensor.__sub__!||~++D%88rcNddlm}|jj||Sr4r_rWs r__rsub__zKerasTensor.__rsub__!||~++E488rcNddlm}|jj||Sr4r r6MultiplyrVrWs r__mul__zKerasTensor.__mul__rbrcNddlm}|jj||Sr4rgrWs r__rmul__zKerasTensor.__rmul__rercNddlm}|jj||Sr4r r6MatmulrVrWs r __matmul__zKerasTensor.__matmul__!zz|))$66rcNddlm}|jj||Sr4rmrWs r __rmatmul__zKerasTensor.__rmatmul__!zz|))%66rcNddlm}|jj||Sr4r r6DividerVrWs r__div__zKerasTensor.__div__rprcNddlm}|jj||Sr4rurWs r__rdiv__zKerasTensor.__rdiv__rsrcNddlm}|jj||Sr4r r6 TrueDividerVrWs r __truediv__zKerasTensor.__truediv__!~~--dE::rcNddlm}|jj||Sr4r{rWs r __rtruediv__zKerasTensor.__rtruediv__!~~--eT::rcLddlm}|jj|Sr4)r r6NegativerVrr6s r__neg__zKerasTensor.__neg__!||~++D11rcLddlm}|jj|Sr4)r r6AbsoluterVrs r__abs__zKerasTensor.__abs__rrcNddlm}|jj||Sr4r r6PowerrVrWs r__pow__zKerasTensor.__pow__s!yy{((u55rcNddlm}|jj||Sr4rrWs r__rpow__zKerasTensor.__rpow__ s!yy{((55rcNddlm}|jj||Sr4r r6 FloorDividerVrWs r __floordiv__zKerasTensor.__floordiv__s! ..tU;;rcNddlm}|jj||Sr4rrWs r __rfloordiv__zKerasTensor.__rfloordiv__s! ..ud;;rcNddlm}|jj||Sr4r r6ModrVrWs r__mod__zKerasTensor.__mod__rZrcNddlm}|jj||Sr4rrWs r__rmod__zKerasTensor.__rmod__r]rcNddlm}|jj||Sr4)r r6LessrVrWs r__lt__zKerasTensor.__lt__$s!xxz''e44rcNddlm}|jj||Sr4)r r6 LessEqualrVrWs r__le__zKerasTensor.__le__)!}},,T599rcNddlm}|jj||Sr4)r r6GreaterrVrWs r__gt__zKerasTensor.__gt__.s!{{}**477rcNddlm}|jj||Sr4)r r6 GreaterEqualrVrWs r__ge__zKerasTensor.__ge__3s!!!//e<rsZ-,!"b@b@#b@J ,.MNO &P &r