o i eA@sdZddlZddlmZddlmZddlmZddlm Z ddl m Z ddl m Z dd l m Zdd l mZdd l mZdd l mZdd lmZddlmZddlmZddZddZddZd1ddZedgd d2ddZedgdd3ddZdd Zd!d"Zd#d$Z  d4d%d&Z!e"ej#e!de$e%e&fe!d'e$e'e!d(   d4d)d*Z(e$ej)e(d'   d4d+d,Z*e$ej+e*d'Gd-d.d.Z,e-e,Gd/d0d0Z.e-e.dS)5zvOperations that generate constants. See the [constants guide](https://tensorflow.org/api_guides/python/constant_op). N) types_pb2) struct_pb2)context)execute)dtypes)ops)tensor)tensor_conversion_registry) tensor_shape) tensor_util)trace)nested_structure_coder) tf_exportcCsX|}t|g|tjtjgtj\}\}||g}d|d|f}tjdd|||d\}|S)zEEager-only version of Reshape op; requires tensor is an eager Tensor.TTshapesReshapeinputsattrsctx)_datatype_enumrargs_to_matching_eagerrint32int64)rshaperattr_t attr_tshape inputs_flatrresultrV/var/www/myenv/lib/python3.10/site-packages/tensorflow/python/framework/constant_op.py_eager_reshape&s   r!cCsF|jj}t||tj}||g}d|dtjf}tjdd|||d\}|S)zAEager-only version of Fill op; requires value is an eager Tensor.r index_typesFillrr)dtypeas_datatype_enumconvert_to_eager_tensorrrrDT_INT32r)dimsvaluerrrrrrrr _eager_fill2s r)cCs(d|jjf}tjdd|g||d\}|S)zFEager-only version of Identity op; requires tensor is an eager Tensor.rsIdentityrr)r#r$r)rrrrrrr _eager_identity=s  r*cCst|tjr |}t|tjr*|dur(|j|kr(td|d|d|jd|S|durCz|j}Wnt yBt |j}Ynw| t||j |S)aConverts the given `value` to an `EagerTensor`. Note that this function could return cached copies of created constants for performance reasons. Args: value: value to convert to EagerTensor. ctx: value of context.context(). dtype: optional desired dtype of the converted EagerTensor. Returns: EagerTensor created from value. Raises: TypeError: if `dtype` is not compatible with the type of t. NzExpected tensor z with dtype z, but got dtype .) isinstancenpndarraycopyr EagerTensorr# TypeErrorr$AttributeErrorras_dtypeensure_initialized device_name)r(rr#rrr r%Es     r%constant)v1ConstFcCst|||||ddS)a{Creates a constant tensor. The resulting tensor is populated with values of type `dtype`, as specified by arguments `value` and (optionally) `shape` (see examples below). The argument `value` can be a constant value, or a list of values of type `dtype`. If `value` is a list, then the length of the list must be less than or equal to the number of elements implied by the `shape` argument (if specified). In the case where the list length is less than the number of elements specified by `shape`, the last element in the list will be used to fill the remaining entries. The argument `shape` is optional. If present, it specifies the dimensions of the resulting tensor. If not present, the shape of `value` is used. If the argument `dtype` is not specified, then the type is inferred from the type of `value`. For example: ```python # Constant 1-D Tensor populated with value list. tensor = tf.constant([1, 2, 3, 4, 5, 6, 7]) => [1 2 3 4 5 6 7] # Constant 2-D tensor populated with scalar value -1. tensor = tf.constant(-1.0, shape=[2, 3]) => [[-1. -1. -1.] [-1. -1. -1.]] ``` `tf.constant` differs from `tf.fill` in a few ways: * `tf.constant` supports arbitrary constants, not just uniform scalar Tensors like `tf.fill`. * `tf.constant` creates a `Const` node in the computation graph with the exact value at graph construction time. On the other hand, `tf.fill` creates an Op in the graph that is expanded at runtime. * Because `tf.constant` only embeds constant values in the graph, it does not support dynamic shapes based on other runtime Tensors, whereas `tf.fill` does. Args: value: A constant value (or list) of output type `dtype`. dtype: The type of the elements of the resulting tensor. shape: Optional dimensions of resulting tensor. name: Optional name for the tensor. verify_shape: Boolean that enables verification of a shape of values. Returns: A Constant Tensor. Raises: TypeError: if shape is incorrectly specified or unsupported. F verify_shapeallow_broadcast_constant_impl)r(r#rnamer:rrr constant_v1is =r?cCst||||dddS)a# Creates a constant tensor from a tensor-like object. Note: All eager `tf.Tensor` values are immutable (in contrast to `tf.Variable`). There is nothing especially _constant_ about the value returned from `tf.constant`. This function is not fundamentally different from `tf.convert_to_tensor`. The name `tf.constant` comes from the `value` being embedded in a `Const` node in the `tf.Graph`. `tf.constant` is useful for asserting that the value can be embedded that way. If the argument `dtype` is not specified, then the type is inferred from the type of `value`. >>> # Constant 1-D Tensor from a python list. >>> tf.constant([1, 2, 3, 4, 5, 6]) >>> # Or a numpy array >>> a = np.array([[1, 2, 3], [4, 5, 6]]) >>> tf.constant(a) If `dtype` is specified, the resulting tensor values are cast to the requested `dtype`. >>> tf.constant([1, 2, 3, 4, 5, 6], dtype=tf.float64) If `shape` is set, the `value` is reshaped to match. Scalars are expanded to fill the `shape`: >>> tf.constant(0, shape=(2, 3)) >>> tf.constant([1, 2, 3, 4, 5, 6], shape=[2, 3]) `tf.constant` has no effect if an eager Tensor is passed as the `value`, it even transmits gradients: >>> v = tf.Variable([0.0]) >>> with tf.GradientTape() as g: ... loss = tf.constant(v + v) >>> g.gradient(loss, v).numpy() array([2.], dtype=float32) But, since `tf.constant` embeds the value in the `tf.Graph` this fails for symbolic tensors: >>> with tf.compat.v1.Graph().as_default(): ... i = tf.compat.v1.placeholder(shape=[None, None], dtype=tf.float32) ... t = tf.constant(i) Traceback (most recent call last): ... TypeError: ... `tf.constant` will create tensors on the current device. Inputs which are already tensors maintain their placements unchanged. Related Ops: * `tf.convert_to_tensor` is similar but: * It has no `shape` argument. * Symbolic tensors are allowed to pass through. >>> with tf.compat.v1.Graph().as_default(): ... i = tf.compat.v1.placeholder(shape=[None, None], dtype=tf.float32) ... t = tf.convert_to_tensor(i) * `tf.fill`: differs in a few ways: * `tf.constant` supports arbitrary constants, not just uniform scalar Tensors like `tf.fill`. * `tf.fill` creates an Op in the graph that is expanded at runtime, so it can efficiently represent large tensors. * Since `tf.fill` does not embed the value, it can produce dynamically sized outputs. Args: value: A constant value (or list) of output type `dtype`. dtype: The type of the elements of the resulting tensor. shape: Optional dimensions of resulting tensor. name: Optional name for the tensor. Returns: A Constant Tensor. Raises: TypeError: if shape is incorrectly specified or unsupported. ValueError: if called on a symbolic tensor. FTr9r<)r(r#rr>rrr r6s acCsxt}|r0tjr(tdt|||||WdS1s#wYt|||||St||||||}|S)zImplementation of constant.z tf.constantN)rexecuting_eagerlyr enabledTrace_constant_eager_implr_create_graph_constant)r(r#rr>r:r;r const_tensorrrr r=s   r=c Cs"t|||}|dur |St|}||jkr|S|r0td|d|dt|dt|jd |j}||krCt|||S|dkrz|j t j krrt dt|t|||}Wdn1shwYt||St|||Std |d|d |d d |d |d )z)Creates a constant on the current device.NzExpected Tensor z (converted from z ) with shape z, but got shape r+rz /device:CPU:0z>Eager execution of tf.constant with unsupported shape. Tensor z) has dz elements, but got `shape` z with z elements).)r%r as_shaperr1tuple num_elementsr!as_listr#rboolrdevicer)r*)rr(r#rr:tnum_txrrr rCsB         rCcCs"t|tjr |j}n|}|jdkS)Nr8)r, tensor_libTensoroptype) tensor_or_oprRrrr is_constant=s  rUcCs|}t|||dS)Nr#r>)r6)vr#r>as_ref_rrr $_constant_tensor_conversion_functionEsrZdcCs|}|std|d|}d}|D] }|dkr |}nq|durH|tjtjfvr8td|d|d|tjkrG|rGtd|d n|rMtjntj}|durVd }t|||d S) z*Function to convert TensorShape to Tensor.z-Cannot convert a partially known TensorShape to a Tensor.rlNzCannot convert TensorShape to dtype +. Allowed dtypes are tf.int32 and tf.int64.zC to dtype int32; a dimension is too large. Consider using tf.int64.shape_as_tensorrV)is_fully_defined ValueErrorrJrrrr1r6)sr#r>rXrYs_list int64_valuedimrrr (_tensor_shape_tensor_conversion_functionWs, rgcCsp|}|jdurtd|d|dur'|tjtjfvr&td|d|dntj}|dur0d}t|j||dS) z(Function to convert Dimension to Tensor.Nz!Cannot convert unknown Dimension r]zCannot convert Dimension r^r_r`rV)r(rbrrrr1r6)rFr#r>rXrYrrr %_dimension_tensor_conversion_functionys rhc@0eZdZdZddZddZddZdd Zd S) _ConstantTensorCodeczCodec for Tensor.cC t|tjSN)r,rPrQselfpyobjrrr can_encode z_ConstantTensorCodec.can_encodecCst~t}t|tjr|jt| |S|j j dkr*|j|j d|St dt|dt |d)z;Returns an encoded `TensorProto` for the given `tf.Tensor`.r8r(zNo encoder for object z of type r+)rStructuredValuer,rr0 tensor_valueCopyFromr make_tensor_protonumpyrRrSget_attrr NotEncodableErrorstr)rnrs encode_fnencoded_tensorrrr do_encodes    z_ConstantTensorCodec.do_encodecC |dS)NrsHasFieldrnr(rrr can_decode z_ConstantTensorCodec.can_decodecCs~|j}tt|}|S)z5Returns the `tf.Tensor` encoded by the proto `value`.)rsr6r MakeNdarray)rnr( decode_fn tensor_protorrrr do_decodesz_ConstantTensorCodec.do_decodeN__name__ __module__ __qualname____doc__rpr|rrrrrr rjs  rjc@ri) _NumpyCodeczCodec for Numpy.cCrkrl)r,r-r.rmrrr rprqz_NumpyCodec.can_encodecCs ~t}|jt||S)z2Returns an encoded `TensorProto` for `np.ndarray`.)rrr numpy_valuertr ru)rnrrz encoded_numpyrrr r|s z_NumpyCodec.do_encodecCr})Nrr~rrrr rrz_NumpyCodec.can_decodecCs~|j}t|}|S)z6Returns the `np.ndarray` encoded by the proto `value`.)rr r)rnr(rrrvrrr rs z_NumpyCodec.do_decodeNrrrrr rs  rrl)NNr8F)NNr8)NNF)/rrvr-tensorflow.core.frameworkrtensorflow.core.protobufrtensorflow.python.eagerrrtensorflow.python.frameworkrrrrPr r r tensorflow.python.profilerr tensorflow.python.saved_modelr tensorflow.python.util.tf_exportrr!r)r*r%r?r6r=rCrUrZ,register_tensor_conversion_function_internal_CONSTANT_OP_CONVERTIBLES#register_tensor_conversion_functionlistrHobjectrg TensorShaperh Dimensionrjregister_codecrrrrr sv                $ @ d     #