AVhddZddlZddlmZddlmZddlmZddlmZddlm Z ddl m Z dd l m Z dd l m Z dd l mZdd ldd lmZddlmZddlmZedddgej*ej,dddej.ddfdZej2dddddej.ddfdZedddgej*ej,dddej.ddfdZej2dej2deddd gej*ej,d ddej.ddfd!Zej2d"ed#d#d$gej*ej,d$d8d%Zej2d&ed'd(gej*ej<dd)*d9d+Zed,ej*d9d-Z d.Z!ej2d/d0Z"ed1d1d2gej*ej,d2dej.ddfd3Z#ed4d5gej*ej,d5ej.ddfd6Z$ed4gej*ej.ddfd7Z%y):z)Operations for generating random numbers.N)context)dtypes)ops) random_seed) tensor_util) array_ops)gen_random_ops)math_ops) shape_util)*) deprecation)dispatch) tf_exportz random.normal random_normal)v1gg?ctj|d|||g5}tj|}tj||d}tj||d}t j |\} } tj||| | } | |z} tj| ||} tj| || cdddS#1swYyxYw)aOutputs random values from a normal distribution. Example that generates a new set of random values every time: >>> tf.random.set_seed(5); >>> tf.random.normal([4], 0, 1, tf.float32) Example that outputs a reproducible result: >>> tf.random.set_seed(5); >>> tf.random.normal([2,2], 0, 1, tf.float32, seed=1) In this case, we are setting both the global and operation-level seed to ensure this result is reproducible. See `tf.random.set_seed` for more information. Args: shape: A 1-D integer Tensor or Python array. The shape of the output tensor. mean: A Tensor or Python value of type `dtype`, broadcastable with `stddev`. The mean of the normal distribution. stddev: A Tensor or Python value of type `dtype`, broadcastable with `mean`. The standard deviation of the normal distribution. dtype: The float type of the output: `float16`, `bfloat16`, `float32`, `float64`. Defaults to `float32`. seed: A Python integer. Used to create a random seed for the distribution. See `tf.random.set_seed` for behavior. name: A name for the operation (optional). Returns: A tensor of the specified shape filled with random normal values. rmeandtypenamestddevseedseed2rN) r name_scoper shape_tensorconvert_to_tensorrget_seedr random_standard_normalr addmaybe_set_static_shapeshaperrrrrr mean_tensor stddev_tensorseed1rrndmulvalues P/home/dcms/DCMS/lib/python3.12/site-packages/tensorflow/python/ops/random_ops.pyrr's\ ~~dOeT6-BC t**51L''EGK))&HMM''-LE5  / /e%u 6C C LLk 5E%%eU3     B+CCRandomStandardNormalgg@c tj|d|||||g5}tj|}tj||d} tj||d} tj||d} tj||d} t j |\} }tj|| | | | | |}tj|||cdddS#1swYyxYw) aOutputs random values from a truncated normal distribution. The generated values follow a normal distribution with specified mean and standard deviation, except that values whose magnitude is more than 2 standard deviations from the mean are dropped and re-picked. Args: shape: A 1-D integer Tensor or Python array. The shape of the output tensor. means: A 0-D Tensor or Python value of type `dtype`. The mean of the truncated normal distribution. stddevs: A 0-D Tensor or Python value of type `dtype`. The standard deviation of the truncated normal distribution. minvals: A 0-D Tensor or Python value of type `dtype`. The minimum value of the truncated normal distribution. maxvals: A 0-D Tensor or Python value of type `dtype`. The maximum value of the truncated normal distribution. dtype: The type of the output. seed: A Python integer. Used to create a random seed for the distribution. See `tf.random.set_seed` for behavior. name: A name for the operation (optional). Returns: A tensor of the specified shape filled with random truncated normal values. parameterized_truncated_normalmeansrstddevsminvalsmaxvalsrN) rrr rrrrr r/r")r$r0r1r2r3rrrr means_tensorstddevs_tensorminvals_tensormaxvals_tensorr'rr(s r+r/r/esD ~~d<eWgw?ADH**51L((e'JL**7%iPN**7%iPN**7%iPN''-LE5  7 7  C%%c51 #s CC((C1zrandom.truncated_normaltruncated_normalctj|d|||g5}tj|}tj||d}tj||d}t j |\} } tj||| | } | |z} tj| ||} tj| || cdddS#1swYyxYw)aOutputs random values from a truncated normal distribution. The values are drawn from a normal distribution with specified mean and standard deviation, discarding and re-drawing any samples that are more than two standard deviations from the mean. Examples: >>> tf.random.truncated_normal(shape=[2]) >>> tf.random.truncated_normal(shape=[2], mean=3, stddev=1, dtype=tf.float32) Args: shape: A 1-D integer Tensor or Python array. The shape of the output tensor. mean: A 0-D Tensor or Python value of type `dtype`. The mean of the truncated normal distribution. stddev: A 0-D Tensor or Python value of type `dtype`. The standard deviation of the normal distribution, before truncation. dtype: The type of the output. Restricted to floating-point types: `tf.half`, `tf.float`, `tf.double`, etc. seed: A Python integer. Used to create a random seed for the distribution. See `tf.random.set_seed` for more information. name: A name for the operation (optional). Returns: A tensor of the specified shape filled with random truncated normal values. r8rrrrrN) rrr rrrrr r8r r!r"r#s r+r8r8sN ~~d.f0EF $**51L''EGK))&HMM''-LE5  ) )e%u 6C C LLk 5E%%eU3    r,ParameterizedTruncatedNormalTruncatedNormalzrandom.uniformrandom_uniformc tj|}tjtjtjtj tj tjf}||vrtd|d|d||jrtd|zd}tj|d|||g5}tj|}t|txr|dk(}t|txr|dk(}|r|r |jr0tj ||d }tj ||d }t#j$|\} } |jrt'j(|||| | | } nRt'j*||| | } |r|s5t-j.| |} nt-j0| ||z z||} tj2| || cdddS#1swYyxYw)a Outputs random values from a uniform distribution. The generated values follow a uniform distribution in the range `[minval, maxval)`. The lower bound `minval` is included in the range, while the upper bound `maxval` is excluded. For floats, the default range is `[0, 1)`. For ints, at least `maxval` must be specified explicitly. In the integer case, the random integers are slightly biased unless `maxval - minval` is an exact power of two. The bias is small for values of `maxval - minval` significantly smaller than the range of the output (either `2**32` or `2**64`). Examples: >>> tf.random.uniform(shape=[2]) >>> tf.random.uniform(shape=[], minval=-1., maxval=0.) >>> tf.random.uniform(shape=[], minval=5, maxval=10, dtype=tf.int64) The `seed` argument produces a deterministic sequence of tensors across multiple calls. To repeat that sequence, use `tf.random.set_seed`: >>> tf.random.set_seed(5) >>> tf.random.uniform(shape=[], maxval=3, dtype=tf.int32, seed=10) >>> tf.random.uniform(shape=[], maxval=3, dtype=tf.int32, seed=10) >>> tf.random.set_seed(5) >>> tf.random.uniform(shape=[], maxval=3, dtype=tf.int32, seed=10) >>> tf.random.uniform(shape=[], maxval=3, dtype=tf.int32, seed=10) Without `tf.random.set_seed` but with a `seed` argument is specified, small changes to function graphs or previously executed operations will change the returned value. See `tf.random.set_seed` for details. Args: shape: A 1-D integer Tensor or Python array. The shape of the output tensor. minval: A Tensor or Python value of type `dtype`, broadcastable with `shape` (for integer types, broadcasting is not supported, so it needs to be a scalar). The lower bound on the range of random values to generate (inclusive). Defaults to 0. maxval: A Tensor or Python value of type `dtype`, broadcastable with `shape` (for integer types, broadcasting is not supported, so it needs to be a scalar). The upper bound on the range of random values to generate (exclusive). Defaults to 1 if `dtype` is floating point. dtype: The type of the output: `float16`, `bfloat16`, `float32`, `float64`, `int32`, or `int64`. Defaults to `float32`. seed: A Python integer. Used in combination with `tf.random.set_seed` to create a reproducible sequence of tensors across multiple calls. name: A name for the operation (optional). Returns: A tensor of the specified shape filled with random uniform values. Raises: ValueError: If `dtype` is integral and `maxval` is not specified. #Argument `dtype` got invalid value . Accepted dtypes are .Nz(Must specify maxval for integer dtype %rr<rminrmaxrrrrr)ras_dtypefloat16bfloat16float32float64int32int64 ValueError is_integerrrr r isinstanceintrrrr random_uniform_intr<r multiplyr!r") r$minvalmaxvalrrraccepted_dtypesminval_is_zero maxval_is_oner'rresults r+r<r<sP //% %^^V__fnn^^V\\6<<A/ /!  -eW4J  1   ^  AEI JJ F ~~d,uff.EF$  # #E *E ,<1Nvs+;! M %2B2B$$V5uEf$$V5uEf''-LE5 00 e5tEf,, U%1f $$VV4&f8&tL %%fe4 5s D-G77H RandomUniformzrandom.shufflerandom_shufflecdtj|\}}tj||||S)aRandomly shuffles a tensor along its first dimension. The tensor is shuffled along dimension 0, such that each `value[j]` is mapped to one and only one `output[i]`. For example, a mapping that might occur for a 3x2 tensor is: ```python [[1, 2], [[5, 6], [3, 4], ==> [1, 2], [5, 6]] [3, 4]] ``` Args: value: A Tensor to be shuffled. seed: A Python integer. Used to create a random seed for the distribution. See `tf.random.set_seed` for behavior. name: A name for the operation (optional). Returns: A tensor of same shape and type as `value`, shuffled along its first dimension. rD)rrr rY)r*rrr'rs r+rYrYFs48%%d+,%  & & %u4 11 RandomShufflezrandom.multinomial multinomialz$Use `tf.random.categorical` instead.)date instructionscztj|d|g5t||||cdddS#1swYyxYw)a/Draws samples from a multinomial distribution. Example: ```python # samples has shape [1, 5], where each value is either 0 or 1 with equal # probability. samples = tf.random.categorical(tf.math.log([[0.5, 0.5]]), 5) ``` Args: logits: 2-D Tensor with shape `[batch_size, num_classes]`. Each slice `[i, :]` represents the unnormalized log-probabilities for all classes. num_samples: 0-D. Number of independent samples to draw for each row slice. seed: A Python integer. Used to create a random seed for the distribution. See `tf.random.set_seed` for behavior. name: Optional name for the operation. output_dtype: The integer type of the output: `int32` or `int64`. Defaults to `int64`. Returns: The drawn samples of shape `[batch_size, num_samples]`. r]Nrrmultinomial_categorical_impl)logits num_samplesrr output_dtypes r+r]r]js=8 ~~dMF84Q ' \4 PQQQ1:zrandom.categoricalcztj|d|g5t||||cdddS#1swYyxYw)a(Draws samples from a categorical distribution. Example: ```python # samples has shape [1, 5], where each value is either 0 or 1 with equal # probability. samples = tf.random.categorical(tf.math.log([[0.5, 0.5]]), 5) ``` Args: logits: 2-D Tensor with shape `[batch_size, num_classes]`. Each slice `[i, :]` represents the unnormalized log-probabilities for all classes. num_samples: 0-D. Number of independent samples to draw for each row slice. dtype: The integer type of the output: `int32` or `int64`. Defaults to `int64`. seed: A Python integer. Used to create a random seed for the distribution. See `tf.random.set_seed` for behavior. name: Optional name for the operation. Returns: The drawn samples of shape `[batch_size, num_samples]`. categoricalNra)rcrdrrrs r+rhrhs=4 ~~dMF84J ' UD IJJJrfcNtj|d}|rtj|ntj}tj tjf}||vrt d|d|dtj|\}}tj|||||S)zGImplementation for random.categorical (v1) and random.categorical (v2).rcrr>r?r@)rrre) rrrrErKrJrLrrr r])rcrdrrrTr'rs r+rbrbs  h 7&$)&//% v||%\\6<<0/ /!  -eW4J  1  %%d+,%  # # kU HHr[ Multinomialcttjstjjr|j j sjtj|}tj|}tj|}|j|j|j yyyy)N)rexecuting_eagerlyrget_default_graphbuilding_functionr$is_fully_definedr rrconstant_value_as_shaper set_shape concatenate)tensorr$postfix_tensor const_shapes r+_maybe_set_static_shape_helperrvs  # # % // ,, ' ' )  # #E *E55e:N [,,^-A-ABC *0 &r[z random.gamma random_gammac tj|d|||g5tj|dtj}tj|d|}tj||ndd|}t j t j|t j|}t j||}tj|\}} tjtj|jj j"t%j&|||| |z } t)| ||| cdddS#1swYyxYw) a6 Draws `shape` samples from each of the given Gamma distribution(s). `alpha` is the shape parameter describing the distribution(s), and `beta` is the inverse scale parameter(s). Note: Because internal calculations are done using `float64` and casting has `floor` semantics, we must manually map zero outcomes to the smallest possible positive floating-point value, i.e., `np.finfo(dtype).tiny`. This means that `np.finfo(dtype).tiny` occurs more frequently than it otherwise should. This bias can only happen for small values of `alpha`, i.e., `alpha << 1` or large values of `beta`, i.e., `beta >> 1`. The samples are differentiable w.r.t. alpha and beta. The derivatives are computed using the approach described in (Figurnov et al., 2018). Example: ```python samples = tf.random.gamma([10], [0.5, 1.5]) # samples has shape [10, 2], where each slice [:, 0] and [:, 1] represents # the samples drawn from each distribution samples = tf.random.gamma([7, 5], [0.5, 1.5]) # samples has shape [7, 5, 2], where each slice [:, :, 0] and [:, :, 1] # represents the 7x5 samples drawn from each of the two distributions alpha = tf.constant([[1.],[3.],[5.]]) beta = tf.constant([[3., 4.]]) samples = tf.random.gamma([30], alpha=alpha, beta=beta) # samples has shape [30, 3, 2], with 30 samples each of 3x2 distributions. loss = tf.reduce_mean(tf.square(samples)) dloss_dalpha, dloss_dbeta = tf.gradients(loss, [alpha, beta]) # unbiased stochastic derivatives of the loss function alpha.shape == dloss_dalpha.shape # True beta.shape == dloss_dbeta.shape # True ``` Args: shape: A 1-D integer Tensor or Python array. The shape of the output samples to be drawn per alpha/beta-parameterized distribution. alpha: A Tensor or Python value or N-D array of type `dtype`. `alpha` provides the shape parameter(s) describing the gamma distribution(s) to sample. Must be broadcastable with `beta`. beta: A Tensor or Python value or N-D array of type `dtype`. Defaults to 1. `beta` provides the inverse scale parameter(s) of the gamma distribution(s) to sample. Must be broadcastable with `alpha`. dtype: The type of alpha, beta, and the output: `float16`, `float32`, or `float64`. seed: A Python integer. Used to create a random seed for the distributions. See `tf.random.set_seed` for behavior. name: Optional name for the operation. Returns: samples: a `Tensor` of shape `tf.concat([shape, tf.shape(alpha + beta)], axis=0)` with values of type `dtype`. References: Implicit Reparameterization Gradients: [Figurnov et al., 2018] (http://papers.nips.cc/paper/7326-implicit-reparameterization-gradients) ([pdf] (http://papers.nips.cc/paper/7326-implicit-reparameterization-gradients.pdf)) rwr$rralphaNrAbetar)rrrrrJrbroadcast_dynamic_shaper$ broadcast_torrr maximumnpfinforas_numpy_dtypetinyr rwrv) r$rzr{rrrbroadcast_shapealpha_broadcastr'rrWs r+rwrws'Z ~~dNUE4,@A  ! !%gV\\ JE  ! !%gU CE   afE CD77  57O,,UODO''-LE5    ++,11## ?e =?C DEF#65/B s D4EE"zrandom.poissonrandom_poissonc t|||||S)aDraws `shape` samples from each of the given Poisson distribution(s). `lam` is the rate parameter describing the distribution(s). Example: ```python samples = tf.random.poisson([0.5, 1.5], [10]) # samples has shape [10, 2], where each slice [:, 0] and [:, 1] represents # the samples drawn from each distribution samples = tf.random.poisson([12.2, 3.3], [7, 5]) # samples has shape [7, 5, 2], where each slice [:, :, 0] and [:, :, 1] # represents the 7x5 samples drawn from each of the two distributions ``` Args: lam: A Tensor or Python value or N-D array of type `dtype`. `lam` provides the rate parameter(s) describing the poisson distribution(s) to sample. shape: A 1-D integer Tensor or Python array. The shape of the output samples to be drawn per "rate"-parameterized distribution. dtype: The type of the output: `float16`, `float32`, `float64`, `int32` or `int64`. seed: A Python integer. Used to create a random seed for the distributions. See `tf.random.set_seed` for behavior. name: Optional name for the operation. Returns: samples: a `Tensor` of shape `tf.concat([shape, tf.shape(lam)], axis=0)` with values of type `dtype`. )random_poisson_v2)lamr$rrrs r+rr!sL 5#udD 99r[c.tj|d||g5tj|dtj}t j |\}}tj|||||}t||||cdddS#1swYyxYw)aDraws `shape` samples from each of the given Poisson distribution(s). `lam` is the rate parameter describing the distribution(s). Example: ```python samples = tf.random.poisson([10], [0.5, 1.5]) # samples has shape [10, 2], where each slice [:, 0] and [:, 1] represents # the samples drawn from each distribution samples = tf.random.poisson([7, 5], [12.2, 3.3]) # samples has shape [7, 5, 2], where each slice [:, :, 0] and [:, :, 1] # represents the 7x5 samples drawn from each of the two distributions ``` Args: shape: A 1-D integer Tensor or Python array. The shape of the output samples to be drawn per "rate"-parameterized distribution. lam: A Tensor or Python value or N-D array of type `dtype`. `lam` provides the rate parameter(s) describing the poisson distribution(s) to sample. dtype: The type of the output: `float16`, `float32`, `float64`, `int32` or `int64`. seed: A Python integer. Used to create a random seed for the distributions. See `tf.random.set_seed` for behavior. name: Optional name for the operation. Returns: samples: a `Tensor` of shape `tf.concat([shape, tf.shape(lam)], axis=0)` with values of type `dtype`. rr$ry)rrrN) rrrrrJrrr rrv)r$rrrrr'rrWs r+rrJsJ ~~d,sEl;  ! !%gV\\ JE''-LE5  - - s%e5:F"65#6  s A'B  B)NN)NNN)&__doc__numpyrtensorflow.python.eagerrtensorflow.python.frameworkrrrrtensorflow.python.opsrr r r $tensorflow.python.ops.gen_random_opstensorflow.python.utilr r tensorflow.python.util.tf_exportradd_dispatch_supportdeprecated_endpointsrHrNotDifferentiabler/r8r<rY deprecatedr]rhrbrvrwrrr[r+rs0+.+33+0*,3/+6 ?AB !!!/2 53C5p,-*-+.+/+.)/(,(,3l $(*<=? !!!"45!>> -6?-`45'( !13C DE !!!"23 j4FjZo& !13C DE !!!"2314F1<o& #]34  BDQD5Q8   J!J8 Hm$D >~~>? !!!.1~~ X2@Xv !123 !!!"23%+^^$T#:44#:L # (.T)$)r[