o 2hd@sdZddlZddlmZddlmZddlmZddlmZddlm Z ddl m Z dd l m Z dd l m Z dd l mZdd lTdd lmZddlmZddlmZedddgdejedddejddfddZedddddejddfddZedddgdejedddejddfddZededed d d!gdejed!ddejddfd"d!Zed#ed$d$d%gdejed%d=d&d%Zed'ed(d)gdejejdd*d+d>d,d)Zed-ejd>d.d/Z d0d1Z!ed2d3d4Z"ed5d5d6gdejed6dejddfd7d6Z#ed8d9gdejed9ejddfd:d9Z$ed8gdejejddfd;d<Z%dS)?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?cCt|d|||gA}t|}tj||dd}tj||dd}t|\} } tj||| | d} | |} t j | ||d} t | || WdS1sNwYdS)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_seedrrandom_standard_normalr addmaybe_set_static_shapeshaperrrrrr mean_tensor stddev_tensorseed1rrndmulvaluer*[/var/www/html/chatgem/venv/lib/python3.10/site-packages/tensorflow/python/ops/random_ops.pyr's.  $RandomStandardNormalgg@c Cst|d|||||gH}t|}tj||dd} tj||dd} tj||dd} tj||dd} t|\} }tj|| | | | | |d}t |||WdS1sWwYdS) 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 rrrrrr-r!)r#r.r/r0r1rrrr means_tensorstddevs_tensorminvals_tensormaxvals_tensorr&rr'r*r*r+r-es,"   $r-zrandom.truncated_normaltruncated_normalcCr)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. r6rrrrrN) rrr rrrrrr6r r r!r"r*r*r+r6s'  $ParameterizedTruncatedNormalTruncatedNormalzrandom.uniformrandom_uniformc Csrt|}tjtjtjtjtjtjf}||vr"td|d|d|dur1|j r/td|d}t |d|||gt}t |}t|toI|dk}t|toR|dk}|rZ|rZ|j rjt j||d d }t j||d d }t|\} } |j rtj|||| | |d } n tj||| | d } |r|st| |} n tj| ||||d} t | || WdS1swYdS)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 %rr9rminrmaxrrrrr)ras_dtypefloat16bfloat16float32float64int32int64 ValueError is_integerrrr r isinstanceintrrrrrandom_uniform_intr9r multiplyr r!) r#minvalmaxvalrrraccepted_dtypesminval_is_zero maxval_is_oner&rresultr*r*r+r9sJ H       $ RandomUniformzrandom.shufflerandom_shufflecCs t|\}}tj||||dS)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. r@)rrrrU)r)rrr&rr*r*r+rUFs RandomShufflezrandom.multinomial multinomialz$Use `tf.random.categorical` instead.)date instructionscCsBt|d|gt||||WdS1swYdS)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]`. rWNrrmultinomial_categorical_impl)logits num_samplesrr output_dtyper*r*r+rWjs $zrandom.categoricalcCsBt|d|gt||||WdS1swYdS)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]`. categoricalNrZ)r\r]rrrr*r*r+r_s $r_cCsntj|dd}|rt|ntj}tjtjf}||vr&td|d|dt|\}}t j |||||dS)zGImplementation for random.categorical (v1) and random.categorical (v2).r\rr:r;r<)rrr^) rrrrArGrFrHrrrrW)r\r]rrrPr&rr*r*r+r[s  r[ MultinomialcCs\ts(tjr*|js,t|}t |}t |}| | |jdSdSdSdS)N)rexecuting_eagerlyrget_default_graphbuilding_functionr#is_fully_definedr rrconstant_value_as_shaper set_shape concatenate)tensorr#postfix_tensor const_shaper*r*r+_maybe_set_static_shape_helpers    rkz random.gamma random_gammac Cst|d|||g]tj|dtjd}tj|d|d}tj|dur$|ndd|d}tt|t|}t||}t |\}} t t |jjjtj|||| d|} t| ||| WdS1sjwYdS) 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)) rlr#rralphaNr=betar)rrrrrFrbroadcast_dynamic_shaper# broadcast_torrr maximumnpfinforas_numpy_dtypetinyrrlrk) r#rnrorrrbroadcast_shapealpha_broadcastr&rrSr*r*r+rls,M  $zrandom.poissonrandom_poissoncCst|||||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#rrrr*r*r+ry!s&cCszt|d||g*tj|dtjd}t|\}}tj|||||d}t ||||WdS1s6wYdS)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`. ryr#rm)rrrN) rrrrrFrrrrzrk)r#r{rrrr&rrSr*r*r+rzJs%  $rz)NN)NNN)&__doc__numpyrstensorflow.python.eagerrtensorflow.python.frameworkrrrrtensorflow.python.opsrrr r $tensorflow.python.ops.gen_random_opstensorflow.python.utilr r tensorflow.python.util.tf_exportradd_dispatch_supportdeprecated_endpointsrDrNotDifferentiabler-r6r9rU deprecatedrWr_r[rkrlryrzr*r*r*r+s             8 6 0  m     [ &