| /external/tensorflow/tensorflow/python/ops/distributions/ |
| gamma.py | 50 parameters `concentration` (aka "alpha") and `rate` (aka "beta").
63 * `concentration = alpha`, `alpha > 0`,
81 concentration = alpha = (mean / stddev)**2
82 rate = beta = mean / stddev**2 = concentration / mean
88 WARNING: This distribution may draw 0-valued samples for small `concentration`
94 dist = Gamma(concentration=3.0, rate=2.0)
95 dist2 = Gamma(concentration=[3.0, 4.0], rate=[2.0, 3.0])
101 concentration,
106 """Construct Gamma with `concentration` and `rate` parameters.
108 The parameters `concentration` and `rate` must be shaped in a way tha
157 def concentration(self): member in class:Gamma
[all...] |
| dirichlet.py | 52 length-`k` vector `concentration` (`k > 1`). The Dirichlet is identically the
73 * `concentration = alpha = [alpha_0, ..., alpha_{k-1}]`, `alpha_j > 0`,
80 The `concentration` represents mean total counts of class occurrence, i.e.,
83 concentration = alpha = mean * total_concentration
134 concentration,
141 concentration: Positive floating-point `Tensor` indicating mean number
144 `concentration.shape = [N1, N2, ..., Nm, k]` then
158 with ops.name_scope(name, values=[concentration]):
160 ops.convert_to_tensor(concentration, name="concentration"),
174 def concentration(self): member in class:Dirichlet
[all...] |
| dirichlet_multinomial.py | 50 with `self.concentration` and `self.total_count`."""
58 length-`K` `concentration` vectors (`K > 1`) and a `total_count` number of
78 * `concentration = alpha = [alpha_0, ..., alpha_{K-1}]`, `alpha_j > 0`,
93 `probs = [p_0,...,p_{K-1}] ~ Dir(concentration)`
97 The last `concentration` dimension parametrizes a single Dirichlet-Multinomial
99 `concentration`, `total_count` and `counts` are broadcast to the same shape.
164 # TODO(b/27419586) Change docstring for dtype of concentration once int
168 concentration,
176 as `concentration`. The shape is broadcastable to `[N1,..., Nm]` with
180 concentration: Positive floating point tensor, whose dtype is th
230 def concentration(self): member in class:DirichletMultinomial
[all...] |
| beta.py | 73 The concentration parameters represent mean total counts of a `1` or a `0`,
183 """Concentration parameter associated with a `1` outcome."""
188 """Concentration parameter associated with a `0` outcome."""
193 """Sum of concentration parameters."""
292 def _maybe_assert_valid_concentration(self, concentration, validate_args):
293 """Checks the validity of a concentration parameter."""
295 return concentration
298 concentration,
299 message="Concentration parameter must be positive."),
300 ], concentration)
[all...] |
| exponential.py | 60 Exponential(rate) = Gamma(concentration=1., rate)
101 concentration=array_ops.ones([], dtype=self._rate.dtype),
|
| /external/tensorflow/tensorflow/contrib/distributions/python/ops/ |
| inverse_gamma.py | 47 parameters `concentration` (aka "alpha") and `rate` (aka "beta").
60 * `concentration = alpha`,
78 concentration = alpha = (mean / stddev)**2
85 WARNING: This distribution may draw 0-valued samples for small concentration
92 dist = tfd.InverseGamma(concentration=3.0, rate=2.0)
93 dist2 = tfd.InverseGamma(concentration=[3.0, 4.0], rate=[2.0, 3.0])
99 concentration,
104 """Construct InverseGamma with `concentration` and `rate` parameters.
106 The parameters `concentration` and `rate` must be shaped in a way that
107 supports broadcasting (e.g. `concentration + rate` is a valid operation)
156 def concentration(self): member in class:InverseGamma
[all...] |
| chi2.py | 59 Chi2(df) = Gamma(concentration=0.5 * df, rate=0.5)
92 concentration=0.5 * self._df,
|
| /external/tensorflow/tensorflow/contrib/distributions/python/ops/bijectors/ |
| weibull.py | 35 """Compute `Y = g(X) = 1 - exp((-X / scale) ** concentration), X >= 0`.
43 Y ~ Weibull(scale, concentration)
44 pdf(y; scale, concentration, y >= 0) = (scale / concentration) * (
45 scale / concentration) ** (concentration - 1) * exp(
46 -(y / scale) ** concentration)
52 concentration=1.,
60 broadcastable with `concentration`.
62 concentration: Positive Float-type `Tensor` that is the same dtype and i
102 def concentration(self): member in class:Weibull
[all...] |
| /external/tensorflow/tensorflow/contrib/distributions/python/kernel_tests/bijectors/ |
| weibull_test.py | 36 concentration = 0.3
38 scale=scale, concentration=concentration,
43 weibull_dist = stats.frechet_r(c=concentration, scale=scale)
61 Weibull(scale=20., concentration=0.3),
67 scale=20., concentration=2., event_ndims=0, validate_args=True)
|
| cholesky_outer_product_test.py | 81 distribution=gamma_lib.Gamma(concentration=1., rate=2.),
|
| invert_test.py | 81 distribution=gamma_lib.Gamma(concentration=1., rate=2.),
|
| /external/guava/guava-tests/benchmark/com/google/common/cache/ |
| LoadingCacheSingleThreadBenchmark.java | 40 @Param("2.5") double concentration; field in class:LoadingCacheSingleThreadBenchmark
53 // power of (1/concentration) and floor()ed
54 max = Ints.checkedCast((long) Math.pow(distinctKeys, concentration));
89 * For example, if concentration=2.0, the following takes the square root of
94 return (int) Math.pow(a, 1.0 / concentration);
|
| /external/guava/guava-tests/benchmark/com/google/common/collect/ |
| MapMakerSingleThreadBenchmark.java | 43 @Param("2.5") double concentration; field in class:MapMakerSingleThreadBenchmark
56 // power of (1/concentration) and floor()ed
57 max = Ints.checkedCast((long) Math.pow(distinctKeys, concentration));
92 * For example, if concentration=2.0, the following takes the square root of
97 return (int) Math.pow(a, 1.0 / concentration);
|
| /external/tensorflow/tensorflow/python/kernel_tests/distributions/ |
| gamma_test.py | 54 gamma = gamma_lib.Gamma(concentration=alpha, rate=beta)
69 gamma = gamma_lib.Gamma(concentration=alpha, rate=beta)
88 gamma = gamma_lib.Gamma(concentration=alpha, rate=beta)
109 gamma = gamma_lib.Gamma(concentration=alpha, rate=beta)
132 gamma = gamma_lib.Gamma(concentration=alpha, rate=beta)
144 gamma = gamma_lib.Gamma(concentration=alpha_v, rate=beta_v)
155 gamma = gamma_lib.Gamma(concentration=alpha_v, rate=beta_v)
165 gamma = gamma_lib.Gamma(concentration=alpha_v,
176 gamma = gamma_lib.Gamma(concentration=alpha_v,
188 gamma = gamma_lib.Gamma(concentration=alpha_v, rate=beta_v
[all...] |
| dirichlet_test.py | 68 self.assertEqual([1, 3], dist.concentration.get_shape())
69 self.assertAllClose(alpha, dist.concentration.eval())
150 dirichlet = dirichlet_lib.Dirichlet(concentration=alpha)
197 dirichlet = dirichlet_lib.Dirichlet(concentration=alpha)
210 dirichlet = dirichlet_lib.Dirichlet(concentration=alpha)
217 dirichlet = dirichlet_lib.Dirichlet(concentration=alpha,
225 dirichlet = dirichlet_lib.Dirichlet(concentration=alpha,
235 dirichlet = dirichlet_lib.Dirichlet(concentration=alpha)
|
| dirichlet_multinomial_test.py | 67 self.assertEqual([1, 3], dist.concentration.get_shape())
68 self.assertAllClose(alpha, dist.concentration.eval())
425 concentration=1. + 2. * self._rng.rand(4, 3, 2).astype(np.float32))
454 concentration=1. + 2. * self._rng.rand(4).astype(np.float32))
|
| /external/tensorflow/tensorflow/contrib/distributions/python/kernel_tests/ |
| inverse_gamma_test.py | 36 inv_gamma = inverse_gamma.InverseGamma(concentration=alpha, rate=beta)
53 inv_gamma = inverse_gamma.InverseGamma(concentration=alpha, rate=beta)
71 inv_gamma = inverse_gamma.InverseGamma(concentration=alpha, rate=beta)
91 inv_gamma = inverse_gamma.InverseGamma(concentration=alpha, rate=beta)
112 inv_gamma = inverse_gamma.InverseGamma(concentration=alpha, rate=beta)
123 inv_gamma = inverse_gamma.InverseGamma(concentration=alpha_v, rate=beta_v)
132 inv_gamma = inverse_gamma.InverseGamma(concentration=alpha_v, rate=beta_v)
143 concentration=alpha_v, rate=beta_v, allow_nan_stats=False)
153 concentration=alpha_v, rate=beta_v, allow_nan_stats=True)
164 inv_gamma = inverse_gamma.InverseGamma(concentration=alpha_v, rate=beta_v
[all...] |
| /external/tensorflow/tensorflow/contrib/bayesflow/python/kernel_tests/ |
| monte_carlo_test.py | 264 p = gamma_lib.Gamma(concentration=concentration_p, rate=1.)
265 q = gamma_lib.Gamma(concentration=concentration_q, rate=3.)
|
| hmc_test.py | 821 gamma_lib.Gamma(concentration=self.dtype([1, 2]),
[all...] |
