| /external/tensorflow/tensorflow/python/eager/ |
| tape_test.py | 30 from tensorflow.python.ops import math_ops
38 mm = math_ops.matmul(a, b)
39 r = math_ops.reduce_sum(mm)
43 math_ops.matmul(dmm, b, transpose_b=True) +
44 math_ops.matmul(array_ops.ones_like(b * dr), b, transpose_b=True),
45 math_ops.matmul(a, dmm, transpose_b=True) +
46 math_ops.matmul(a, array_ops.ones_like(a) * dr, transpose_b=True)
89 mm = math_ops.matmul(a, b)
90 return math_ops.reduce_sum(mm)
96 math_ops.matmul
[all...] |
| /external/tensorflow/tensorflow/contrib/bayesflow/python/ops/ |
| halton_sequence_impl.py | 29 from tensorflow.python.ops import math_ops
157 max_sizes_by_axes = _base_expansion_size(math_ops.reduce_max(indices),
160 max_size = math_ops.reduce_max(max_sizes_by_axes)
172 exponents_by_axes = array_ops.tile([math_ops.range(max_size)], [dim, 1])
177 coeffs = math_ops.floor_div(indices, weights)
178 coeffs *= 1 - math_ops.cast(weight_mask, dtype)
180 return math_ops.reduce_sum(coeffs / weights, axis=-1)
209 sample_indices = math_ops.range(n, dtype=dtype)
211 sample_indices = math_ops.cast(sample_indices, dtype)
241 return math_ops.floor(math_ops.log(num) / math_ops.log(bases)) +
[all...] |
| monte_carlo_impl.py | 30 from tensorflow.python.ops import math_ops
105 log_f_plus_z = math_ops.log(nn.relu(f_z) + 1.)
106 log_f_minus_z = math_ops.log(nn.relu(-1. * f_z) + 1.)
111 return math_ops.exp(log_f_plus_integral) - math_ops.exp(log_f_minus_integral)
186 centered_values = math_ops.exp(log_values - center)
192 log_mean_of_values = math_ops.log(_sample_mean(centered_values)) + center
331 return math_ops.reduce_mean(f(samples), axis=axis, keep_dims=keep_dims)
351 return math_ops.reduce_mean(fx, axis=axis, keep_dims=keep_dims)
356 return math_ops.reduce_mean(values, reduction_indices=[0]
[all...] |
| mcmc_diagnostics_impl.py | 30 from tensorflow.python.ops import math_ops
171 mask = math_ops.cast(mask, dtype=dt)
173 mask = math_ops.cumsum(mask, axis=0)
175 mask = math_ops.maximum(1. - mask, 0.)
187 k = math_ops.range(0., _axis_size(auto_corr, axis=0))
198 return n / (-1 + 2 * math_ops.reduce_sum(nk_factor * auto_corr, axis=0))
338 sample_axis = math_ops.range(0, sample_ndims)
339 chain_axis = math_ops.range(sample_ndims,
341 sample_and_chain_axis = math_ops.range(
351 math_ops.reduce_mean(state, sample_axis, keepdims=True)
[all...] |
| /external/tensorflow/tensorflow/contrib/distributions/python/ops/bijectors/ |
| power_transform.py | 25 from tensorflow.python.ops import math_ops
85 return math_ops.exp(x)
88 return math_ops.exp(math_ops.log1p(x * self.power) / self.power)
93 return math_ops.log(y)
96 return math_ops.expm1(math_ops.log(y) * self.power) / self.power
101 return (self.power - 1.) * math_ops.reduce_sum(
102 math_ops.log(y), axis=event_dims)
108 return math_ops.reduce_sum(x, axis=event_dims
[all...] |
| weibull.py | 25 from tensorflow.python.ops import math_ops
108 return -math_ops.expm1(-((x / self.scale) ** self.concentration))
112 return self.scale * (-math_ops.log1p(-y)) ** (1 / self.concentration)
117 return math_ops.reduce_sum(
118 -math_ops.log1p(-y) +
119 (1 / self.concentration - 1) * math_ops.log(-math_ops.log1p(-y)) +
120 math_ops.log(self.scale / self.concentration),
126 return math_ops.reduce_sum(
128 (self.concentration - 1) * math_ops.log(x)
[all...] |
| gumbel.py | 25 from tensorflow.python.ops import math_ops
97 return math_ops.exp(-math_ops.exp(-z))
101 return self.loc - self.scale * math_ops.log(-math_ops.log(y))
106 return math_ops.reduce_sum(
107 math_ops.log(self.scale / (-math_ops.log(y) * y)), axis=event_dims)
112 return math_ops.reduce_sum(
113 -z - math_ops.exp(-z) - math_ops.log(self.scale), axis=event_dims
[all...] |
| /external/tensorflow/tensorflow/python/ops/ |
| linalg_grad.py | 34 from tensorflow.python.ops import math_ops
42 return -math_ops.matmul(
43 ainv, math_ops.matmul(grad, ainv, adjoint_b=True), adjoint_a=True)
72 middle = math_ops.matmul(l, grad, adjoint_a=True)
77 grad_a = math_ops.matmul(
78 math_ops.matmul(l_inverse, middle, adjoint_a=True), l_inverse)
97 qdq = math_ops.matmul(q, dq, adjoint_a=True)
99 rdr = math_ops.matmul(r, dr, adjoint_b=True)
109 grad_a = math_ops.matmul(q, dr + _TriangularSolve(tril, r))
110 grad_b = _TriangularSolve(dq - math_ops.matmul(q, qdq), r
[all...] |
| metrics_impl.py | 29 from tensorflow.python.ops import math_ops
106 math_ops.equal(rank_diff, -1),
118 math_ops.equal(rank_diff, 1), maybe_squeeze_weights,
124 math_ops.equal(weights_rank_tensor, 0), lambda: weights,
151 math_ops.equal(
175 math_ops.equal(array_ops.rank(predictions),
191 t = math_ops.truediv(numerator, denominator)
193 condition = math_ops.greater(denominator, zero)
194 zero = math_ops.cast(zero, t.dtype)
212 math_ops.equal
[all...] |
| nn_impl.py | 32 from tensorflow.python.ops import math_ops
90 result = math_ops.exp(log_input) - log_input * targets
97 stirling_approx = (targets * math_ops.log(targets)) - targets + (
98 point_five * math_ops.log(two_pi * targets))
101 cond = math_ops.logical_and(targets >= zeros, targets <= ones)
180 return math_ops.add(
182 math_ops.log1p(math_ops.exp(neg_abs_logits)),
257 return math_ops.add(
259 log_weight * (math_ops.log1p(math_ops.exp(-math_ops.abs(logits)))
[all...] |
| /external/tensorflow/tensorflow/python/profiler/ |
| tfprof_logger_test.py | 23 from tensorflow.python.ops import math_ops
32 y = math_ops.matmul(a, b)
38 return math_ops.matmul(a, b)
|
| /external/tensorflow/tensorflow/contrib/solvers/python/ops/ |
| util.py | 25 from tensorflow.python.ops import math_ops
44 apply=lambda v: math_ops.matmul(matrix, v, adjoint_a=False),
45 apply_adjoint=lambda v: math_ops.matmul(matrix, v, adjoint_a=True))
67 return math_ops.reduce_sum(math_ops.conj(x) * y)
77 return math_ops.sqrt(l2norm_squared(v))
|
| /external/tensorflow/tensorflow/python/kernel_tests/ |
| bucketize_op_test.py | 23 from tensorflow.python.ops import math_ops
30 op = math_ops._bucketize(
38 op = math_ops._bucketize(
46 op = math_ops._bucketize(
54 op = math_ops._bucketize(
64 math_ops._bucketize(constant_op.constant([-5, 0]), boundaries=0)
|
| cwise_ops_test.py | 34 from tensorflow.python.ops import math_ops
110 if x.dtype in (np.complex64, np.complex128) and tf_func == math_ops.sign:
210 self._compareBoth(x, np.abs, math_ops.abs)
212 self._compareBoth(x, np.negative, math_ops.negative)
214 self._compareBoth(y, self._inv, math_ops.reciprocal)
215 self._compareBoth(x, np.square, math_ops.square)
216 self._compareBoth(z, np.sqrt, math_ops.sqrt)
217 self._compareBoth(z, self._rsqrt, math_ops.rsqrt)
218 self._compareBoth(x, np.exp, math_ops.exp)
219 self._compareBoth(x, np.expm1, math_ops.expm1
[all...] |
| argmax_op_test.py | 23 from tensorflow.python.ops import math_ops
61 self._testBothArg(math_ops.argmax, x, 0, x.argmax())
62 self._testBothArg(math_ops.argmin, x, 0, x.argmin())
69 self._testBothArg(math_ops.argmax, x, axis, x.argmax(axis))
70 self._testBothArg(math_ops.argmin, x, axis, x.argmin(axis))
80 ans = math_ops.argmax(x, axis=0, output_type=dtypes.int32)
88 ans = math_ops.argmin(x, axis=0, output_type=dtypes.int32)
107 for op in math_ops.argmin, math_ops.argmax:
114 for op in math_ops.argmin, math_ops.argmax
[all...] |
| /external/tensorflow/tensorflow/contrib/timeseries/python/timeseries/state_space_models/ |
| kalman_filter.py | 30 from tensorflow.python.ops import math_ops
131 min_diag = math_ops.reduce_min(diag)
170 math_ops.matmul(
207 prior_variance_transitioned = math_ops.matmul(
208 math_ops.matmul(transition_matrices, prior_state_var),
243 kalman_solve_rhs = math_ops.matmul(
253 math_ops.matmul(
258 gain_obs = math_ops.matmul(
266 posterior_state_var = math_ops.matmul(identity_minus_factor,
280 left_multiplied_state_var = math_ops.matmul(identity_minus_factor
[all...] |
| /external/tensorflow/tensorflow/contrib/distributions/python/ops/ |
| test_util.py | 27 from tensorflow.python.ops import math_ops
87 batch_size = math_ops.reduce_prod(dist.batch_shape_tensor())
93 probs = math_ops.exp(dist.log_prob(edges))
128 x = math_ops.to_float(dist.sample(num_samples, seed=seed))
129 sample_mean = math_ops.reduce_mean(x, axis=0)
130 sample_variance = math_ops.reduce_mean(
131 math_ops.square(x - sample_mean), axis=0)
132 sample_stddev = math_ops.sqrt(sample_variance)
178 value_range = [math_ops.reduce_min(x), 1 + math_ops.reduce_max(x)
[all...] |
| /external/tensorflow/tensorflow/contrib/opt/python/training/ |
| powersign.py | 26 from tensorflow.python.ops import math_ops
118 math_ops.cast(self._lr_t, var.dtype.base_dtype),
119 math_ops.cast(self._logbase_t, var.dtype.base_dtype),
120 math_ops.cast(self._sign_decay_t, var.dtype.base_dtype),
121 math_ops.cast(self._beta_t, var.dtype.base_dtype),
130 math_ops.cast(self._lr_t, var.dtype.base_dtype),
131 math_ops.cast(self._logbase_t, var.dtype.base_dtype),
132 math_ops.cast(self._sign_decay_t, var.dtype.base_dtype),
133 math_ops.cast(self._beta_t, var.dtype.base_dtype),
138 lr_t = math_ops.cast(self._lr_t, var.dtype.base_dtype
[all...] |
| /external/tensorflow/tensorflow/python/ops/distributions/ |
| special_math.py | 27 from tensorflow.python.ops import math_ops
96 z = math_ops.abs(w)
97 y = array_ops.where(math_ops.less(z, half_sqrt_2),
98 1. + math_ops.erf(w),
99 array_ops.where(math_ops.greater(w, 0.),
100 2. - math_ops.erfc(z),
101 math_ops.erfc(z)))
217 z = math_ops.sqrt(-2. * math_ops.log(sanitized_mcp))
218 first_term = z - math_ops.log(z) /
[all...] |
| /external/tensorflow/tensorflow/python/training/ |
| adam.py | 24 from tensorflow.python.ops import math_ops
146 math_ops.cast(beta1_power, var.dtype.base_dtype),
147 math_ops.cast(beta2_power, var.dtype.base_dtype),
148 math_ops.cast(self._lr_t, var.dtype.base_dtype),
149 math_ops.cast(self._beta1_t, var.dtype.base_dtype),
150 math_ops.cast(self._beta2_t, var.dtype.base_dtype),
151 math_ops.cast(self._epsilon_t, var.dtype.base_dtype),
160 math_ops.cast(beta1_power, grad.dtype.base_dtype),
161 math_ops.cast(beta2_power, grad.dtype.base_dtype),
162 math_ops.cast(self._lr_t, grad.dtype.base_dtype)
[all...] |
| /external/tensorflow/tensorflow/contrib/coder/python/ops/ |
| coder_ops_test.py | 24 from tensorflow.python.ops import math_ops
38 histogram = math_ops.bincount(data, minlength=10, maxlength=10)
39 cdf = math_ops.cumsum(histogram, exclusive=False)
43 data = math_ops.cast(data, dtypes.int16)
|
| /external/tensorflow/tensorflow/contrib/kfac/python/kernel_tests/ |
| op_queue_test.py | 23 from tensorflow.python.ops import math_ops
33 math_ops.add(1, 2),
34 math_ops.subtract(1, 2),
35 math_ops.reduce_mean([1, 2]),
|
| /external/tensorflow/tensorflow/contrib/sparsemax/python/ops/ |
| sparsemax_loss.py | 23 from tensorflow.python.ops import math_ops
51 math_ops.reduce_mean(logits, axis=1)[:, array_ops.newaxis]
54 support = math_ops.cast(sparsemax > 0, sparsemax.dtype)
60 return math_ops.reduce_sum(sum_s + q_part, axis=1)
|
| /external/tensorflow/tensorflow/compiler/tests/ |
| argminmax_test.py | 26 from tensorflow.python.ops import math_ops
53 lambda x: math_ops.argmax(x, axis=0, output_type=dtypes.int32),
57 lambda x: math_ops.argmax(x, axis=0, output_type=dtypes.int32),
61 lambda x: math_ops.argmax(x, axis=1, output_type=dtypes.int32),
66 lambda x: math_ops.argmin(x, axis=0, output_type=dtypes.int32),
70 lambda x: math_ops.argmin(x, axis=0, output_type=dtypes.int32),
74 lambda x: math_ops.argmin(x, axis=1, output_type=dtypes.int32),
|
| /external/tensorflow/tensorflow/contrib/seq2seq/python/ops/ |
| loss.py | 24 from tensorflow.python.ops import math_ops
97 crossent = math_ops.reduce_sum(crossent)
98 total_size = math_ops.reduce_sum(weights)
106 crossent = math_ops.reduce_sum(crossent, axis=[1])
107 total_size = math_ops.reduce_sum(weights, axis=[1])
111 crossent = math_ops.reduce_sum(crossent, axis=[0])
112 total_size = math_ops.reduce_sum(weights, axis=[0])
|
