/aosp_15_r20/external/libopus/dnn/torch/rdovae/ |
H A D | export_rdovae_weights.py | 190 ('core_encoder.module.dense_1' , 'enc_dense1', 'TANH', False,), 192 ('core_encoder.module.state_dense_1' , 'gdense1' , 'TANH', True,), 193 ('core_encoder.module.state_dense_2' , 'gdense2' , 'TANH', True) 202 ('core_encoder.module.gru1' , 'enc_gru1', 'TANH', True), 203 ('core_encoder.module.gru2' , 'enc_gru2', 'TANH', True), 204 ('core_encoder.module.gru3' , 'enc_gru3', 'TANH', True), 205 ('core_encoder.module.gru4' , 'enc_gru4', 'TANH', True), 206 ('core_encoder.module.gru5' , 'enc_gru5', 'TANH', True), 214 ('core_encoder.module.conv1.conv' , 'enc_conv1', 'TANH', True), 215 ('core_encoder.module.conv2.conv' , 'enc_conv2', 'TANH', True), [all …]
|
/aosp_15_r20/libcore/luni/src/test/resources/ |
H A D | math_important_numbers.csv | 568 tanh,0x1.fb8f76b1e2ab6p-1,0x1.5bf0a8b145769p1,2.718281828459045 569 tanh,-0x1.fb8f76b1e2ab6p-1,-0x1.5bf0a8b145769p1,-2.718281828459045 570 tanh,0x0.0p0,0x0.0p0,0.0 571 tanh,-0x0.0p0,-0x0.0p0,-0.0 572 tanh,0x1.85efab514f394p-1,0x1.0p0,1.0 573 tanh,-0x1.85efab514f394p-1,-0x1.0p0,-1.0 574 tanh,-0x1.d9353d7568af3p-2,-0x1.0p-1,-0.5 575 tanh,0x1.d9353d7568af3p-2,0x1.0p-1,0.5 576 tanh,-0x1.ffff15f81f9abp-1,-0x1.921fb54442d18p2,-6.283185307179586 577 tanh,-0x1.fffe74ef7ed71p-1,-0x1.815e630c155e1p2,-6.021385919380436 [all …]
|
/aosp_15_r20/external/python/cpython3/Lib/test/ |
D | cmath_testcases.txt | 1580 -- For exp, cosh, sinh, tanh we limit tests to arguments whose 1932 -- tanh: Hyperbolic Tangent -- 1939 -- tanh0000 tanh 0.0 0.0 -> 0.0 0.0 1940 -- tanh0001 tanh 0.0 -0.0 -> 0.0 -0.0 1941 -- tanh0002 tanh -0.0 0.0 -> -0.0 0.0 1942 -- tanh0003 tanh -0.0 -0.0 -> -0.0 -0.0 1945 tanh0004 tanh -21.200500450664993 -1.6970729480342996 -> -1.0 1.9241352344849399e-19 1946 tanh0005 tanh -0.34158771504251928 -8.0848504951747131 -> -2.123711225855613 1.2827526782026006 1947 tanh0006 tanh -15.454144725193689 -0.23619582288265617 -> -0.99999999999993283 -3.4336684248260036e… 1948 tanh0007 tanh -7.6103163119661952 -0.7802748320307008 -> -0.99999999497219438 -4.9064845343755437e-… [all …]
|
/aosp_15_r20/bionic/libm/upstream-freebsd/lib/msun/src/ |
H A D | s_tanh.c | 12 /* Tanh(x) 18 * 0. tanh(x) is defined to be ----------- 21 * 1. reduce x to non-negative by tanh(-x) = -tanh(x). 22 * 2. 0 <= x < 2**-28 : tanh(x) := x with inexact if x != 0 24 * 2**-28 <= x < 1 : tanh(x) := -----; t = expm1(-2x) 27 * 1 <= x < 22 : tanh(x) := 1 - -----; t = expm1(2x) 29 * 22 <= x <= INF : tanh(x) := 1. 32 * tanh(NaN) is NaN; 33 * only tanh(0)=0 is exact for finite argument. 45 tanh(double x) in tanh() function [all …]
|
/aosp_15_r20/external/pytorch/aten/src/ATen/native/quantized/cpu/qnnpack/src/ |
H A D | tanh.c | 42 "failed to create TanH operator with %zu channels: number of channels must be non-zero", in pytorch_qnnp_create_tanh_nc_q8() 49 "failed to create TanH operator with %.7g input scale: scale must be finite and positive", in pytorch_qnnp_create_tanh_nc_q8() 56 "failed to create TanH operator with %.7g output scale: scale must be finite and positive", in pytorch_qnnp_create_tanh_nc_q8() 63 "failed to create TanH operator with [%" PRIu8 ", %" PRIu8 in pytorch_qnnp_create_tanh_nc_q8() 74 … "failed to create TanH operator with %.7g output scale: only output scale of 2/256 is supported", in pytorch_qnnp_create_tanh_nc_q8() 81 "failed to create TanH operator with %" PRIu8 in pytorch_qnnp_create_tanh_nc_q8() 100 "failed to allocate 256 bytes for TanH lookup table"); in pytorch_qnnp_create_tanh_nc_q8() 110 /* Scale tanh(x) by 1 / output scale = 128.0 in pytorch_qnnp_create_tanh_nc_q8() 137 pytorch_qnnp_operator_t tanh, in pytorch_qnnp_setup_tanh_nc_q8() argument 150 tanh->batch_size = 0; in pytorch_qnnp_setup_tanh_nc_q8() [all …]
|
/aosp_15_r20/external/pytorch/test/cpp/tensorexpr/ |
H A D | test_graph_opt.cpp | 85 %6 : Float(60, strides=[1], device=cpu) = aten::tanh(%5) in TEST_F() 93 // The `aten::log` and `aten::tanh` ops must be moved to the inputs of in TEST_F() 99 ->check("aten::tanh") in TEST_F() 100 ->check("aten::tanh") in TEST_F() 101 ->check("aten::tanh") in TEST_F() 104 ->check_not("aten::tanh") in TEST_F() 110 auto ref = at::tanh(at::log(at::cat({x, y, z}, 0))); in TEST_F() 132 %5 : Float(60, strides=[1], device=cpu) = aten::tanh(%cat) in TEST_F() 141 // The `aten::tanh` op must be moved to the inputs of `aten::cat`. in TEST_F() 145 .check("aten::tanh") in TEST_F() [all …]
|
/aosp_15_r20/external/python/cpython2/Lib/test/ |
D | cmath_testcases.txt | 1555 -- For exp, cosh, sinh, tanh we limit tests to arguments whose 1858 -- tanh: Hyperbolic Tangent -- 1862 tanh0000 tanh 0.0 0.0 -> 0.0 0.0 1863 tanh0001 tanh 0.0 -0.0 -> 0.0 -0.0 1864 tanh0002 tanh -0.0 0.0 -> -0.0 0.0 1865 tanh0003 tanh -0.0 -0.0 -> -0.0 -0.0 1868 tanh0004 tanh -21.200500450664993 -1.6970729480342996 -> -1.0 1.9241352344849399e-19 1869 tanh0005 tanh -0.34158771504251928 -8.0848504951747131 -> -2.123711225855613 1.2827526782026006 1870 tanh0006 tanh -15.454144725193689 -0.23619582288265617 -> -0.99999999999993283 -3.4336684248260036e… 1871 tanh0007 tanh -7.6103163119661952 -0.7802748320307008 -> -0.99999999497219438 -4.9064845343755437e-… [all …]
|
/aosp_15_r20/art/test/123-inline-execute2/ |
H A D | expected-stdout.txt | 8 Math.tanh(0.0) = 0.000000000000 18 Math.tanh(0.7853981633974483) = 0.655794202633 27 Math.tanh(1.5707963267948966) = 0.917152335667 37 Math.tanh(2.356194490192345) = 0.982193380007 47 Math.tanh(3.141592653589793) = 0.996272076221 57 Math.tanh(3.9269908169872414) = 0.999223894879 66 Math.tanh(4.71238898038469) = 0.999838613989 76 Math.tanh(5.497787143782138) = 0.999966449000 86 Math.tanh(6.283185307179586) = 0.999993025340 157 StrictMath.tanh(0.0) = 0.0 [all …]
|
/aosp_15_r20/external/tensorflow/tensorflow/python/kernel_tests/math_ops/ |
H A D | cwise_ops_unary_test.py | 206 self._compareBoth(x, np.tanh, math_ops.tanh) 235 self._compareBothSparse(x, np.tanh, math_ops.tanh) 242 self._compareBoth(x, np.tanh, math_ops.tanh) 244 self._compareBoth(x, np.tanh, math_ops.tanh) 265 self._compareBoth(x, np.tanh, math_ops.tanh) 290 self._compareBothSparse(x, np.tanh, math_ops.tanh) 316 self._compareBoth(x, np.tanh, math_ops.tanh) 344 self._compareBothSparse(x, np.tanh, math_ops.tanh) 369 self._compareBoth(x, np.tanh, math_ops.tanh) 392 self._compareBothSparse(x, np.tanh, math_ops.tanh) [all …]
|
/aosp_15_r20/external/tensorflow/tensorflow/compiler/jit/ |
H A D | introduce_floating_point_jitter_pass_test.cc | 46 Output tanh_a = ops::Tanh(root.WithOpName("tanh_a"), sigmoid_a); in TEST() 47 Output tanh_b = ops::Tanh(root.WithOpName("tanh_b"), sigmoid_b); in TEST() 62 auto m_tanh_a = NodeWith(Op("Tanh"), Inputs(Out(m_sigmoid_a_with_jitter))); in TEST() 67 auto m_tanh_b = NodeWith(Op("Tanh"), Inputs(Out(m_sigmoid_b_with_jitter))); in TEST() 125 Output tanh = ops::Tanh(root.WithOpName("tanh"), sigmoid); in TEST() local 139 auto m_tanh = NodeWith(Op("Tanh"), Inputs(Out(m_sigmoid_with_jitter))); in TEST() 141 Node* tanh_transformed = testing::FindNodeByName(graph.get(), "tanh"); in TEST() 155 Output tanh_s = ops::Tanh(root.WithOpName("tanh_s"), svd.s); in TEST() 156 Output tanh_u = ops::Tanh(root.WithOpName("tanh_u"), svd.u); in TEST() 157 Output tanh_v = ops::Tanh(root.WithOpName("tanh_v"), svd.v); in TEST() [all …]
|
/aosp_15_r20/libcore/ojluni/src/test/java/lang/Math/ |
H A D | HyperbolicTests.java | 27 * @summary Tests for {Math, StrictMath}.{sinh, cosh, tanh} 742 * Test accuracy of {Math, StrictMath}.tanh. The specified accuracy is 2.5 ulps. 744 * The definition of tanh(x) is 748 * The series expansion of tanh(x) = 754 * 1. For large values of x tanh(x) ~= signum(x) 756 * 2. For small values of x, tanh(x) ~= x. 758 * Additionally, tanh is an odd function; tanh(-x) = -tanh(x). 771 // x tanh(x) in testTanh() 970 // For values of x larger than 22, tanh(x) is 1.0 in double in testTanh() 988 Tests.testTolerance("Math.tanh(double", in testTanhCaseWithTolerance() [all …]
|
/aosp_15_r20/external/arm-optimized-routines/pl/math/test/testcases/directed/ |
H A D | tanh.tst | 1 ; tanh.tst 6 func=tanh op1=7ff80000.00000001 result=7ff80000.00000001 errno=0 7 func=tanh op1=fff80000.00000001 result=7ff80000.00000001 errno=0 8 func=tanh op1=7ff00000.00000001 result=7ff80000.00000001 errno=0 status=i 9 func=tanh op1=fff00000.00000001 result=7ff80000.00000001 errno=0 status=i 10 func=tanh op1=7ff00000.00000000 result=3ff00000.00000000 errno=0 11 func=tanh op1=fff00000.00000000 result=bff00000.00000000 errno=0 12 func=tanh op1=00000000.00000000 result=00000000.00000000 errno=0 13 func=tanh op1=80000000.00000000 result=80000000.00000000 errno=0 17 func=tanh op1=00000000.00000001 result=00000000.00000001 errno=0 maybestatus=ux [all …]
|
/aosp_15_r20/external/pytorch/benchmarks/fastrnns/ |
H A D | cells.py | 19 cellgate = cellgate.tanh() 23 hy = outgate * cy.tanh() 43 cellgate = torch.tanh(cellgate) 47 hy = outgate * torch.tanh(cy) 67 cellgate = torch.tanh(cellgate) 71 hy = outgate * torch.tanh(cy) 90 cellgate = torch.tanh(cellgate) 94 hy = outgate * torch.tanh(cy) 109 cellgate = torch.tanh(cellgate) 113 hy = outgate * torch.tanh(cy) [all …]
|
/aosp_15_r20/external/arm-optimized-routines/pl/math/ |
H A D | v_tanh_3u.c | 2 * Double-precision vector tanh(x) function. 42 the scalar variant of tanh. */ in expm1_inline() 66 return v_call_f64 (tanh, x, y, special); in special_case() 69 /* Vector approximation for double-precision tanh(x), using a simplified 73 float64x2_t VPCS_ATTR V_NAME_D1 (tanh) (float64x2_t x) in V_NAME_D1() argument 92 /* tanh(x) = (e^2x - 1) / (e^2x + 1). */ in V_NAME_D1() 101 PL_SIG (V, D, 1, tanh, -10.0, 10.0) 102 PL_TEST_ULP (V_NAME_D1 (tanh), 2.27) 103 PL_TEST_EXPECT_FENV (V_NAME_D1 (tanh), WANT_SIMD_EXCEPT) 104 PL_TEST_SYM_INTERVAL (V_NAME_D1 (tanh), 0, 0x1p-27, 5000) [all …]
|
H A D | sv_tanh_3u.c | 2 * Double-precision SVE tanh(x) function. 40 the scalar variant of tanh. */ in expm1_inline() 65 return sv_call_f64 (tanh, x, y, special); in special_case() 68 /* SVE approximation for double-precision tanh(x), using a simplified 72 svfloat64_t SV_NAME_D1 (tanh) (svfloat64_t x, svbool_t pg) in SV_NAME_D1() argument 83 /* tanh(x) = (e^2x - 1) / (e^2x + 1). */ in SV_NAME_D1() 92 PL_SIG (SV, D, 1, tanh, -10.0, 10.0) 93 PL_TEST_ULP (SV_NAME_D1 (tanh), 2.27) 94 PL_TEST_SYM_INTERVAL (SV_NAME_D1 (tanh), 0, 0x1p-27, 5000) 95 PL_TEST_SYM_INTERVAL (SV_NAME_D1 (tanh), 0x1p-27, 0x1.241bf835f9d5fp+4, 50000) [all …]
|
H A D | tanh_3u.c | 2 * Double-precision tanh(x) function. 48 /* Approximation for double-precision tanh(x), using a simplified version of 50 tanh(-0x1.c4a4ca0f9f3b7p-3) got -0x1.bd6a21a163627p-3 53 tanh (double x) in tanh() function 69 /* tanh(x) = (e^2x - 1) / (e^2x + 1). */ in tanh() 74 PL_SIG (S, D, 1, tanh, -10.0, 10.0) 75 PL_TEST_ULP (tanh, 2.27) 76 PL_TEST_SYM_INTERVAL (tanh, 0, TinyBound, 1000) 77 PL_TEST_SYM_INTERVAL (tanh, TinyBound, BoringBound, 100000) 78 PL_TEST_SYM_INTERVAL (tanh, BoringBound, inf, 1000)
|
H A D | v_tanhf_2u6.c | 2 * Single-precision vector tanh(x) function. 32 /* Approximation for single-precision vector tanh(x), using a simplified 36 float32x4_t VPCS_ATTR V_NAME_F1 (tanh) (float32x4_t x) in V_NAME_F1() argument 59 /* tanh(x) = (e^2x - 1) / (e^2x + 1). */ in V_NAME_F1() 68 PL_SIG (V, F, 1, tanh, -10.0, 10.0) 69 PL_TEST_ULP (V_NAME_F1 (tanh), 2.09) 70 PL_TEST_EXPECT_FENV (V_NAME_F1 (tanh), WANT_SIMD_EXCEPT) 71 PL_TEST_SYM_INTERVAL (V_NAME_F1 (tanh), 0, 0x1p-23, 1000) 72 PL_TEST_SYM_INTERVAL (V_NAME_F1 (tanh), 0x1p-23, 0x1.205966p+3, 100000) 73 PL_TEST_SYM_INTERVAL (V_NAME_F1 (tanh), 0x1.205966p+3, inf, 100)
|
H A D | sv_tanhf_2u6.c | 2 * Single-precision SVE tanh(x) function. 31 /* Approximation for single-precision SVE tanh(x), using a simplified 35 svfloat32_t SV_NAME_F1 (tanh) (svfloat32_t x, const svbool_t pg) in SV_NAME_F1() argument 47 /* tanh(x) = (e^2x - 1) / (e^2x + 1). */ in SV_NAME_F1() 55 PL_SIG (SV, F, 1, tanh, -10.0, 10.0) 56 PL_TEST_ULP (SV_NAME_F1 (tanh), 2.07) 57 PL_TEST_SYM_INTERVAL (SV_NAME_F1 (tanh), 0, 0x1p-23, 1000) 58 PL_TEST_SYM_INTERVAL (SV_NAME_F1 (tanh), 0x1p-23, 0x1.205966p+3, 100000) 59 PL_TEST_SYM_INTERVAL (SV_NAME_F1 (tanh), 0x1.205966p+3, inf, 100)
|
/aosp_15_r20/prebuilts/go/linux-x86/src/math/ |
D | tanh.go | 11 // tanh.c 17 // double x, y, tanh(); 19 // y = tanh( x ); 30 // tanh(x) = sinh(x)/cosh(x) = 1 - 2/(exp(2x) + 1). 68 // Tanh returns the hyperbolic tangent of x. 72 // Tanh(±0) = ±0 73 // Tanh(±Inf) = ±1 74 // Tanh(NaN) = NaN 75 func Tanh(x float64) float64 { func 79 return tanh(x) [all …]
|
/aosp_15_r20/external/executorch/backends/arm/test/ops/ |
H A D | test_tanh.py | 32 class Tanh(torch.nn.Module): class in TestTanh 35 self.tanh = torch.nn.Tanh() 38 return self.tanh(x) 50 .check(["torch.ops.aten.tanh.default"]) 69 .check(["torch.ops.aten.tanh.default"]) 93 .check_count({"torch.ops.aten.tanh.default": 1}) 122 self._test_tanh_tosa_MI_pipeline(self.Tanh(), (test_data,)) 126 self._test_tanh_tosa_BI_pipeline(self.Tanh(), (test_data,)) 130 self._test_tanh_tosa_u55_BI_pipeline(self.Tanh(), (test_data,)) 134 self._test_tanh_tosa_u85_BI_pipeline(self.Tanh(), (test_data,))
|
/aosp_15_r20/external/armnn/docs/ |
H A D | 05_03_delegate.dox | 44 - AVERAGE_POOL_2D, Supported Fused Activation: RELU, RELU6, RELU_N1_TO_1, SIGMOID, TANH, NONE 46 - AVERAGE_POOL_3D, Supported Fused Activation: RELU, RELU6, RELU_N1_TO_1, SIGMOID, SIGN_BIT, TANH, … 54 - CONCATENATION, Supported Fused Activation: RELU, RELU6, RELU_N1_TO_1, SIGMOID, TANH, NONE 56 - CONV_2D, Supported Fused Activation: RELU, RELU6, RELU_N1_TO_1, SIGMOID, TANH, NONE 58 - CONV_3D, Supported Fused Activation: RELU, RELU6, RELU_N1_TO_1, SIGMOID, TANH, NONE 62 - DEPTHWISE_CONV_2D, Supported Fused Activation: RELU, RELU6, RELU_N1_TO_1, SIGMOID, TANH, NONE 82 - FULLY_CONNECTED, Supported Fused Activation: RELU, RELU6, RELU_N1_TO_1, SIGMOID, TANH, NONE 120 - MAX_POOL_2D, Supported Fused Activation: RELU, RELU6, RELU_N1_TO_1, SIGMOID, TANH, NONE 122 - MAX_POOL_3D, Supported Fused Activation: RELU, RELU6, RELU_N1_TO_1, SIGMOID, SIGN_BIT, TANH, NONE 192 - TANH
|
/aosp_15_r20/external/tensorflow/tensorflow/compiler/xla/tests/ |
H A D | exhaustive_unary_test_complex.cc | 41 // TODO(b/138126045): Current libc++ implementation of the complex tanh in SetParamsForTanh() 44 // TODO(b/138750327): Current libc++ implementation of the complex tanh in SetParamsForTanh() 121 // The current libc++ implementation of the complex tanh function provides 122 // less accurate results when the denomenator of a complex tanh is small, due 124 // we cast it to and from a complex128 when computing tanh. 125 UNARY_TEST_COMPLEX_64(Tanh, { 128 // This implementation of Tanh becomes less accurate when the denominator in __anon9f6fcb090602() 137 Tanh, 139 return static_cast<complex64>(std::tanh(static_cast<complex128>(x))); in __anon9f6fcb090702() 192 // Similar to the Tanh bug. [all …]
|
/aosp_15_r20/external/tensorflow/tensorflow/lite/kernels/internal/reference/ |
H A D | lstm_cell.h | 120 const float new_input = std::tanh(activ_temp_data[Offset( in LstmCell() 136 output_gate * std::tanh(new_state); in LstmCell() 180 // for a fixed-point tanh() implementation for that format, which internally 190 // This array is only fed to Logistic and Tanh functions, for which 198 // Now, Logistic and Tanh 202 // Logistic(4) = 1 - 1.8e-2 Tanh(4) = 1 - 6.7e-4 203 // Logistic(8) = 1 - 3.4e-4 Tanh(8) = 1 - 2.3e-7 204 // Logistic(16) = 1 - 1.1e-7 Tanh(16) = 1 - 2.5e-14 345 // Rest of the LSTM cell: tanh and logistic math functions, and some adds in LstmCell() 355 // This is the return type of math functions such as tanh, logistic, in LstmCell() [all …]
|
/aosp_15_r20/external/tensorflow/tensorflow/compiler/mlir/tensorflow/tests/ |
H A D | layout_optimization_move_transposes_begin.mlir | 8 // CHECK: %[[TANH:[0-9]*]] = "tf.Tanh"(%[[ARG_TRANSPOSE]]) {{.*}} tensor<1x8x4x4xf32> 9 // CHECK: return %[[TANH]] 11 %0 = "tf.Tanh"(%arg0) : (tensor<1x4x4x8xf32>) -> tensor<1x4x4x8xf32> 23 // CHECK: %[[TANH:[0-9]*]] = "tf.Tanh"(%[[ARG_TRANSPOSE]]) {{.*}} tensor<1x8x4x4xf32> 24 // CHECK: %[[RELU:[0-9]*]] = "tf.Relu"(%[[TANH]]) {{.*}} tensor<1x8x4x4xf32> 27 %0 = "tf.Tanh"(%arg0) : (tensor<1x4x4x8xf32>) -> tensor<1x4x4x8xf32> 57 // CHECK: %[[TANH:[0-9]*]] = "tf.Tanh"(%[[ARG_TRANSPOSE]]) {{.*}} tensor<1x8x4x4xf32> 58 // CHECK: %[[ADD:[0-9]*]] = "tf.AddV2"(%[[TANH]], %[[TANH]]) {{.*}} tensor<1x8x4x4xf32> 61 %0 = "tf.Tanh"(%arg0) : (tensor<1x4x4x8xf32>) -> tensor<1x4x4x8xf32>
|
/aosp_15_r20/external/libopus/dnn/training_tf2/ |
H A D | rdovae.py | 78 y = x - d*tf.math.tanh(x/(.1+d)) 205 … enc_dense1 = Dense(cond_size2, activation='tanh', kernel_constraint=constraint, name='enc_dense1') 207 … enc_dense3 = Dense(cond_size2, activation='tanh', kernel_constraint=constraint, name='enc_dense3') 209 … enc_dense5 = Dense(cond_size2, activation='tanh', kernel_constraint=constraint, name='enc_dense5') 211 … enc_dense7 = Dense(cond_size, activation='tanh', kernel_constraint=constraint, name='enc_dense7') 212 … enc_dense8 = Dense(cond_size, activation='tanh', kernel_constraint=constraint, name='enc_dense8') 229 global_dense1 = Dense(128, activation='tanh', name='gdense1') 230 global_dense2 = Dense(nb_state_dim, activation='tanh', name='gdense2') 242 … dec_dense1 = Dense(cond_size2, activation='tanh', kernel_constraint=constraint, name='dec_dense1') 244 … dec_dense3 = Dense(cond_size2, activation='tanh', kernel_constraint=constraint, name='dec_dense3') [all …]
|