/frameworks/ml/nn/tools/test_generator/tests/P_depthwise_conv/ |
depthwise_conv.bin.mod.py | 9 i0 = Parameter("op0", "TENSOR_FLOAT32", "{1, 1, 1, 3}", [-0.966213, -0.467474, -0.82203]) # parameters variable 11 model = model.DepthWiseConv(i2, i0, i1, i4, i5, i6, i7, i8).To(i3)
|
/frameworks/ml/nn/tools/test_generator/tests/P_quantized_conv/ |
quantized.mod.py | 7 i0 = Parameter("op0", "TENSOR_QUANT8_ASYMM", "{1, 2, 2, 1}", [1, 1, 1, 1]) # parameters variable 10 model = model.Conv(i2, i0, i1, i4, i5, i6, i7).To(i3)
|
/external/clang/test/CodeGen/ |
fp16-ops.c | 15 volatile int i0; variable 101 h1 = h0 * i0; 131 h1 = (h0 / i0); 161 h1 = (h0 + i0); 191 h1 = (h0 - i0); 216 test = (i0 < h0); 220 test = (h0 < i0); 245 test = (i0 > h0); 249 test = (h0 > i0); 274 test = (i0 <= h0) [all...] |
/external/clang/test/Sema/ |
attr-unused.c | 22 Int_not_unused i0; // expected-warning {{unused variable}} local
|
/external/libchrome/base/third_party/icu/ |
icu_utf.cc | 212 int32_t i0 = i; local 218 c=utf8_errorValue[i-i0];
|
/frameworks/ml/nn/runtime/test/generated/models/ |
avg_pool_float_2.model.cpp | 7 auto i0 = model->addOperand(&type0); local 22 model->addOperation(ANEURALNETWORKS_AVERAGE_POOL_2D, {i0, padding, padding, padding, padding, stride, stride, filter, filter, activation}, {output}); 25 {i0},
|
avg_pool_float_2_relaxed.model.cpp | 7 auto i0 = model->addOperand(&type0); local 22 model->addOperation(ANEURALNETWORKS_AVERAGE_POOL_2D, {i0, padding, padding, padding, padding, stride, stride, filter, filter, activation}, {output}); 25 {i0},
|
avg_pool_float_3.model.cpp | 7 auto i0 = model->addOperand(&type0); local 22 model->addOperation(ANEURALNETWORKS_AVERAGE_POOL_2D, {i0, padding, padding, padding, padding, stride, stride, filter, filter, activation}, {output}); 25 {i0},
|
avg_pool_float_3_relaxed.model.cpp | 7 auto i0 = model->addOperand(&type0); local 22 model->addOperation(ANEURALNETWORKS_AVERAGE_POOL_2D, {i0, padding, padding, padding, padding, stride, stride, filter, filter, activation}, {output}); 25 {i0},
|
avg_pool_float_4.model.cpp | 7 auto i0 = model->addOperand(&type0); local 22 model->addOperation(ANEURALNETWORKS_AVERAGE_POOL_2D, {i0, padding, padding, padding, padding, stride, stride, filter, filter, relu6_activation}, {output}); 25 {i0},
|
avg_pool_float_4_relaxed.model.cpp | 7 auto i0 = model->addOperand(&type0); local 22 model->addOperation(ANEURALNETWORKS_AVERAGE_POOL_2D, {i0, padding, padding, padding, padding, stride, stride, filter, filter, relu6_activation}, {output}); 25 {i0},
|
avg_pool_quant8_2.model.cpp | 7 auto i0 = model->addOperand(&type0); local 22 model->addOperation(ANEURALNETWORKS_AVERAGE_POOL_2D, {i0, padding, padding, padding, padding, stride, stride, filter, filter, activation}, {output}); 25 {i0},
|
avg_pool_quant8_3.model.cpp | 7 auto i0 = model->addOperand(&type0); local 22 model->addOperation(ANEURALNETWORKS_AVERAGE_POOL_2D, {i0, padding, padding, padding, padding, stride, stride, filter, filter, activation}, {output}); 25 {i0},
|
max_pool_float_2.model.cpp | 7 auto i0 = model->addOperand(&type0); local 22 model->addOperation(ANEURALNETWORKS_MAX_POOL_2D, {i0, padding, padding, padding, padding, stride, stride, filter, filter, activation}, {output}); 25 {i0},
|
max_pool_float_2_relaxed.model.cpp | 7 auto i0 = model->addOperand(&type0); local 22 model->addOperation(ANEURALNETWORKS_MAX_POOL_2D, {i0, padding, padding, padding, padding, stride, stride, filter, filter, activation}, {output}); 25 {i0},
|
max_pool_float_3.model.cpp | 7 auto i0 = model->addOperand(&type0); local 22 model->addOperation(ANEURALNETWORKS_MAX_POOL_2D, {i0, padding, padding, padding, padding, stride, stride, filter, filter, relu6_activation}, {output}); 25 {i0},
|
max_pool_float_3_relaxed.model.cpp | 7 auto i0 = model->addOperand(&type0); local 22 model->addOperation(ANEURALNETWORKS_MAX_POOL_2D, {i0, padding, padding, padding, padding, stride, stride, filter, filter, relu6_activation}, {output}); 25 {i0},
|
max_pool_quant8_2.model.cpp | 7 auto i0 = model->addOperand(&type0); local 22 model->addOperation(ANEURALNETWORKS_MAX_POOL_2D, {i0, padding, padding, padding, padding, stride, stride, filter, filter, activation}, {output}); 25 {i0},
|
max_pool_quant8_3.model.cpp | 7 auto i0 = model->addOperand(&type0); local 22 model->addOperation(ANEURALNETWORKS_MAX_POOL_2D, {i0, padding, padding, padding, padding, stride, stride, filter, filter, relu1_activation}, {output}); 25 {i0},
|
/frameworks/ml/nn/runtime/test/specs/V1_0/ |
conv_1_h3_w2_SAME.mod.py | 8 i0 = Parameter("op0", "TENSOR_FLOAT32", "{1, 3, 2, 3}", [-0.966213, -0.467474, -0.82203, -0.579455, 0.0278809, -0.79946, -0.684259, 0.563238, 0.37289, 0.738216, 0.386045, -0.917775, 0.184325, -0.270568, 0.82236, 0.0973683, -0.941308, -0.144706]) # parameters variable 10 model = model.Conv(i2, i0, i1, i4, i5, i6, i7).To(i3)
|
conv_1_h3_w2_VALID.mod.py | 8 i0 = Parameter("op0", "TENSOR_FLOAT32", "{1, 3, 2, 3}", [-0.966213, -0.467474, -0.82203, -0.579455, 0.0278809, -0.79946, -0.684259, 0.563238, 0.37289, 0.738216, 0.386045, -0.917775, 0.184325, -0.270568, 0.82236, 0.0973683, -0.941308, -0.144706]) # parameters variable 10 model = model.Conv(i2, i0, i1, i4, i5, i6, i7).To(i3)
|
conv_3_h3_w2_SAME.mod.py | 8 i0 = Parameter("op0", "TENSOR_FLOAT32", "{3, 3, 2, 3}", [-0.966213, -0.579455, -0.684259, 0.738216, 0.184325, 0.0973683, -0.176863, -0.23936, -0.000233404, 0.055546, -0.232658, -0.316404, -0.012904, 0.320705, -0.326657, -0.919674, 0.868081, -0.824608, -0.467474, 0.0278809, 0.563238, 0.386045, -0.270568, -0.941308, -0.779227, -0.261492, -0.774804, -0.79665, 0.22473, -0.414312, 0.685897, -0.327792, 0.77395, -0.714578, -0.972365, 0.0696099, -0.82203, -0.79946, 0.37289, -0.917775, 0.82236, -0.144706, -0.167188, 0.268062, 0.702641, -0.412223, 0.755759, 0.721547, -0.43637, -0.274905, -0.269165, 0.16102, 0.819857, -0.312008]) # parameters variable 10 model = model.Conv(i2, i0, i1, i4, i5, i6, i7).To(i3)
|
conv_3_h3_w2_VALID.mod.py | 8 i0 = Parameter("op0", "TENSOR_FLOAT32", "{3, 3, 2, 3}", [-0.966213, -0.579455, -0.684259, 0.738216, 0.184325, 0.0973683, -0.176863, -0.23936, -0.000233404, 0.055546, -0.232658, -0.316404, -0.012904, 0.320705, -0.326657, -0.919674, 0.868081, -0.824608, -0.467474, 0.0278809, 0.563238, 0.386045, -0.270568, -0.941308, -0.779227, -0.261492, -0.774804, -0.79665, 0.22473, -0.414312, 0.685897, -0.327792, 0.77395, -0.714578, -0.972365, 0.0696099, -0.82203, -0.79946, 0.37289, -0.917775, 0.82236, -0.144706, -0.167188, 0.268062, 0.702641, -0.412223, 0.755759, 0.721547, -0.43637, -0.274905, -0.269165, 0.16102, 0.819857, -0.312008]) # parameters variable 10 model = model.Conv(i2, i0, i1, i4, i5, i6, i7).To(i3)
|
depthwise_conv.mod.py | 9 i0 = Parameter("op0", "TENSOR_FLOAT32", "{1, 1, 1, 3}", [-0.966213, -0.467474, -0.82203]) # parameters variable 11 model = model.DepthWiseConv(i2, i0, i1, i4, i5, i6, i7, i8).To(i3)
|
logistic_float_2.mod.py | 25 i0 = Input("input", "TENSOR_FLOAT32", "{%d, %d, %d, %d}" % (d0, d1, d2, d3)) variable 29 model = model.Operation("LOGISTIC", i0).To(output) 34 input0 = {i0: input_values}
|