/frameworks/ml/nn/runtime/test/specs/ |
H A D | fully_connected_float_large_weights_as_inputs.mod.py | 20 bias = Input("b0", "TENSOR_FLOAT32", "{1}") variable 23 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0) 30 bias:
|
H A D | fully_connected_float_weights_as_inputs.mod.py | 20 bias = Input("b0", "TENSOR_FLOAT32", "{1}") variable 23 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0) 29 bias: [4]}
|
H A D | fully_connected_quant8_large_weights_as_inputs.mod.py | 20 bias = Input("b0", "TENSOR_INT32", "{1}, 0.04, 0") variable 23 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0) 30 bias:
|
H A D | fully_connected_quant8_weights_as_inputs.mod.py | 20 bias = Input("b0", "TENSOR_INT32", "{1}, 0.25f, 0") variable 23 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0) 29 bias: [4]}
|
H A D | fully_connected_float.mod.py | 20 bias = Parameter("b0", "TENSOR_FLOAT32", "{1}", [4]) variable 23 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0)
|
H A D | fully_connected_float_large.mod.py | 20 bias = Parameter("b0", "TENSOR_FLOAT32", "{1}", [900000]) variable 23 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0)
|
H A D | fully_connected_quant8.mod.py | 20 bias = Parameter("b0", "TENSOR_INT32", "{1}, 0.25f, 0", [4]) variable 23 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0)
|
H A D | fully_connected_quant8_large.mod.py | 20 bias = Parameter("b0", "TENSOR_INT32", "{1}, 0.04, 0", [10]) variable 23 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0)
|
H A D | local_response_norm_float_1.mod.py | 4 bias = Float32Scalar("bias", 9.) variable 9 model = model.Operation("LOCAL_RESPONSE_NORMALIZATION", i1, radius, bias, alpha, beta).To(output)
|
H A D | local_response_norm_float_2.mod.py | 4 bias = Float32Scalar("bias", 0.) variable 9 model = model.Operation("LOCAL_RESPONSE_NORMALIZATION", i1, radius, bias, alpha, beta).To(output)
|
H A D | local_response_norm_float_3.mod.py | 4 bias = Float32Scalar("bias", 0.) variable 9 model = model.Operation("LOCAL_RESPONSE_NORMALIZATION", i1, radius, bias, alpha, beta).To(output)
|
H A D | local_response_norm_float_4.mod.py | 4 bias = Float32Scalar("bias", 9.) variable 9 model = model.Operation("LOCAL_RESPONSE_NORMALIZATION", i1, radius, bias, alpha, beta).To(output)
|
H A D | rnn_state.mod.py | 26 bias = Input("bias", "TENSOR_FLOAT32", "{%d}" % (units)) variable 34 model = model.Operation("RNN", input, weights, recurrent_weights, bias, hidden_state_in, 80 bias: [
|
H A D | svdf_state.mod.py | 27 bias = Input("bias", "TENSOR_FLOAT32", "{%d}" % (units)) variable 34 model = model.Operation("SVDF", input, weights_feature, weights_time, bias, state_in, 56 bias: [],
|
H A D | rnn.mod.py | 26 bias = Input("bias", "TENSOR_FLOAT32", "{%d}" % (units)) variable 34 model = model.Operation("RNN", input, weights, recurrent_weights, bias, hidden_state_in, 80 bias: [
|
/frameworks/native/services/sensorservice/ |
H A D | CorrectedGyroSensor.cpp | 59 const vec3_t bias(mSensorFusion.getGyroBias()); 61 outEvent->data[0] -= bias.x; 62 outEvent->data[1] -= bias.y; 63 outEvent->data[2] -= bias.z;
|
/frameworks/ml/nn/common/operations/ |
H A D | Normalization.cpp | 45 int32_t radius, float bias, float alpha, float beta, 49 radius, bias, alpha, beta, 44 localResponseNormFloat32(const float* inputData, const Shape& inputShape, int32_t radius, float bias, float alpha, float beta, float* outputData, const Shape& outputShape) argument
|
/frameworks/ml/nn/runtime/test/generated/models/ |
H A D | local_response_norm_float_1.model.cpp | 9 auto bias = model->addOperand(&type2); local 17 model->setOperandValue(bias, bias_init, sizeof(float) * 1); 22 model->addOperation(ANEURALNETWORKS_LOCAL_RESPONSE_NORMALIZATION, {input, radius, bias, alpha, beta}, {output});
|
H A D | local_response_norm_float_2.model.cpp | 9 auto bias = model->addOperand(&type2); local 17 model->setOperandValue(bias, bias_init, sizeof(float) * 1); 22 model->addOperation(ANEURALNETWORKS_LOCAL_RESPONSE_NORMALIZATION, {input, radius, bias, alpha, beta}, {output});
|
H A D | local_response_norm_float_3.model.cpp | 9 auto bias = model->addOperand(&type2); local 17 model->setOperandValue(bias, bias_init, sizeof(float) * 1); 22 model->addOperation(ANEURALNETWORKS_LOCAL_RESPONSE_NORMALIZATION, {input, radius, bias, alpha, beta}, {output});
|
H A D | local_response_norm_float_4.model.cpp | 9 auto bias = model->addOperand(&type2); local 17 model->setOperandValue(bias, bias_init, sizeof(float) * 1); 22 model->addOperation(ANEURALNETWORKS_LOCAL_RESPONSE_NORMALIZATION, {input, radius, bias, alpha, beta}, {output});
|
H A D | rnn.model.cpp | 13 auto bias = model->addOperand(&type3); local 19 model->addOperation(ANEURALNETWORKS_RNN, {input, weights, recurrent_weights, bias, hidden_state_in, activation_param}, {hidden_state_out, output}); 22 {input, weights, recurrent_weights, bias, hidden_state_in, activation_param},
|
H A D | rnn_state.model.cpp | 13 auto bias = model->addOperand(&type3); local 19 model->addOperation(ANEURALNETWORKS_RNN, {input, weights, recurrent_weights, bias, hidden_state_in, activation_param}, {hidden_state_out, output}); 22 {input, weights, recurrent_weights, bias, hidden_state_in, activation_param},
|
H A D | svdf.model.cpp | 14 auto bias = model->addOperand(&type3); local 21 model->addOperation(ANEURALNETWORKS_SVDF, {input, weights_feature, weights_time, bias, state_in, rank_param, activation_param}, {state_out, output}); 24 {input, weights_feature, weights_time, bias, state_in, rank_param, activation_param},
|
H A D | svdf_state.model.cpp | 14 auto bias = model->addOperand(&type3); local 21 model->addOperation(ANEURALNETWORKS_SVDF, {input, weights_feature, weights_time, bias, state_in, rank_param, activation_param}, {state_out, output}); 24 {input, weights_feature, weights_time, bias, state_in, rank_param, activation_param},
|