Searched refs:input_size (Results 1 – 4 of 4) sorted by relevance
/hardware/qcom/neuralnetworks/hvxservice/1.0/ |
D | HexagonModel.cpp | 237 uint32_t input_size = dims[3]; in createFullyConnectedWeightTensor() local 240 num_units, input_size, reinterpret_cast<const float*>(operandInfo.buffer)); in createFullyConnectedWeightTensor() 241 return createTensorInternal(1, 1, input_size, num_units, in createFullyConnectedWeightTensor() 246 num_units, input_size, reinterpret_cast<const uint8_t*>(operandInfo.buffer)); in createFullyConnectedWeightTensor() 247 return createTensorInternal(1, 1, input_size, num_units, in createFullyConnectedWeightTensor()
|
/hardware/interfaces/neuralnetworks/1.0/ |
D | types.hal | 549 * [batch_size, input_size], where "input_size" corresponds to the 552 * elements by "input_size". 554 * [num_units, input_size], where "num_units" corresponds to the number 929 * A 2-D tensor of shape [batch_size, input_size], where “batch_size” 930 * corresponds to the batching dimension, and “input_size” is the size 933 * A 2-D tensor of shape [num_units, input_size], where “num_units” 936 * A 2-D tensor of shape [num_units, input_size]. 938 * A 2-D tensor of shape [num_units, input_size]. 940 * A 2-D tensor of shape [num_units, input_size]. 1260 * A 2-D tensor of shape [batch_size, input_size], where “batch_size” [all …]
|
/hardware/interfaces/neuralnetworks/1.2/ |
D | types.hal | 766 * [batch_size, input_size], where "input_size" corresponds to the 769 * elements by "input_size". 772 * [num_units, input_size], where "num_units" corresponds to the number 1214 * A 2-D tensor of shape [batch_size, input_size], where “batch_size” 1215 * corresponds to the batching dimension, and “input_size” is the size 1218 * A 2-D tensor of shape [num_units, input_size], where “num_units” 1221 * A 2-D tensor of shape [num_units, input_size]. 1223 * A 2-D tensor of shape [num_units, input_size]. 1225 * A 2-D tensor of shape [num_units, input_size]. 1628 * A 2-D tensor of shape [batch_size, input_size], where “batch_size” [all …]
|
/hardware/interfaces/neuralnetworks/1.3/ |
D | types.hal | 752 * [batch_size, input_size], where "input_size" corresponds to the 755 * elements by "input_size". 758 * [num_units, input_size], where "num_units" corresponds to the number 1211 * A 2-D tensor of shape [batch_size, input_size], where “batch_size” 1212 * corresponds to the batching dimension, and “input_size” is the size 1215 * A 2-D tensor of shape [num_units, input_size], where “num_units” 1218 * A 2-D tensor of shape [num_units, input_size]. 1220 * A 2-D tensor of shape [num_units, input_size]. 1222 * A 2-D tensor of shape [num_units, input_size]. 1664 * A 2-D tensor of shape [batch_size, input_size], where “batch_size” [all …]
|