Home
last modified time | relevance | path

Searched refs:tensor (Results 1 – 25 of 34) sorted by relevance

12

/aosp12/hardware/interfaces/neuralnetworks/1.1/
H A Dtypes.hal47 * * 0: An n-D tensor, specifying the tensor to be reshaped
82 * Supported tensor rank: up to 4
109 * Supported tensor rank: up to 4
135 * Pads a tensor.
144 * Supported tensor rank: up to 4
147 * * 0: An n-D tensor, specifying the tensor to be padded.
212 * Given a tensor input, this operation returns a tensor of the same
224 * * 0: An n-D tensor, the tensor to be squeezed.
258 * * 0: An n-D tensor, specifying the tensor to be sliced.
330 * perm tensor.
[all …]
/aosp12/packages/modules/NeuralNetworks/tools/api/
H A Dtypes.spec364 * * 0: A tensor.
1090 * in the input tensor with each element in the output tensor.
1238 * * 0: An n-D tensor, specifying the tensor to be normalized.
1240 * * 0: A 4-D tensor, specifying the tensor to be normalized.
2045 * * 0: A tensor, specifying the tensor to be reshaped.
2502 * * 0: An n-D tensor, specifying the tensor to be reshaped
2656 * * 0: An n-D tensor, specifying the tensor to be padded.
2950 * * 0: An n-D tensor, specifying the tensor to be transposed.
3838 * * 0: An n-D tensor, specifying the tensor to be shuffled.
4806 * * 0: An n-D tensor, specifying the tensor to be padded.
[all …]
H A DNeuralNetworksTypes.t333 * of the element type byte size, e.g., a tensor with
574 * A tensor operand type with all dimensions specified is "fully
576 * known at model construction time), a tensor operand type should be
580 * If a tensor operand's type is not fully specified, the dimensions
586 * <p>In the following situations, a tensor operand type must be fully
594 * model within a compilation. A fully specified tensor operand type
602 * not have a fully specified tensor operand type.</li>
607 * A fully specified tensor operand type must either be provided
613 * A tensor operand type of specified rank but some number of
619 * Starting at NNAPI feature level 3, a tensor operand type of unspecified rank is
[all …]
H A DOperandTypes.t51 * A tensor of OEM specific values.
/aosp12/hardware/interfaces/neuralnetworks/1.2/
H A Dtypes.hal189 * * 0: A tensor.
751 * in the input tensor with each element in the output tensor.
870 * * 0: An n-D tensor, specifying the tensor to be normalized.
1531 * * 0: A tensor, specifying the tensor to be reshaped.
1869 * * 0: An n-D tensor, specifying the tensor to be reshaped
1979 * * 0: An n-D tensor, specifying the tensor to be padded.
2072 * * 0: An n-D tensor, the tensor to be squeezed.
2107 * * 0: An n-D tensor, specifying the tensor to be sliced.
2794 * * 0: An n-D tensor, specifying the tensor to be shuffled.
3613 * * 0: An n-D tensor, specifying the tensor to be padded.
[all …]
H A DIPreparedModel.hal57 * If the prepared model was prepared from a model wherein all tensor
109 * If the prepared model was prepared from a model wherein all tensor
152 * If the prepared model was prepared from a model wherein all tensor
H A DIDevice.hal133 * and transformed tensor buffers. Any modification to the data cache should
/aosp12/hardware/interfaces/neuralnetworks/1.3/
H A Dtypes.hal128 * * 0: A tensor.
738 * in the input tensor with each element in the output tensor.
860 * * 0: An n-D tensor, specifying the tensor to be normalized.
1544 * * 0: A tensor, specifying the tensor to be reshaped.
1917 * * 0: An n-D tensor, specifying the tensor to be reshaped
2039 * * 0: An n-D tensor, specifying the tensor to be padded.
2136 * * 0: An n-D tensor, the tensor to be squeezed.
2173 * * 0: An n-D tensor, specifying the tensor to be sliced.
2969 * * 0: An n-D tensor, specifying the tensor to be shuffled.
3829 * * 0: An n-D tensor, specifying the tensor to be padded.
[all …]
H A DIPreparedModel.hal62 * If the prepared model was prepared from a model wherein all tensor
148 * If the prepared model was prepared from a model wherein all tensor
/aosp12/hardware/interfaces/neuralnetworks/1.0/
H A Dtypes.hal108 * * 0: A tensor.
468 * * 0: A tensor.
524 * * 0: A tensor.
534 * in the input tensor with each element in the output tensor.
589 * in the Output tensor. For a miss, the corresponding sub-tensor in
647 * * 0: A 4-D tensor, specifying the tensor to be normalized.
1097 * * 0: A tensor.
1182 * Reshapes a tensor.
1184 * Given tensor, this operation returns a tensor that has the same values as
1194 * * 0: A tensor, specifying the tensor to be reshaped.
[all …]
H A Dtypes.t37 * A tensor of OEM specific values.
H A DIPreparedModel.hal52 * If the prepared model was prepared from a model wherein all tensor
/aosp12/packages/modules/NeuralNetworks/runtime/test/specs/V1_3/
H A Dbidirectional_sequence_rnn_1_3.mod.py20 def convert_to_time_major(tensor, tensor_shape): argument
21 return np.array(tensor).reshape(tensor_shape).transpose(
30 def reverse_batch_major(tensor, tensor_shape): argument
31 return np.array(tensor).reshape(tensor_shape)[:, ::-1, :].flatten().tolist()
33 def split_tensor_in_two(tensor, tensor_shape): argument
34 tensor = np.array(tensor).reshape(tensor_shape)
35 left, right = np.split(tensor, 2, axis=len(tensor_shape) - 1)
H A Dbidirectional_sequence_rnn_state_output.mod.py20 def convert_to_time_major(tensor, tensor_shape): argument
21 return np.array(tensor).reshape(tensor_shape).transpose([1, 0, 2
31 def reverse_batch_major(tensor, tensor_shape): argument
32 return np.array(tensor).reshape(tensor_shape)[:, ::-1, :].flatten().tolist()
35 def split_tensor_in_two(tensor, tensor_shape): argument
36 tensor = np.array(tensor).reshape(tensor_shape)
37 left, right = np.split(tensor, 2, axis=len(tensor_shape) - 1)
H A Dunidirectional_sequence_rnn.mod.py42 def convert_to_time_major(tensor, num_batches, max_time, input_size): argument
43 return np.array(tensor).reshape([num_batches, max_time, input_size
/aosp12/packages/modules/NeuralNetworks/runtime/test/specs/V1_2/
H A Dbidirectional_sequence_rnn.mod.py20 def convert_to_time_major(tensor, tensor_shape): argument
21 return np.array(tensor).reshape(tensor_shape).transpose(
30 def reverse_batch_major(tensor, tensor_shape): argument
31 return np.array(tensor).reshape(tensor_shape)[:, ::-1, :].flatten().tolist()
33 def split_tensor_in_two(tensor, tensor_shape): argument
34 tensor = np.array(tensor).reshape(tensor_shape)
35 left, right = np.split(tensor, 2, axis=len(tensor_shape) - 1)
H A Dunidirectional_sequence_rnn.mod.py39 def convert_to_time_major(tensor, num_batches, max_time, input_size): argument
40 return np.array(tensor).reshape([num_batches, max_time,
/aosp12/packages/modules/NeuralNetworks/tools/test_generator/
H A Dspec_visualizer.py148 for tensor in op.ins:
150 "source": str(tensor),
153 for tensor in op.outs:
155 "target": str(tensor),
H A DREADME.md199 … as an internal operand. Will skip if the model does not have any output tensor that is compatible…
231 …model to model inputs. Will skip if the model does not have any constant tensor, or if the model h…
233 …t as an internal operand. Will skip if the model does not have any input tensor that is compatible…
/aosp12/packages/modules/NeuralNetworks/common/operations/
H A DQuantizedLSTMTest.cpp226 Result setInputTensor(Execution* execution, int tensor, const std::vector<T>& data) { in setInputTensor() argument
227 return execution->setInput(tensor, data.data(), sizeof(T) * data.size()); in setInputTensor()
230 Result setOutputTensor(Execution* execution, int tensor, std::vector<T>* data) { in setOutputTensor() argument
231 return execution->setOutput(tensor, data->data(), sizeof(T) * data->size()); in setOutputTensor()
H A DQLSTM.cpp101 inline bool hasTensor(IOperationExecutionContext* context, const uint32_t tensor) { in hasTensor() argument
102 return context->getInputBuffer(tensor) != nullptr; in hasTensor()
174 for (const int tensor : requiredTensorInputs) { in prepare() local
175 NN_RET_CHECK(!context->isOmittedInput(tensor)) in prepare()
176 << "required input " << tensor << " is omitted"; in prepare()
H A DUnidirectionalSequenceLSTM.cpp94 inline bool hasTensor(IOperationExecutionContext* context, const uint32_t tensor) { in hasTensor() argument
95 return context->getInputBuffer(tensor) != nullptr; in hasTensor()
/aosp12/packages/modules/NeuralNetworks/extensions/
H A DREADME.md61 * A custom tensor type.
63 * Attached to this tensor is {@link ExampleTensorParams}.
76 * * 0: A tensor of {@link EXAMPLE_TENSOR}.
/aosp12/packages/inputmethods/LatinIME/dictionaries/
H A Den_US_wordlist.combined.gz1dictionary=main:en_us,locale=en_US,description=English (US),date ...
H A Den_GB_wordlist.combined.gz1dictionary=main:en_gb,locale=en_GB,description=English (UK),date ...

12