| /packages/modules/NeuralNetworks/tools/api/ |
| D | types.spec | 111 * Supported tensor rank: 4, with "NHWC" (i.e., Num_samples, Height, Width,
213 * Supported tensor rank: 4, with "NHWC" or "NCHW" data layout.
220 * Since %{NNAPILevel3}, generic zero-sized input tensor is supported. Zero
226 * Since %{NNAPILevel3}, zero batches is supported for this tensor.
292 * A tensor of OEM specific values.
321 * Types prefaced with %{ANN}TENSOR_* must be used for tensor data (i.e., tensors
343 /** A tensor of 32 bit floating point values. */
346 /** A tensor of 32 bit integer values. */
350 * A tensor of 8 bit unsigned integers that represent real numbers.
352 * Attached to this tensor are two numbers that can be used to convert the
[all …]
|
| D | OperationTypes.t | 49 * Expands a representation of a sparse tensor to a dense tensor.
51 * To encode a conceptual n-dimensional dense tensor with dims [D0, ..., Dn-1], potentially with
57 * * 2: How each block dimension in [Dn, ..., Dn+k-1] maps to the original tensor dimension in
70 * Supported tensor {@link OperandType}:
84 * http://tensor-compiler.org/kjolstad-oopsla17-tensor-compiler.pdf
87 * * 0: A 1-D tensor representing the compressed sparse tensor data of a conceptual
88 * n-dimensional tensor.
89 * * 1: A 1-D {@link OperandType::TENSOR_INT32} tensor defining the traversal order for reading
90 * the non-zero blocks. For an n-dimensional tensor with dimensions [D0, D1, …, Dn-1]: if
96 * * 2: An optional 1-D {@link OperandType::TENSOR_INT32} tensor defining the block map. For a
[all …]
|
| D | NeuralNetworksTypes.t | 336 * should typically create one shared memory object that contains every constant tensor
350 * of the element type byte size, e.g., a tensor with
591 * A tensor operand type with all dimensions specified is "fully
593 * known at model construction time), a tensor operand type should be
597 * If a tensor operand's type is not fully specified, the dimensions
603 * <p>In the following situations, a tensor operand type must be fully
611 * model within a compilation. A fully specified tensor operand type
619 * not have a fully specified tensor operand type.</li>
624 * A fully specified tensor operand type must either be provided
630 * A tensor operand type of specified rank but some number of
[all …]
|
| D | OperandTypes.t | 51 * A tensor of OEM specific values.
|
| /packages/modules/NeuralNetworks/runtime/test/specs/V1_3/ |
| D | bidirectional_sequence_rnn_1_3.mod.py | 20 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)
|
| D | bidirectional_sequence_rnn_state_output.mod.py | 20 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)
|
| D | unidirectional_sequence_rnn.mod.py | 42 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
|
| /packages/modules/NeuralNetworks/runtime/test/specs/V1_2/ |
| D | bidirectional_sequence_rnn.mod.py | 20 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)
|
| D | unidirectional_sequence_rnn.mod.py | 39 def convert_to_time_major(tensor, num_batches, max_time, input_size): argument
40 return np.array(tensor).reshape([num_batches, max_time,
|
| /packages/modules/NeuralNetworks/runtime/operation_converters/ |
| D | SubGraphContext.cpp | 54 int SubGraphContext::addTensorFlatbuffer(TensorFlatbuffer tensor, int32_t operandIdx) { in addTensorFlatbuffer() argument
55 mTensorVector.push_back(tensor); in addTensorFlatbuffer()
205 TensorFlatbuffer tensor = tflite::CreateTensorDirect( in createTensorFlatbufferFromOperand() local
208 addTensorFlatbuffer(tensor, operandIdx); in createTensorFlatbufferFromOperand()
|
| D | SubGraphContext.h | 45 int addTensorFlatbuffer(TensorFlatbuffer tensor, int32_t operandIdx = -1);
|
| /packages/modules/NeuralNetworks/tools/test_generator/ |
| D | spec_visualizer.py | 148 for tensor in op.ins:
150 "source": str(tensor),
153 for tensor in op.outs:
155 "target": str(tensor),
|
| D | README.md | 199 … 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…
|
| /packages/modules/NeuralNetworks/common/cpu_operations/ |
| D | QuantizedLSTMTest.cpp | 226 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()
|
| D | QLSTM.cpp | 36 inline bool hasTensor(IOperationExecutionContext* context, const uint32_t tensor) { in hasTensor() argument
37 return context->getInputBuffer(tensor) != nullptr; in hasTensor()
58 for (const int tensor : requiredTensorInputs) { in prepare() local
59 NN_RET_CHECK(!context->isOmittedInput(tensor)) in prepare()
60 << "required input " << tensor << " is omitted"; in prepare()
|
| D | UnidirectionalSequenceLSTM.cpp | 40 inline bool hasTensor(IOperationExecutionContext* context, const uint32_t tensor) { in hasTensor() argument
41 return context->getInputBuffer(tensor) != nullptr; in hasTensor()
|
| /packages/modules/NeuralNetworks/extensions/ |
| D | README.md | 61 * A custom tensor type.
63 * Attached to this tensor is {@link ExampleTensorParams}.
76 * * 0: A tensor of {@link EXAMPLE_TENSOR}.
|
| /packages/modules/OnDevicePersonalization/src/com/android/ondevicepersonalization/services/inference/ |
| D | IsolatedModelServiceImpl.java | 155 Tensor tensor = interpreter.getInputTensor(i); in runTfliteInterpreter() local
156 int[] shape = tensor.shape(); in runTfliteInterpreter()
|
| /packages/inputmethods/LatinIME/dictionaries/ |
| D | en_GB_wordlist.combined.gz | 1dictionary=main:en_gb,locale=en_GB,description=English (UK),date ... |
| D | en_US_wordlist.combined.gz | 1dictionary=main:en_us,locale=en_US,description=English (US),date ... |
| D | en_wordlist.combined.gz | 1dictionary=main:en,locale=en,description=English,date=1414726273, ... |
| D | pl_wordlist.combined.gz | 1dictionary=main:pl,locale=pl,description=Polski,date=1414726264, ... |
| D | nl_wordlist.combined.gz | 1dictionary=main:nl,locale=nl,description=Nederlands,date=1414726258, ... |
| D | nb_wordlist.combined.gz | 1dictionary=main:nb,locale=nb,description=Norsk bokmål,date=1393228136 ... |
| D | pt_BR_wordlist.combined.gz | 1dictionary=main:pt_br,locale=pt_BR,description=Português (Brasil),date ... |