| /external/tensorflow/tensorflow/lite/kernels/internal/ |
| D | kernel_utils.cc | 26 int input_size, int num_units, int batch_size, in RnnBatchStep() argument
33 bias_ptr, input_size, /*aux_input_size=*/0, num_units, in RnnBatchStep()
42 int input_size, int aux_input_size, int num_units, in RnnBatchStep() argument
48 if (output_batch_leading_dim == num_units) { in RnnBatchStep()
50 tensor_utils::VectorBatchVectorAssign(bias_ptr, num_units, batch_size, in RnnBatchStep()
55 input_weights_ptr, num_units, input_size, input_ptr_batch, batch_size, in RnnBatchStep()
61 aux_input_weights_ptr, num_units, aux_input_size, aux_input_ptr_batch, in RnnBatchStep()
67 recurrent_weights_ptr, num_units, num_units, hidden_state_ptr_batch, in RnnBatchStep()
72 output_ptr_batch, num_units * batch_size, activation, output_ptr_batch); in RnnBatchStep()
73 std::copy_n(output_ptr_batch, num_units * batch_size, in RnnBatchStep()
[all …]
|
| D | kernel_utils.h | 41 int input_size, int num_units, int batch_size,
51 int input_size, int aux_input_size, int num_units,
70 int num_units, int batch_size, int output_batch_leading_dim,
82 const float* bias_ptr, int input_size, int aux_input_size, int num_units,
|
| /external/tensorflow/tensorflow/core/ops/ |
| D | cudnn_rnn_ops_test.cc | 44 int num_units = 4; in TEST() local
47 std::vector<int> input_shape = {seq_length, batch_size, num_units}; in TEST()
49 num_units}; in TEST()
51 num_units * dir_count}; in TEST()
81 int num_units = 4; in TEST() local
84 std::vector<int> input_shape = {seq_length, batch_size, num_units}; in TEST()
86 num_units}; in TEST()
88 num_units * dir_count}; in TEST()
118 int num_units = 4; in TEST() local
121 std::vector<int> input_shape = {max_seq_length, batch_size, num_units}; in TEST()
[all …]
|
| D | cudnn_rnn_ops.cc | 93 auto num_units = c->Dim(input_h_shape, 2); in __anon20e2ac3d0302() local
101 TF_RETURN_IF_ERROR(c->Multiply(num_units, dir_count, &output_size)); in __anon20e2ac3d0302()
142 auto num_units = c->Dim(input_h_shape, 2); in __anon20e2ac3d0402() local
149 TF_RETURN_IF_ERROR(c->Multiply(num_units, dir_count, &output_size)); in __anon20e2ac3d0402()
196 auto num_units = c->Dim(input_h_shape, 2); in __anon20e2ac3d0502() local
207 TF_RETURN_IF_ERROR(c->Multiply(num_units, dir_count, &output_size)); in __anon20e2ac3d0502()
|
| /external/tensorflow/tensorflow/lite/kernels/ |
| D | unidirectional_sequence_rnn.cc | 87 const int num_units = input_weights->dims->data[0]; in Prepare() local
100 TF_LITE_ENSURE_EQ(context, hidden_state->dims->data[1], num_units); in Prepare()
110 output_size_array->data[2] = num_units; in Prepare()
167 int accum_scratch_dims[2] = {num_units, batch_size}; in Prepare()
195 int row_sums_dims[2] = {2, num_units}; in Prepare()
221 const int num_units = input_weights->dims->data[0]; in EvalFloat() local
237 GetTensorData<float>(output) + s * num_units * batch_size; in EvalFloat()
241 input_size, num_units, batch_size, num_units, params->activation, in EvalFloat()
249 GetTensorData<float>(hidden_state) + b * num_units; in EvalFloat()
256 b * num_units * max_time + s * num_units; in EvalFloat()
[all …]
|
| D | unidirectional_sequence_rnn_test.cc | 230 int num_units() { return units_; } in num_units() function in tflite::__anona0a7fc2c0111::UnidirectionalRNNOpModel
295 float* golden_end = golden_start + rnn.num_units() * rnn.sequence_len(); in TEST()
324 float* golden_end = golden_start + rnn.num_units() * rnn.sequence_len(); in TEST_P()
351 float* golden_end = golden_start + rnn.num_units() * rnn.sequence_len(); in TEST_P()
380 float* golden_batch_start = rnn_golden_output + i * rnn.num_units(); in TEST()
381 float* golden_batch_end = golden_batch_start + rnn.num_units(); in TEST()
410 float* golden_batch_start = rnn_golden_output + i * rnn.num_units(); in TEST_P()
411 float* golden_batch_end = golden_batch_start + rnn.num_units(); in TEST_P()
441 float* golden_batch_start = rnn_golden_output + i * rnn.num_units(); in TEST_P()
442 float* golden_batch_end = golden_batch_start + rnn.num_units(); in TEST_P()
|
| D | basic_rnn_test.cc | 216 int num_units() { return units_; } in num_units() function in tflite::__anon2c82b85c0111::RNNOpModel
276 float* golden_start = rnn_golden_output + i * rnn.num_units(); in TEST()
277 float* golden_end = golden_start + rnn.num_units(); in TEST()
305 float* golden_start = rnn_golden_output + i * rnn.num_units(); in TEST_P()
306 float* golden_end = golden_start + rnn.num_units(); in TEST_P()
333 float* golden_start = rnn_golden_output + i * rnn.num_units(); in TEST_P()
334 float* golden_end = golden_start + rnn.num_units(); in TEST_P()
|
| D | basic_rnn.cc | 81 const int num_units = input_weights->dims->data[0]; in Prepare() local
94 TF_LITE_ENSURE_EQ(context, hidden_state->dims->data[1], num_units); in Prepare()
103 output_size_array->data[1] = num_units; in Prepare()
160 int accum_scratch_dims[2] = {num_units, batch_size}; in Prepare()
189 int row_sums_dims[2] = {2, num_units}; in Prepare()
207 const int num_units = input_weights->dims->data[0]; in EvalFloat() local
224 input_size, num_units, batch_size, output_batch_leading_dim, in EvalFloat()
240 const int num_units = input_weights->dims->data[0]; in EvalHybrid() local
273 num_units, batch_size, output_batch_leading_dim, params->activation, in EvalHybrid()
|
| /external/tensorflow/tensorflow/python/kernel_tests/nn_ops/ |
| D | rnn_test.py | 361 num_units=input_size,
383 num_units=input_size,
404 num_units = 512
410 np.random.randn(batch_size, num_units).astype(np.float32)
450 def static_vs_dynamic_rnn_benchmark(batch_size, max_time, num_units, use_gpu): argument
458 np.random.randn(batch_size, num_units).astype(np.float32)
484 (batch_size, max_time, num_units, use_gpu, delta_static, delta_dynamic,
494 num_units=input_size,
512 def half_seq_len_vs_unroll_half_rnn_benchmark(batch_size, max_time, num_units, argument
521 np.random.randn(batch_size, num_units).astype(np.float32)
[all …]
|
| D | rnn_cell_test.py | 383 num_units = 3
391 num_units, initializer=initializer, state_is_tuple=False)
398 self.assertEqual(out.get_shape().as_list(), [batch_size, num_units])
406 num_units = 3
414 num_units,
425 self.assertEqual(out.get_shape().as_list(), [batch_size, num_units])
433 self.assertAllEqual(value, np.zeros((batch_size, num_units)))
437 num_units = 3
444 state_saver = TestStateSaver(batch_size, 2 * num_units)
446 num_units,
[all …]
|
| /external/mesa3d/src/gallium/drivers/lima/ir/gp/ |
| D | disasm.c | 37 num_units enumerator
40 static const gpir_codegen_store_src gp_unit_to_store_src[num_units] = {
170 printf("^%d", cur_dest_index - 1 * num_units + unit_acc_0); in print_src()
174 printf("^%d", cur_dest_index - 1 * num_units + unit_acc_1); in print_src()
178 printf("^%d", cur_dest_index - 1 * num_units + unit_mul_0); in print_src()
182 printf("^%d", cur_dest_index - 1 * num_units + unit_mul_1); in print_src()
186 printf("^%d", cur_dest_index - 1 * num_units + unit_pass); in print_src()
212 printf("^%d", cur_dest_index - 1 * num_units + unit_complex); in print_src()
216 printf("^%d", cur_dest_index - 2 * num_units + unit_pass); in print_src()
220 printf("^%d", cur_dest_index - 2 * num_units + unit_acc_0); in print_src()
[all …]
|
| /external/ComputeLibrary/src/runtime/NEON/functions/ |
| D | NEQLSTMLayer.cpp | 272 const int num_units = input_to_output_weights->info()->dimension(1); in configure() local
326 …s->info(), _input_to_input_eff_bias.info(), GEMMLowpReductionKernelInfo(num_units, false, -qinput.… in configure()
327 …nfo(), _recurrent_to_input_eff_bias.info(), GEMMLowpReductionKernelInfo(num_units, false, -qoutput… in configure()
337 …->info(), _input_to_forget_eff_bias.info(), GEMMLowpReductionKernelInfo(num_units, false, -qinput.… in configure()
338 …fo(), _recurrent_to_forget_eff_bias.info(), GEMMLowpReductionKernelInfo(num_units, false, -qoutput… in configure()
339 …ts->info(), _input_to_cell_eff_bias.info(), GEMMLowpReductionKernelInfo(num_units, false, -qinput.… in configure()
340 …info(), _recurrent_to_cell_eff_bias.info(), GEMMLowpReductionKernelInfo(num_units, false, -qoutput… in configure()
341 …->info(), _input_to_output_eff_bias.info(), GEMMLowpReductionKernelInfo(num_units, false, -qinput.… in configure()
342 …fo(), _recurrent_to_output_eff_bias.info(), GEMMLowpReductionKernelInfo(num_units, false, -qoutput… in configure()
376 const TensorInfo mm_out_info(TensorShape(num_units, batch_size), 1, DataType::S32); in configure()
[all …]
|
| /external/ComputeLibrary/src/runtime/CL/functions/ |
| D | CLQLSTMLayer.cpp | 201 const int num_units = input_to_output_weights->info()->dimension(1); in configure() local
253 …s->info(), _input_to_input_eff_bias.info(), GEMMLowpReductionKernelInfo(num_units, false, -qinput.… in configure()
254 …weights->info(), _recurrent_to_input_eff_bias.info(), GEMMLowpReductionKernelInfo(num_units, false, in configure()
257 …->info(), _input_to_forget_eff_bias.info(), GEMMLowpReductionKernelInfo(num_units, false, -qinput.… in configure()
258 …eights->info(), _recurrent_to_forget_eff_bias.info(), GEMMLowpReductionKernelInfo(num_units, false, in configure()
260 …ts->info(), _input_to_cell_eff_bias.info(), GEMMLowpReductionKernelInfo(num_units, false, -qinput.… in configure()
261 …info(), _recurrent_to_cell_eff_bias.info(), GEMMLowpReductionKernelInfo(num_units, false, -qoutput… in configure()
263 …->info(), _input_to_output_eff_bias.info(), GEMMLowpReductionKernelInfo(num_units, false, -qinput.… in configure()
264 …eights->info(), _recurrent_to_output_eff_bias.info(), GEMMLowpReductionKernelInfo(num_units, false, in configure()
298 const TensorInfo mm_out_info(TensorShape(num_units, batch_size), 1, DataType::S32); in configure()
[all …]
|
| /external/tensorflow/tensorflow/core/api_def/base_api/ |
| D | api_def_CudnnRNNV3.pbtxt | 12 when input_size == num_units; 'auto_select' implies 'skip_input' when
13 input_size == num_units; otherwise, it implies 'linear_input'.
23 [num_layer * dir, batch_size, num_units]. If time_major is false, the shape
24 is [batch_size, num_layer * dir, num_units].
26 [num_layer * dir, batch, num_units]. For other models, it is ignored.
33 [seq_length, batch_size, dir * num_units]. If time_major is false, the
34 shape is [batch_size, seq_length, dir * num_units].
|
| D | api_def_CudnnRNNBackpropV3.pbtxt | 12 when input_size == num_units; 'auto_select' implies 'skip_input' when
13 input_size == num_units; otherwise, it implies 'linear_input'.
23 [num_layer * dir, batch_size, num_units]. If time_major is false, the shape
24 is [batch_size, num_layer * dir, num_units].
26 [num_layer * dir, batch, num_units]. For other models, it is ignored.
33 [seq_length, batch_size, dir * num_units]. If time_major is false, the
34 shape is [batch_size, seq_length, dir * num_units].
|
| D | api_def_CudnnRNN.pbtxt | 11 when input_size == num_units; 'auto_select' implies 'skip_input' when
12 input_size == num_units; otherwise, it implies 'linear_input'.
20 num_units].
22 [num_layer * dir, batch, num_units]. For other models, it is ignored.
28 dir * num_units].
|
| D | api_def_CudnnRNNV2.pbtxt | 12 when input_size == num_units; 'auto_select' implies 'skip_input' when
13 input_size == num_units; otherwise, it implies 'linear_input'.
21 num_units].
23 [num_layer * dir, batch, num_units]. For other models, it is ignored.
29 dir * num_units].
|
| D | api_def_CudnnRNNBackprop.pbtxt | 10 when input_size == num_units; 'auto_select' implies 'skip_input' when
11 input_size == num_units; otherwise, it implies 'linear_input'.
19 num_units].
21 [num_layer * dir, batch, num_units]. For other models, it is ignored.
27 dir * num_units].
|
| D | api_def_CudnnRNNBackpropV2.pbtxt | 13 when input_size == num_units; 'auto_select' implies 'skip_input' when
14 input_size == num_units; otherwise, it implies 'linear_input'.
22 num_units].
24 [num_layer * dir, batch, num_units]. For other models, it is ignored.
30 dir * num_units].
|
| D | api_def_CudnnRNNParamsSize.pbtxt | 9 num_units: Specifies the size of the hidden state.
14 when input_size == num_units; 'auto_select' implies 'skip_input' when
15 input_size == num_units; otherwise, it implies 'linear_input'.
|
| D | api_def_CudnnRNNCanonicalToParams.pbtxt | 13 num_units: Specifies the size of the hidden state.
27 when input_size == num_units; 'auto_select' implies 'skip_input' when
28 input_size == num_units; otherwise, it implies 'linear_input'.
|
| /external/tensorflow/tensorflow/lite/kernels/internal/reference/ |
| D | svdf.h | 38 int batch_size, int memory_size, int num_filters, int num_units, int rank, in ApplyTimeWeightsBiasAndActivation() argument
54 batch_size * num_units, rank); in ApplyTimeWeightsBiasAndActivation()
57 tensor_utils::VectorBatchVectorAdd(bias_ptr, num_units, batch_size, in ApplyTimeWeightsBiasAndActivation()
62 tensor_utils::ApplyActivationToVector(output_ptr, batch_size * num_units, in ApplyTimeWeightsBiasAndActivation()
163 const int num_units = num_filters / rank; in EvalFloatSVDF() local
187 batch_size, memory_size, num_filters, num_units, rank, weights_time_data, in EvalFloatSVDF()
204 const int num_units = num_filters / rank; in EvalHybridSVDF() local
242 batch_size, memory_size, num_filters, num_units, rank, weights_time_data, in EvalHybridSVDF()
|
| /external/marisa-trie/lib/marisa/grimoire/vector/ |
| D | flat-vector.h | 105 std::size_t num_units = values.empty() ? 0 : (64 / MARISA_WORD_SIZE); in build_() local
107 num_units = (std::size_t)( in build_()
110 num_units += num_units % (64 / MARISA_WORD_SIZE); in build_()
113 units_.resize(num_units); in build_()
114 if (num_units > 0) { in build_()
|
| /external/tensorflow/tensorflow/core/kernels/ |
| D | cudnn_rnn_ops.cc | 153 CudnnRnnParameters(int num_layers, int input_size, int num_units, in CudnnRnnParameters() argument
159 num_units_(num_units), in CudnnRnnParameters()
169 HashList({num_layers, input_size, num_units, max_seq_length, batch_size, in CudnnRnnParameters()
274 Status ToRNNInputMode(TFRNNInputMode tf_input_mode, int num_units, in ToRNNInputMode() argument
284 *input_mode = (input_size == num_units) ? RnnInputMode::kRnnSkipInput in ToRNNInputMode()
501 int num_units; member
516 num_units == rhs.num_units && dir_count == rhs.dir_count && in IsCompatibleWith()
524 num_layers, input_size, num_units, dir_count, max_seq_length, in DebugString()
539 HashList({shapes.num_layers, shapes.input_size, shapes.num_units, in operator ()()
608 model_shapes->num_units = (*input_h)->dim_size(2); in ExtractForwardInput()
[all …]
|
| /external/tensorflow/tensorflow/python/keras/layers/legacy_rnn/ |
| D | rnn_cell_impl.py | 421 num_units, argument
443 self._num_units = num_units
528 num_units, argument
552 self._num_units = num_units
680 num_units, argument
731 self._num_units = num_units
859 num_units, argument
938 self._num_units = num_units
955 LSTMStateTuple(num_units, num_proj) if state_is_tuple else num_units +
960 LSTMStateTuple(num_units, num_units) if state_is_tuple else 2 *
[all …]
|