Home
last modified time | relevance | path

Searched refs:weights (Results 1 – 25 of 49) sorted by relevance

12

/packages/modules/NeuralNetworks/runtime/test/specs/V1_3/
Dfully_connected_quant8_signed.mod.py19 weights = Parameter("op2", "TENSOR_QUANT8_ASYMM_SIGNED", "{3, 10}, 0.5f, -1", variable
26 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act_relu).To(out0)
42 weights = Parameter("op2", "TENSOR_QUANT8_ASYMM_SIGNED", "{1, 5}, 0.2, -128", [-118, -108, -108, -1… variable
46 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0)
61 weights = Input("op2", "TENSOR_QUANT8_ASYMM_SIGNED", "{1, 5}, 0.2, -128") # num_units = 1, input_si… variable
65 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0)
70 weights:
84 weights = Parameter("op2", "TENSOR_QUANT8_ASYMM_SIGNED", "{1, 1}, 0.5f, -128", [-126]) variable
88 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0)
103 weights = Input("op2", "TENSOR_QUANT8_ASYMM_SIGNED", "{1, 1}, 0.5f, -128") variable
[all …]
Dunidirectional_sequence_rnn.mod.py19 def test(name, input, weights, recurrent_weights, bias, hidden_state, argument
25 model = Model().Operation("UNIDIRECTIONAL_SEQUENCE_RNN", input, weights,
31 weights: weights_data,
181 weights=Input("weights", "TENSOR_FLOAT32",
207 weights=Input("weights", "TENSOR_FLOAT32",
/packages/modules/NeuralNetworks/common/cpu_operations/
DQuantizedLSTM.cpp212 uint8_t* weights) { in assignWeightsSubmatrix() argument
218 weights[(row + offset_row) * weightsDims[1] + column + offset_column] = submatrixValues[i]; in assignWeightsSubmatrix()
270 auto checkWeightsShape = [&](const RunTimeOperandInfo* weights, uint32_t columns) -> bool { in prepare() argument
271 NN_RET_CHECK_EQ(NumDimensions(weights), 2u); in prepare()
272 NN_RET_CHECK_EQ(SizeOfDimension(weights, 0), outputSize); in prepare()
273 NN_RET_CHECK_EQ(SizeOfDimension(weights, 1), columns); in prepare()
274 NN_RET_CHECK_EQ(weights->scale, weightsScale); in prepare()
275 NN_RET_CHECK_EQ(weights->zeroPoint, weightsZeroPoint); in prepare()
354 uint8_t* weights) { in concatenateWeights() argument
357 assignWeightsSubmatrix(inputToInputWeights_, 0 * outputSize, outputSize, weightsDims, weights); in concatenateWeights()
[all …]
DUnidirectionalSequenceRNN.cpp56 const T* weights = context->getInputBuffer<T>(kWeightsTensor); in executeTyped() local
96 RNN::RNNStep<T>(input, fixedTimeInputShape, hiddenState, bias, weights, weightsShape, in executeTyped()
120 Shape weights = context->getInputShape(kWeightsTensor); in prepare() local
131 const uint32_t numUnits = getSizeOfDimension(weights, 0); in prepare()
135 NN_RET_CHECK_EQ(getNumberOfDimensions(weights), 2u); in prepare()
140 NN_RET_CHECK_EQ(inputSize, getSizeOfDimension(weights, 1)); in prepare()
/packages/modules/NeuralNetworks/common/types/operations/src/
DFullyConnected.cpp26 bool validateShapes(const Shape& input, const Shape& weights, const Shape& bias, Shape* output) { in validateShapes() argument
29 NN_RET_CHECK(weights.type == input.type); in validateShapes()
40 NN_RET_CHECK_EQ(getNumberOfDimensions(weights), 2u); in validateShapes()
43 uint32_t num_units = getSizeOfDimension(weights, 0u); in validateShapes()
44 uint32_t input_size = getSizeOfDimension(weights, 1u); in validateShapes()
124 Shape weights = context->getInputShape(kWeightsTensor); in validate() local
126 if (hasKnownRank(input) && hasKnownRank(weights) && hasKnownRank(bias)) { in validate()
127 NN_RET_CHECK(validateShapes(input, weights, bias)); in validate()
/packages/modules/NeuralNetworks/runtime/test/
DTestMemory.cpp61 WrapperMemory weights(offsetForMatrix3 + sizeof(matrix3), PROT_READ, fd, 0); in TEST_F() local
62 ASSERT_TRUE(weights.isValid()); in TEST_F()
75 model.setOperandValueFromMemory(e, &weights, offsetForMatrix2, sizeof(Matrix3x4)); in TEST_F()
76 model.setOperandValueFromMemory(a, &weights, offsetForMatrix3, sizeof(Matrix3x4)); in TEST_F()
124 WrapperMemory weights(buffer); in TEST_F() local
125 ASSERT_TRUE(weights.isValid()); in TEST_F()
138 model.setOperandValueFromMemory(e, &weights, offsetForMatrix2, sizeof(Matrix3x4)); in TEST_F()
139 model.setOperandValueFromMemory(a, &weights, offsetForMatrix3, sizeof(Matrix3x4)); in TEST_F()
/packages/modules/Wifi/framework/java/android/net/wifi/
DWifiNetworkSelectionConfig.java191 private static boolean isValidFrequencyWeightArray(SparseArray<Integer> weights) { in isValidFrequencyWeightArray() argument
192 if (weights == null) return false; in isValidFrequencyWeightArray()
194 for (int i = 0; i < weights.size(); i++) { in isValidFrequencyWeightArray()
195 int value = weights.valueAt(i); in isValidFrequencyWeightArray()
479 public @NonNull Builder setFrequencyWeights(@NonNull SparseArray<Integer> weights) in setFrequencyWeights() argument
481 if (!isValidFrequencyWeightArray(weights)) { in setFrequencyWeights()
482 if (weights == null) { in setFrequencyWeights()
486 + weights.toString()); in setFrequencyWeights()
488 mWifiNetworkSelectionConfig.mFrequencyWeights = weights; in setFrequencyWeights()
/packages/modules/NeuralNetworks/runtime/test/specs/V1_2/
Dunidirectional_sequence_rnn.mod.py19 def test(name, input, weights, recurrent_weights, bias, hidden_state, argument
24 model = Model().Operation("UNIDIRECTIONAL_SEQUENCE_RNN", input, weights,
29 weights: weights_data,
143 weights=Input("weights", "TENSOR_FLOAT32", "{{{}, {}}}".format(
165 weights=Input("weights", "TENSOR_FLOAT32", "{{{}, {}}}".format(
Drnn_float16.mod.py24 weights = Input("weights", "TENSOR_FLOAT16", "{%d, %d}" % (units, input_size)) variable
34 model = model.Operation("RNN", input, weights, recurrent_weights, bias, hidden_state_in,
38 weights: [
Dfully_connected_v1_2.mod.py20 weights = Parameter("op2", "TENSOR_FLOAT32", "{1, 1}", [2]) variable
24 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0)
28 weights: ("TENSOR_QUANT8_ASYMM", 0.5, 120),
/packages/modules/NeuralNetworks/runtime/test/specs/V1_0/
Dfully_connected_float_weights_as_inputs.mod.py19 weights = Input("op2", "TENSOR_FLOAT32", "{1, 1}") variable
23 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0)
28 weights: [2],
Dfully_connected_quant8_weights_as_inputs.mod.py19 weights = Input("op2", "TENSOR_QUANT8_ASYMM", "{1, 1}, 0.5f, 0") variable
23 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0)
28 weights: [2],
Dfully_connected_float_large_weights_as_inputs.mod.py19 weights = Input("op2", "TENSOR_FLOAT32", "{1, 5}") # num_units = 1, input_size = 5 variable
23 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0)
28 weights:
Dfully_connected_quant8_large_weights_as_inputs.mod.py19 weights = Input("op2", "TENSOR_QUANT8_ASYMM", "{1, 5}, 0.2, 0") # num_units = 1, input_size = 5 variable
23 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0)
28 weights:
Drnn_state.mod.py24 weights = Input("weights", "TENSOR_FLOAT32", "{%d, %d}" % (units, input_size)) variable
34 model = model.Operation("RNN", input, weights, recurrent_weights, bias, hidden_state_in,
38 weights: [
Drnn.mod.py24 weights = Input("weights", "TENSOR_FLOAT32", "{%d, %d}" % (units, input_size)) variable
34 model = model.Operation("RNN", input, weights, recurrent_weights, bias, hidden_state_in,
38 weights: [
Dfully_connected_float_large.mod.py19 weights = Parameter("op2", "TENSOR_FLOAT32", "{1, 5}", [2, 3, 4, 5, 6]) # num_units = 1, input_size… variable
23 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0)
Dfully_connected_quant8.mod.py19 weights = Parameter("op2", "TENSOR_QUANT8_ASYMM", "{1, 1}, 0.5f, 0", [2]) variable
23 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0)
Dfully_connected_quant8_large.mod.py19 weights = Parameter("op2", "TENSOR_QUANT8_ASYMM", "{1, 5}, 0.2, 0", [10, 20, 20, 20, 10]) # num_uni… variable
23 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0)
Dfully_connected_float_2.mod.py19 weights = Parameter("op2", "TENSOR_FLOAT32", "{16, 8}", variable
48 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act_relu).To(out0)
/packages/modules/NeuralNetworks/runtime/test/specs/V1_1/
Dfully_connected_float_large_weights_as_inputs_relaxed.mod.py19 weights = Input("op2", "TENSOR_FLOAT32", "{1, 5}") # num_units = 1, input_size = 5 variable
23 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0)
29 weights:
Dfully_connected_float_weights_as_inputs_relaxed.mod.py19 weights = Input("op2", "TENSOR_FLOAT32", "{1, 1}") variable
23 model = model.Operation("FULLY_CONNECTED", in0, weights, bias, act).To(out0)
29 weights: [2],
Drnn_state_relaxed.mod.py24 weights = Input("weights", "TENSOR_FLOAT32", "{%d, %d}" % (units, input_size)) variable
34 model = model.Operation("RNN", input, weights, recurrent_weights, bias, hidden_state_in,
39 weights: [
Drnn_relaxed.mod.py24 weights = Input("weights", "TENSOR_FLOAT32", "{%d, %d}" % (units, input_size)) variable
34 model = model.Operation("RNN", input, weights, recurrent_weights, bias, hidden_state_in,
39 weights: [
/packages/modules/Wifi/framework/tests/src/android/net/wifi/
DWifiNetworkSelectionConfigTest.java55 SparseArray<Integer> weights = new SparseArray<>(); in testWifiNetworkSelectionConfigParcel() local
56 weights.put(2450, WifiNetworkSelectionConfig.FREQUENCY_WEIGHT_HIGH); in testWifiNetworkSelectionConfigParcel()
57 weights.put(5450, WifiNetworkSelectionConfig.FREQUENCY_WEIGHT_LOW); in testWifiNetworkSelectionConfigParcel()
68 .setFrequencyWeights(weights) in testWifiNetworkSelectionConfigParcel()
91 assertTrue(weights.contentEquals(parcelConfig.getFrequencyWeights())); in testWifiNetworkSelectionConfigParcel()

12