Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 4 of 4 for set_quantization_component (0.69 sec)

  2. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/stablehlo/tests/fill_quantization_options_test.cc 

          bias_component;
  weight_component.set_quantization_component(
      QuantizationComponentSpec::COMPONENT_WEIGHT);
  weight_component.set_bit_width(QuantizationComponentSpec::BIT_WIDTH_16);
  weight_component.set_bit_type(QuantizationComponentSpec::BIT_TYPE_FLOAT);
  bias_component.set_quantization_component(
      QuantizationComponentSpec::COMPONENT_BIAS);
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue Mar 05 09:05:02 UTC 2024
    - 4.3K bytes
    - Viewed (0)
  3. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/tensorflow/ops/tf_op_quant_spec_test.cc 

        tensorflow::quantization::QuantizationComponentSpec;

TEST(TfOpQuantSpecTest, WeightComponentSpecExist) {
  QuantizationOptions quant_options;
  QuantizationComponentSpec quant_spec;
  quant_spec.set_quantization_component(
      QuantizationComponentSpec::COMPONENT_WEIGHT);
  quant_spec.set_tensor_type(QuantizationComponentSpec::TENSORTYPE_INT_8);
  auto mutable_quant_method = quant_options.mutable_quantization_method();
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue Aug 22 18:28:40 UTC 2023
    - 1.8K bytes
    - Viewed (0)
  4. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/stablehlo/utils/fill_quantization_options.cc 

                                      const QuantizationComponent& component,
                                  const BitType bit_type,
                                  const BitWidth bit_width) {
  spec->set_quantization_component(component);
  spec->set_bit_type(bit_type);
  spec->set_bit_width(bit_width);
}

::stablehlo::quantization::QuantizationOptions FillPresetQuantizationOptions(
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue Mar 05 08:32:43 UTC 2024
    - 6.2K bytes
    - Viewed (0)
  5. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/tensorflow/ops/tf_quantize_op_test.cc 

      Value value = CreateConstValue<float>(builder, module->getLoc(), {1024, 2},
                                        SmallVector<float>(2048, 0));

  QuantizationComponentSpec quant_spec;
  quant_spec.set_quantization_component(
      QuantizationComponentSpec::COMPONENT_WEIGHT);
  quant_spec.set_tensor_type(QuantizationComponentSpec::TENSORTYPE_INT_8);

  std::optional<TF::PartitionedCallOp> dequantize_op = ApplyUniformQuantization(
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Sun Dec 10 05:52:02 UTC 2023
    - 3K bytes
    - Viewed (0)
Back to top