Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 1 of 1 for CreatePreprocessOpPass (0.13 sec)

  2. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/tensorflow/passes/quantize_composite_functions.cc 

      pm.enableVerifier(false);

  QuantizationSpecs quant_specs;
  quant_specs.inference_type = tensorflow::DT_QINT8;
  quant_specs.disable_per_channel = !enable_per_channel_quantization_;

  pm.addPass(CreatePreprocessOpPass(target_opset_, quantization_method_,
                                    enable_per_channel_quantization_));

  // Apply activation-weight quantization.
  if (quantization_method_ ==
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu Apr 25 16:01:03 UTC 2024
    - 54.5K bytes
    - Viewed (0)
Back to top