Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 1 of 1 for AddQuantizationPasses (0.2 sec)

  2. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/lite/quantization/lite/quantize_model.cc 

      if (fully_quantize) {
    input_mlir_type = tflite::ConvertElementType(inference_type, mlir_builder);
    output_mlir_type = input_mlir_type;
  }

  tensorflow::AddQuantizationPasses(mlir::TFL::PassConfig(quant_specs), pm);
  pm.addPass(TFL::CreateModifyIONodesPass(input_mlir_type, output_mlir_type));
  // If the first or final ops are not quantized, remove QDQ.
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Wed Jun 12 23:15:24 UTC 2024
    - 6.3K bytes
    - Viewed (0)
Back to top