Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 3 of 3 for SetInputNodesQuantizationParams (0.71 sec)

  1. tensorflow/compiler/mlir/quantization/tensorflow/passes/prepare_quantize.cc

      // non-float tensor types will be skipped because they are not quantizable.
      // Return true if number of input nodes doesn't equal to that of the input
      // ranges.
      bool SetInputNodesQuantizationParams(func::FuncOp func);
    
      // The function might contain more stats ops than required, and it will
      // introduce requantize if the calibration stats have conflicts. This method
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu Apr 25 16:01:03 UTC 2024
    - 17.2K bytes
    - Viewed (0)
  2. tensorflow/compiler/mlir/lite/transforms/prepare_quantize.cc

      // non-float tensor types will be skipped because they are not quantizable.
      // Return true if number of input nodes doesn't equal to that of the input
      // ranges.
      bool SetInputNodesQuantizationParams(func::FuncOp func);
    
      // The function might contain more stats ops than required, and it will
      // introduce requantize if the calibration stats have conflicts. This method
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Thu Apr 25 16:01:03 UTC 2024
    - 17.6K bytes
    - Viewed (0)
  3. tensorflow/compiler/mlir/lite/python/saved_model_to_tfl_flatbuffer.cc

      }
    
      if (toco_flags.has_qdq_conversion_mode() &&
          toco_flags.qdq_conversion_mode() != "NONE") {
        // Setting this flag causes
        // PrepareQuantize::SetInputNodesQuantizationParams() to be false and allows
        // PrepareQuantizePass to complete. For the most part this step is
        // unnecessary for non-TF QDQ models.
        pass_config.quant_specs.disable_set_input_nodes_quantization_params = true;
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Sun May 12 12:39:37 UTC 2024
    - 11K bytes
    - Viewed (0)
Back to top