Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 1 of 1 for enable_legacy_weight_only (0.15 sec)

  2. github.com/tensorflow/tensorflow

    tensorflow/compiler/mlir/quantization/tensorflow/quantization_options.proto 

      // Produces legacy weight-only graph where the qconst op(containing quantized
  // values) is followed by a dequantization op. This flag will be deprecated.
  bool enable_legacy_weight_only = 13;

  // If set to true, it forces calibration in graph model instead of eager mode
  // when the context is in eager mode. This will be forcibly set to true when
  // using DebuggerOptions.
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Tue Mar 19 06:31:19 UTC 2024
    - 9.2K bytes
    - Viewed (0)
Back to top