Search Options

Results per page
Sort
Preferred Languages
Advance

Results 11 - 11 of 11 for QAT (0.28 sec)

  1. tensorflow/compiler/mlir/quantization/common/quantization_lib/quantization_utils.cc

          effective_maxs.push_back(std::max(max, kSmallestHalfRange));
        }
      }
    }
    
    // Sets the min / max, scale and zero_points from the fake quant num_bits
    // attribute from QAT.
    QuantizedType ResetMinMaxFromNumBits(const QuantizedType type,
                                         const int num_bits,
                                         const bool narrow_range,
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Wed May 08 02:10:16 UTC 2024
    - 43.2K bytes
    - Viewed (0)
Back to top