Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 2 of 2 for getPerChunkConverter (0.16 sec)

  1. tensorflow/compiler/mlir/quantization/common/ir/UniformSupport.cc

        return {};
      }
      SmallVector<UniformQuantizedValueConverter, 4> converters;
      converters.reserve(dim_size);
      for (int i = 0, e = dim_size; i != e; ++i) {
        converters.push_back(getPerChunkConverter(i));
      }
    
      // Scan the elements of the dense elements attributes and quantize them by
      // using the right quantization parameters.
      int64_t flatten_index = 0;
      auto shape = type.getShape();
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Wed May 08 02:10:16 UTC 2024
    - 4.3K bytes
    - Viewed (0)
  2. tensorflow/compiler/mlir/quantization/common/ir/UniformSupport.h

      // Get a uniform converter for the index-th chunk along the quantizationDim.
      // All the elements in this chunk is quantized by the returned converter.
      UniformQuantizedValueConverter getPerChunkConverter(int index) const {
        return UniformQuantizedValueConverter(scales_[index], zero_points_[index],
                                              clamp_min_, clamp_max_,
    Registered: Sun Jun 16 05:45:23 UTC 2024
    - Last Modified: Wed May 08 02:10:16 UTC 2024
    - 9.8K bytes
    - Viewed (0)
Back to top