【量化】【TensorFlow】实现细节+重要代码片

QuantizationParams

// Quantization parameters, determining the mapping of quantized values
// to real values (i.e. determining how quantized values are mathematically
// interpreted).
//
// The correspondence is as follows:
//
//   real_value = scale * (quantized_value - zero_point);
//
// In other words, zero_point designates which quantized value corresponds to
// the real 0 value, and scale designates the difference between the real values
// corresponding to consecutive quantized values differing by 1.
struct QuantizationParams {
  int32 zero_point = 0;
  double scale = 0.;
};

FullyConnected

inline void FullyConnected(const uint8* input_data, const Dims<4>& input_dims,
                           int32 input_offset, const uint8* filter_data,
                           const Dims<4>& filter_dims, int32 filter_offset,
                           const int32* bias_data, const Dims<4>& bias_dims,
                           int32 output_offset, int32 output_multiplier,
                           int output_shift, int32 output_activation_min,
                           int32 output_activation_max, uint8* output_data,
                           const Dims<4>& output_dims,
                           gemmlowp::GemmContext* gemm_context) {
  (void)gemm_context;  // only used in optimized code.
  TFLITE_DCHECK_LE(output_ac