【量化】【TensorFlow】实现细节+重要代码片

最新推荐文章于 2021-03-18 21:24:42 发布

代码款款

最新推荐文章于 2021-03-18 21:24:42 发布

阅读量1.8k

点赞数

分类专栏： # 通用实验相关 # 模型压缩（model compression）文章标签： TensorFlow api quantize

本文链接：https://blog.csdn.net/yifen4234/article/details/80306835

版权

本文深入探讨了TensorFlow的量化技术，详细介绍了QuantizationParams、FullyConnected等核心概念，以及GetOrComputeMinMax和quantize_v2等关键函数的使用。通过解析op_def_library.py中的相关代码，揭示了TensorFlow量化API的工作原理。

摘要由CSDN通过智能技术生成

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