You're reading the documentation for a development version.
For the latest stable release version, please have a look at master.

Dismiss

Function float_to_fp16_vector

• Defined in File quantize.h

Function Documentation

void float_to_fp16_vector(uint8_t *output, const float *input, const int size, const int stride)

批量数据的单精度浮点数到半精度浮点数的量化操作

参数:

• output -- [OUT] 反量化后的数据

• input -- [IN] 待反量化的数据

• size -- [IN] 待反量化数据的大小

• stride -- [IN] 待反量化数据的步长