std :: ml::float16
Function std::fp16_to_f32
float fp16_to_f32(unsigned short h)Converts an fp16 bit pattern back to float32. Exact -- every fp16 value (including subnormals, infinities, and NaNs) is exactly representable in float32.
std :: ml::float16
float fp16_to_f32(unsigned short h)Converts an fp16 bit pattern back to float32. Exact -- every fp16 value (including subnormals, infinities, and NaNs) is exactly representable in float32.