Function at::fake_quantize_per_tensor_affine(const at::Tensor&, double, int64_t, int64_t, int64_t)#

• Defined in File Functions.h

Function Documentation#

inline at::Tensor at::fake_quantize_per_tensor_affine(const at::Tensor &self, double scale, int64_t zero_point, int64_t quant_min, int64_t quant_max)#