-
由 Alexander Alekhin 提交于
* dnn(ocl4dnn): fix LRN layer accuracy problems - FP16 intermediate computation is not accurate and may provide NaN values * dnn(test): update tolerance for FP16
8041ab8a
* dnn(ocl4dnn): fix LRN layer accuracy problems - FP16 intermediate computation is not accurate and may provide NaN values * dnn(test): update tolerance for FP16