alexliyang

excuse me, I donnot know this mean? how to keep R/G/B ration?

the network blocked upload image :( the train data I used likes trainning 3DLUT model, 480p jpg file as the original , and use expertC's as the ground truth, then...

here is the goundtruth:  and the inference out is  I think they have more difference, how to improve the training model? > Can you she image output that...

这里采用了adjust_bn_momentum后，推理的结果和没有采用是有差异的，我转换到onnx后，差异会变大，这种情况下应该怎么处理更好？ 谢谢先

ARM 平台支持的算子相对比较少，比如conv_transpose, PRelu, spacetodepth, depthtospace, 是否能增加一下？