SUPER-MARIO comments

Results 101 comments of


                                            SUPER-MARIO

question about trainDAN.py - loading training data

@td042 Hi, if you follow the steps in README, you will get the npz-files. `python training\testSetPreparation.py` will create the npz-files, i.e. dataset_nimgs=x*.npz, x is a number which depends on the...

question about trainDAN.py - loading training data

@td042 Yes.

question about trainDAN.py - loading training data

@td042 You should do `python trainingSetPreparation.py` to make trainset, meanwhile, you should set `STAGE` to 1, I've tried to git clone this repo and I found no problem. The meaning...

question about trainDAN.py - loading training data

@td042 According to the error message, it seems that you created two graphs, I don't know what's wrong with the code, I can run `trainDAN.py` with no error occurred, if...

error on trainingsetpreparation

What error?

STAGE2的时候发现test error爆发式增长

这个应当和训练参数有关。

加不加mean shape影响

meanshape的意义在于，模型实际上是学习ground truth和meanshape的残差，使用自己的数据集的话，如果是68点，如果不是，可以自己算一下平均，当然，也可以不用meanshape。

issues about trainDNA.py

@JWSunny 还真没遇到过，请问你是用这份代码里的脚本生成的数据吗？

issues about trainDNA.py

@JWSunny 是N 6，你可以用脚本试试就知道产生的数据是什么样子了的。

issues about trainDNA.py

@JWSunny hi，请问哪里的处理有问题，也请你说一下，因为我的使用过程中没发现这个问题，有解决方法也请分享一下吧。