Junghyun Park

Results 14 comments of Junghyun Park

@jlooper Hi, I can't assign this issue myself. Will you help me?

I found the reason of error. When I print `t.device` and `self.src_device_obj` in torch *data_parallel.py* file. I got cpu for t.device and cuda:0 for self.src_device_obj. I guess the model made...

Yes I have and I checked it again by using that link. ![image](https://user-images.githubusercontent.com/36429399/62756298-23dad600-bab2-11e9-90ee-a656c1e006c6.png)

@ahmetgunduz Unfortunately not yet. I will try to run this code with other machine which has another cuda and cudnn version next week to check this problem whether cuda problem...

@Cadene Did you mean this 'http://data.lip6.fr/cadene/pretrainedmodels/inceptionv4-8e4777a0.pth'?

I tried it before. After that I always get another error like this. ![image](https://user-images.githubusercontent.com/36429399/55270755-4976f800-52e6-11e9-82a0-d846a8a7f8d3.png)

@kaifeng777 sorry I couldn't solve it

@SooDevv @MijeongJeon 아! 이거 처리를 안했네요. 데이터를 직접 전처리를 해야되는 문제가 있었는데, 어떻게할까요?

블로그의 주소입니다. [딥러닝(CycleGAN)을 이용해 Fornite 를 PUBG 로 바꾸기](https://towardsdatascience.com/turning-fortnite-into-pubg-with-deep-learning-cyclegan-2f9d339dcdb0)

고맙습니다! 사실 모르는 게임이라.. ㅋㅋ