-
Notifications
You must be signed in to change notification settings - Fork 246
New issue
Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? # to your account
I've run through the code, poor result #26
Comments
@Greenleaf88 I also want to run the code ,but I meet the cannot find Cudnn BatchNorm.Can you help me solve the problem? can you tell me the vesion of your software ? Thanks a lot |
@dongcin I've also met with lots of version problems, using CUDA 7/CUDNN 4 would be OK. |
@Greenleaf88 Thanks for your reply. I download the cuda 7.0 But I find that the driver version is 7.5 running version is 7.0 .Have you met the problem |
cuda version is not important..CUDNN v4 is important. I am able to get good result with cuda 8. |
@Greenleaf88 @AjayNandoriya also want to test the code. However, the download link of deep3d-0050.params seems dead now. Do you have backup version of this file? Thanks in advance!! |
with cuda 7.5 and cudnn4. Completely shiiiiiiiiiiiiiiit results with demo images. If you can get results like the demo, you should sell it to film makers to be a billionare |
@phonchi Do you find the pre-trained model? |
@Greenleaf88 Hi。I'm learning the project too. Can you tell me hao to run the code. Or how to make my own lmdb database.Thanks! |
@Samo-777 Can you tell me hao to run the convert_movie.py ? |
@liutianling how to run data.py to get the lmdb database .
i do not how to run it.please help me !Thanks a lot |
@Samo-777 Haha, bro, that's really mean. But I agree with you, because I have just run the demo code....... |
Although I mansged to run through the test code with my own dataset, the result is very poor, the right eye images are rather blur compared with left one. Could you please share the file mean.npz ? My test data set is very small and may be the mean values generated from it are not very good?
The text was updated successfully, but these errors were encountered: