-
Getting this new error:
Traceback (most recent call last): File "/home/nendo/.local/lib/python3.8/site-packages/rq/worker.py", line 1431, in perform_job rv = job.perform() File "/home/nendo/.local/…
-
I tried changing the MipGenSettings on the RenderTarget but it had no effect at all. I guess autogenerate mipmaps uses a default way (averaging?) for creating mipmaps and that's it. Is that right?
-
-
# URP 설정
1. Post Processing 비활성화
2. 안티 앨리어싱 MSAA 2x 사용
## Post Processing
Post Processing 이 GPU 성능을 많이 차지한다. 비활성화 하거나 최적화 설정이 필요하다.
- Bloom 설정이 Batch 를 엄청나게 차지한다
- Batch Count
- Ena…
Eu4ng updated
9 months ago
-
Hi,
I saw your code resizes the input images to 3:2. Can I use images with different resolution ratio to train the model? Do I need to revise some code?
Thanks
-
Other models, such as pix2pix, cycleGAN are common to get a result with artifacts. But the ESRGAN model has a great result without any artifacts? How did you achieve this?
Thank you!
-
I've noticed the track for the removed reads, but I didn't understand why are they removed? Were they have been labeled as PCR duplicates? I'd like to see some more verbosity in pop-ups about these re…
-
Thanks for your excellent work!
I noticed convcrf is run on gpu, while fullcrf is run on cpu. Is it unfair to compare two algorithms on different platforms?
-
-
Thanks for sharing! When I apply DSC3D block in my own net and dataset. I meet the OOM problem, the training patch_size is 128x128x128, the batchsize is 2 and the input_channels is 32. How can i sovl…