Dachun Kai

icon indicating a website link WeChat ID: Boy_Dachun icon indicating an email [email protected]

icon company University of Science and Technology of China icon location Hefei, Anhui Province, China icon location PhD student at USTC, interested in computational imaging, and multi-modal learning.

Results 33 comments of Dachun Kai

new issues about No module named 'basicsr.version'

> 我下载了basicsr,但也显示ModuleNotFoundError: No module named 'basicsr.version' 你的pip install basicsr或者python setup.py develop任何一个都没有跑

Error when training basicvsr x2 model after 300k iterations

This bug still exists.🥲

Other flow teacher network?

Thank you, but I couldn't find the analysis in Task-Oriented Flow Distillation Loss explaining why RAFT's teacher network is not as good as LiteFlowNet, or Pwc-Net? Additionally, I noticed that...

Vid4 Test Error

+1, have you solved this problem?

A question about the PSRT-Sliding model in psrt_sliding_arch.py

Meet the same problem. How to solve it?

How to deblur single image ? The options for a single frame image are missing

Could anyone provide such single frame deblur option file? Thanks a lot!

Model Parameters is different from the paper

Thanks. Is there any error with the [experimenta.cfg](https://github.com/KAIST-VICLab/FMA-Net/blob/main/experiment.cfg) file? According to my understanding, [num_seq](https://github.com/KAIST-VICLab/FMA-Net/blob/main/experiment.cfg#L22) should be equal to [num_flow](https://github.com/KAIST-VICLab/FMA-Net/blob/main/experiment.cfg#L39) + 1, i.e., if using three frames as a sliding window....

Model Parameters is different from the paper

@GeunhyukYouk Does num_seq mean the number of frames in each sliding window? Are there any limitations on the test video frame length, such as the relationship between the total number...

Frame index mismatch between GOPRO_Large and GOPRO_Large_all?

Yes, I found the same problem. Have you found which frames are used to simulate `GOPRO_Large/test/GOPR0384_11_05/blur/004001.png.` in `GOPRO_Large_all`?

VRAM Requirement?

Hi, we haven't compared our model directly with [Video2X](https://github.com/k4yt3x/video2x) yet, but thank you for the suggestion. We will consider doing a comparison in the future. We tested upscaling 100 frames...