ECCV2022-RIFE

ECCV2022-RIFE copied to clipboard

Outputted videos are "very slightly" shorter than input videos

10

This issue is similar to #23 but I believe a different bug is causing this. Outputted videos are shorter by usually only a few seconds. If I rip the audio...

sloganking

Image encoding is a bottleneck - Implement multithreaded image writing?

1

Using uncompressed BMP instead of PNG increased my speed from ~14 FPS at 1080p to ~18 FPS, proving that the image encoding slows things down and bottlenecks the GPU. Is...

n00mkrad

"assert len(arr) == framesize" throws an error

3

Hello, I tried to run the command "python3 inference_video.py --exp=1 --video=video.mp4" on my own custom video, but I got the error : ``` [email protected] in /shared/httpd/arXiv2020-RIFE $ python3 inference_video.py --exp=1...

Thaldos

Testtime of RIFE_m

2

How can i test the time of RIFE_m

bis70

如何对任意时刻进行插帧

4

注意到RIFE设计为对t=0.5处进行插帧，再利用迭代方式获取更多帧数。如果我想在任意时刻进行插帧，请问如何修改？

QMME

train error (nccl) torch.distributed

2

I think your work is great. Unfortunately I do not manage to train the NN. The following error message appears in the console: (rife) PS C:\Users\C\PycharmProjects\RIFE> python -m torch.distributed.launch --nproc_per_node=1...

bis70

关于复现模型训练

4

我想用复现您的模型训练过程，但是您的训练代码是分布式训练的，我只有一台电脑，一个cpu，一个gpu，在使用您的代码训练时，发生了以下错误，请问如何用您的代码进行训练，顺便问下您当初训练了多久？  

Sean082408

有关示例中的命令无法运行的问题。

2

您好，在您给的示例中的这句命令运行在终端上没有任何反应，没用得到期待的效果，而且执行时间也很短，请问是什么问题呢？

Sean082408

hi, just add `!pip3 install -r requirements.txt` to google colab link to fix dependency error /:

BLACKGAMER1221

It is not using GPU

2

I have NVIDIA RTX 3070 GPU and when I ran this command: python inference_video.py --exp=2 --scale=1 --video=test_video.mp4 It wasn't using any of my GPU but a CPU instead.

Pekgame