FMA-Net

FMA-Net copied to clipboard

run on single video

3

hi, i see the evaluation/testing code but how can i run the pretrained model on a single video?

ahmadmustafaanis

training dataset and super resolution capability

1

Hi, thank you for your great work! I have a couple of questions: 1. Are the experimental results' pretrained weights trained on the REDS train set (excluding Clips 000, 011,...

jimmycv07

Strange Inference time ?

1

In your paper you wrote the inference time with Basic VSR++ is 0.072 seconds and i wonder how you get these values? That would lead in 13.9FPS and i never...

Platorius

Colab version + Can't reproduce the results on the custom video

1

Hello, and thank you for sharing FMA-Ne code. I have been waiting for the model for a while, as I personally love to apply ML tools to ancient historical videos....

DenisSergeevitch

Deblurring and general video quality enhancement

3

First, thanks a lot for sharing the model weights and the code. We did some tests and it works pretty well on certain types of video. But in our use...

ngaer

How much vram is needed

1

Hi, thank you for your great work! How much vram do I need when testing?

kackbob

No such file or directory: './results/FMA-Net\\test\\avg_rgb_psnr.txt'

1

when I run the main.py by "python main.py --test --config_path experiment.cfg",This question arises，How can i get the text，thank you

17307181179

Thanks for your work! I load your pretrained R&D ckpt and finetune the model on my dataset. But after 40 epochs, the model seems to collapse. The Recon Loss and...

Solidays-Hung

Could you tell us how to calculate the Average Motion Magnitude of optical flow for obtaining the PSNR/ tOF results in Tab. 3 in the main paper? Besides, how to...

QZ1-boy

Model Parameters is different from the paper

5

I found that when num_seq=10 and num_flow=9, the measured parameter count is 10.41M; when num_seq=3 and num_flow=2, the measured parameter count is 9.37M. But the parameter count mentioned in the...

DachunKai