search

ltkong218 / IFRNet

IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation (CVPR 2022)
MIT License
259 stars 23 forks source link

Evaluation Results for gopro dataset #24

Open VongolaWu opened 1 year ago

VongolaWu commented 1 year ago

Hi, When I use your provided checkpoint for gopro dataset, the evaluate result seems very low. I set the resume_epoch to 599 (epochs=600) and resume_path to the provided checkpoint (checkpoints/IFRNet_GoPro.pth), also comments all the training parts so that it will directly go to the evaluation part. The results are: image Could you give me some possible reasons so that I can debug?

ltkong218 commented 1 year ago

For your problems, I have following suggestions:

We have tested our pre-trained checkpoints of IFRNet for both 2x and 8x frame interpolation. If your PSNR is only around 15~16 dB, I think your experimental environment is incorrectly configured. Please check whether your PyTorch version and backward warping operation meet the requirement. If your environment is correctly configured, you should reproduce our 2x and 8x frame interpolation demos in our GitHub repository. Please also follow the training and test datasets split in our code.

Thanks.

VongolaWu commented 1 year ago

Thank you for your reply. Could you share the environment list? So that I can use exact packages.

ltkong218 commented 1 year ago

In fact, I have developed and deployed this repository on different environment including PyTorch 1.3.0 and PyTorch 1.9.1. Since the IFRNet is concise and does not depend on complex modules, most PyTorch environments can run IFRNet. Thanks.