DCVC-DC training code about dcvc HOT 5 CLOSED

@nzomi

Hi, I'm quite interested in the training code for DCVC-DC as well. However, the model trends to collapse after few epochs.
Do you have similar problem? or could you share your training code for reference.

Thank you so mush.

from dcvc.

@Cihsaing Hi Cihsaing! I simply used the training strategy provided by TCM v1 https://arxiv.org/abs/2111.13850v1

from dcvc.

@nzomi Hi, Could I discuss some details with you personally?

from dcvc.

I observe exactly the same issue as @nzomi. After cascaded training with hierarchical GOP (using the same weights mentioned in the paper), the BD-PSNR rate is higher than the officially trained models, if the test sequences are only 5 frames long. However the BD-rate rapidly deteriorates for sequences longed than 5 frames. At the end, when coding a sequence that is like 32 frames long, the coding performance is much worse than official models.

I use the vimeo90k, that is 7 frames long for training. could that be the issue here? Or is there any other tricks in the training to keep the PSNR more consistent?

from dcvc.

I'm so interested in the DCVC-FM, could you please send me the traing codes. Thanks very much.

[email protected]

from dcvc.