valPSNR increase very slowly about super-slomo HOT 9 CLOSED

• I have added tensorboard. How do the interpolated images look on the validation set?

• Are you using a custom dataset or adobe240fps dataset?

  • If you are using a custom dataset, then it should have slow motion videos. The dataloader takes frame1 and frame8 as reference and interpolates the frames in between.

• Did you use the create_dataset script?

from super-slomo.

Thanks for your reply
First interpolated images looks not good and blurred.

And I used adobe240dataset using create_dataset script

from super-slomo.

Can you attach the interpolated results from tensorboard? Also specify your setup- CPU/GPU, PyTorch version, OS, etc. 15.5 valPSNR is really low. Maybe there is a problem with dataset or setup.

from super-slomo.

I'm using GTX 1060
Is that problem reducing batch size to 4?

I added validation image, and graph

from super-slomo.

#22
seems like this was the problem
I've changed code and graph looks good.

from super-slomo.

#22
seems like this was the problem
I've changed code and graph looks good.

Right. The two reference (left and right corner) look very different. Frames in a clip look very similar since they are slow motion videos. Will fix the code.

from super-slomo.

@avinashpaliwal line 69 in create_dataset.py.
I changed line
images = os.listdir(os.path.join(root, file))
to
images = sorted(os.listdir(os.path.join(root, file)))

from super-slomo.

@avinashpaliwal I have the same problem. I had trained the model to 270 epoch, but the valPSNR keep bellow 15, can you help me ?

the follow is valPSNR changing curve

from super-slomo.

@avinashpaliwal I have the same problem. I had trained the model to 270 epoch, but the valPSNR keep bellow 15, can you help me ?

the follow is valPSNR changing curve

Try the new create_dataset script to generate the dataset and try training again. The model starts converging right from the beginning.

from super-slomo.