Closed yuangan closed 4 years ago
Hey!
Sorry for the delayed response. From your parameters, it looks like a couple of things are off:
city_test.txt
only has 2 images and was originally meant to pipe-clean the script infrastructure and not to compare results. You will need the full "City" imagelist to obtain a decent result. Also, note that the amount of images that city_test.txt
uses is much lesser than the nFrames in this case, which won't let the model extract temporal information from adjacent frames since the frames aren't available.nFrames
is pretty low in your case (7) and should be usually set higher.other_dataset
and residual
might also be off -- I'll need some time to look into those though.Hope this helps!
Hi, I've tested your model weights/netG_epoch_4_1.pth, and I can't get the result of 26.57/0.773 on Foliage datasets. I just got Avg PSNR Predicted = 25.728. Could you tell me how to get it? Besides, the result of City is also under 26. These are my arguments:
Namespace(chop_forward=False, data_dir='./Vid4', debug=False, file_list='city_test.txt', future_frame=True, gpu_mode=False, gpus=1, model='weights/netG_epoch_4_1.pth', model_type='RBPN', nFrames=7, other_dataset=True, output='Results/', residual=False, seed=123, testBatchSize=1, threads=1, upscale_factor=4)
PS: Could you offer the augmented dataset? Thanks very much!