loss during training about caffe-vdsr HOT 9 CLOSED

Hi, 0.4 is ok. You can test your trained model in Set5 or Set14 and check the PSNR, and you can have a look at my training log, https://raw.githubusercontent.com/huangzehao/caffe-vdsr/master/Train/VDSR_291_multiscale_adam.log.

from caffe-vdsr.

@huangzehao Thanks for your reply.
I find that the PSNR does not become bigger or converge with the iteration increasing.
when I trained 170000 times , the psnr of butteffly is 29.922.
when I trained 250000 times , the psnr of butteffly is 29.898 .
when I trained 360000 times , the psnr of butteffly is 29.917.
when I trained 450000 times , the psnr of butteffly is 29.714.
when I trained 520000 times , the psnr of butteffly is 29.978.
Is it weird???

from caffe-vdsr.

@ @huangzehao Looking forward to your reply! Thank you !

from caffe-vdsr.

Hi, sorry for the late reply.
You should benchmark your model in full dataset, including Set5, Set14 and BSD100.
The psnr of single image sometimes can not represent the performance of your model.

from caffe-vdsr.

Hi, I have a question regarding the training. How many iterations do we need to train a reasonable VDSR model?
According to your discussion above, it seems at least 2*10^5 iterations are needed.
But it is stated in the paper that the training takes less than 4 hours which I think is not quite enough to finish more than 10^5 iterations.

from caffe-vdsr.

@xuxy09 Hi, check this #29

from caffe-vdsr.

Thanks. Seems like we have the same concern about the training time. And I agree with you that it is impossible to finish 80 epochs in 4 hours with one Titan Z, especially considering that Caffe is faster than MatConvnet generally. I think 24 hours should be a more reasonable answer.

from caffe-vdsr.

hello，@huangzehao I also have the same question about the test loss value。 In your Train log,the test loss converges to 0.4 after 15 epoch，it's ok test in Set5，But Set14 and BSD100。So I just want know How many epoch the Set14 and BSD100 datasets can get the same results in paper. Hope for your reply ,Thank you !

from caffe-vdsr.

@ChaofWang Hi, you can test the trained model in Set14 and BSD100. 20 or 30 epoch is enough.

from caffe-vdsr.