Cannot reproduce results
yuanze-lin opened this issue · comments
Hi, dear authors, I've recently reproduced your work, the command is as following:
python main.py --data_root /home/data/ --dataset gopro_ds_lmdb --ds_config 2ms16ms --batch_size 32 --data_format RGB
I use 4 x p40 devices, but the output is:
2021/06/09, 02:28:12 - gopro_ds_lmdb results generating ...
2021/06/09, 02:28:12 - seq 000 image results generating ...
2021/06/09, 02:28:54 - seq 001 image results generating ...
2021/06/09, 02:29:33 - seq 002 image results generating ...
2021/06/09, 02:30:11 - seq 003 image results generating ...
2021/06/09, 02:30:49 - seq 004 image results generating ...
2021/06/09, 02:31:28 - seq 005 image results generating ...
2021/06/09, 02:32:06 - seq 006 image results generating ...
2021/06/09, 02:32:59 - seq 007 image results generating ...
2021/06/09, 02:33:37 - seq 008 image results generating ...
2021/06/09, 02:34:15 - seq 009 image results generating ...
2021/06/09, 02:34:53 - seq 010 image results generating ...
2021/06/09, 02:35:24 - Test images : 1067
2021/06/09, 02:35:24 - Test PSNR : 29.877435602139418
2021/06/09, 02:35:24 - Test SSIM : 0.8923279783187907
2021/06/09, 02:35:24 - Average time per image: 0.07301736338173642
Final PSNR and SSIM are much lower than paper's results.
Furthermore, can you provide pretrained weights on GoPro dataset?
Hi, the batch size will affect the performance, if you keep the other hyper-parameters unchanged. (same learning rate, better performance with smaller batch size)
Furthermore, can you provide pretrained weights on GoPro dataset?
Sorry, I can only provide the pretrained weights for our BSD dataset.
The pre-training weights for the GoPro dataset are in Huawei's workstation, and I don't have access to it.
Hi, the batch size will affect the performance, if you keep the other hyper-parameters unchanged. (same learning rate, better performance with smaller batch size)
Furthermore, can you provide pretrained weights on GoPro dataset?
Sorry, I can only provide the pretrained weights for our BSD dataset.
The pre-training weights for the GoPro dataset are in Huawei's workstation, and I don't have access to it.
Dear author, thanks for your quick reply, and I want to know how to reproduce the results of GoPro dataset.
Please keep the batch size as default value, i.e. 8.
Please keep the batch size as default value, i.e. 8.
OK, I'll try your suggestion