-
Hi,
I tried the latest version of Edsr-pytorch with an argument named '--chop_forward' but it complains no such argument exists. Is it still there or name changed to something?
Thanks!
-
Making model...
Preparing loss function:
1.000 * L1
[Epoch 1] Learning rate: 1.00e-4
Making model...
Preparing loss function:
1.000 * L1
[Epoch 1] Learning rate: 1.00e-4
Tracebac…
-
Hi，
From the paper,I noticed the sentence “ We also observe that fine-tuning on a network pretrained on the BI degradation model leads to higher PSNR values than training from scratch. ”Could you tell…
lkyee updated
5 years ago
-
appreciate your excellent work..... I'm training WDSR model on DIV2K_x3 training set ,now the global step is about 2650000: PSNR = 31.0282, global_step = 2650000, loss = 0.01833889. it is increasing …
-
I was trying to learn using my own data set, but when executing the code the following
There was an error.
Traceback (most recent call last):
File "main.py", line 4, in
import data
Fil…
-
I'm running slightly modified code of EDSR baseline network from here: https://github.com/thstkdgus35/EDSR-PyTorch
The training on first epoch goes well, but on the test stage when loading a model it…
-
https://github.com/thstkdgus35/EDSR-PyTorch/blob/70294bb6170651dd1c2435da18a34c0e2cf63511/src/model/common.py#L21
nn.Module or nn.Conv2d does not have the "requires_grad" attribute.
I think the gr…
-
How do you evaluate the models? The command I tested was this one:
`python main.py --data_test Set5 --data_range 801-900 --scale 4 --pre_train download --test_only --self_ensemble`
where my pars…
-
Can you explain the function of residual scaling parameter β in RRDB?
-
In paper of edsr,rcan and so on, before residual there should be a conv.
For example, in edsr , (conv-act-conv)*n_blocks-conv , and there is a residual before and after this.
In rcan, …