liqilei / gmfn Goto Github PK

Can you tell me about the training time? How many 2080ti did you use for training?

Hi, liqilei
After I have run about 700 epoches, the reult on val set is 32.41(highest result). I want to know if my training process seems to be problematic?
How long did you reach 32.47 of SRFBN when you were training? How long does it take to reach 32.70?
Thank you.

In order to reproduce the results in your paper, do I only need to prepare training data and then modify the value of scale in json?

Hey @Paper99,

Thanks for sharing your code! I wonder if it is possible to help with visualizing featuer-maps as you did in your paper figure 4.

Thanks

you must add codes of networks/init.py for create model (add contractor codes for GMFN).

Hi,
After I have trained the DIV2k, I get the final result(use best_ckp.pth to test):

set5:38.16/0.9610
set14:33.91/0.9203
urban100:32.81/0.9349
B100:32.30/0.9011
manga109:39.01/0.9776

It seems much lower than that in your paper.

hi liqilei,thank you for your outstanding work.
I test my image.the result like this: Edge contours are obvious
How can I do this?

CUDA_VISIBLE_DEVICES=0 python train.py -opt options/train/train_GMFN.json
I use celeba dataset train

===> Training Epoch: [1/1000]... Learning Rate: 0.000200
Epoch: [1/1000]: 0%| | 0/251718 [00:00<?, ?it/s]
Traceback (most recent call last):
File "train.py", line 131, in
main()
File "train.py", line 69, in main
iter_loss = solver.train_step()
File "/exp_sr/SRFBN/solvers/SRSolver.py", line 104, in train_step
loss_steps = [self.criterion_pix(sr, split_HR) for sr in outputs]
File "/exp_sr/SRFBN/solvers/SRSolver.py", line 104, in
loss_steps = [self.criterion_pix(sr, split_HR) for sr in outputs]
File "/toolscnn/env_pyt0.4_py3.5_awsrn/lib/python3.5/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/toolscnn/env_pyt0.4_py3.5_awsrn/lib/python3.5/site-packages/torch/nn/modules/loss.py", line 87, in forward
return F.l1_loss(input, target, reduction=self.reduction)
File "/toolscnn/env_pyt0.4_py3.5_awsrn/lib/python3.5/site-packages/torch/nn/functional.py", line 1702, in l1_loss
input, target, reduction)
File "/toolscnn/env_pyt0.4_py3.5_awsrn/lib/python3.5/site-packages/torch/nn/functional.py", line 1674, in _pointwise_loss
return lambd_optimized(input, target, reduction)
RuntimeError: input and target shapes do not match: input [16 x 3 x 192 x 192], target [16 x 3 x 48 x 48] at /pytorch/aten/src/THCUNN/generic/AbsCriterion.cu:12