Nasrin Rahimi

Hi @xinntao I wonder what is the distinguishing property of the REDS4 000 video, that SR using EDVR has the worst PSNR and SSIM for that?

Problem with importing ModulatedDeformConvPack

6

Hi Everyone, I am trying to train the EDVR in google colab with torch.__version__ '1.3.0+cu100' I have compliled the DCN module first: (!python setup.py develop) and this is the result:...

RuntimeError: Error(s) in loading state_dict for EDVR

5

Hi everyone, I have trained the EDVR with this log for debluring task: 19-11-04 13:38:42.765 - INFO: name: 001_EDVRwoTSA_scratch_lr4e-4_600k_REDS_LrCAR4S use_tb_logger: True model: video_base distortion: sr scale: 4 gpu_ids: [0] datasets:[...

Hi, I want to use BasicVSR++ as generator in GAN framework, how can I do this in mmediting? Also, How can I add customized loss functions in training? Is there...

KeyError: "BasicVSR: 'BasicVSRPlusPlus is not in the model registry'"

4

Hi, I am training BasicVSR++ from scratch on HPC cluster with following environment info: `> sys.platform: linux Python: 3.8.12 (default, Oct 12 2021, 13:49:34) [GCC 7.5.0] CUDA available: True GPU...

loading pretrained BasicVSR++

2

Hi @ckkelvinchan I want to use BasicVSR++ in EDVR old codes as model (I do not want to use mmediting codes at this step) I initiated BasicVSR++ model: from mmedit.models.backbones.sr_backbones.basicvsr_pp...

Hi @ckkelvinchan I can train basicvsr++ with default settings using mmediting codes without any problem and it fits in the gpu memory. However, when I use https://github.com/xinntao/EDVR/tree/old_version to train basicvsr_pp.py...

Hi @andreas128 Thanks for your great work and sharing the code. I tried to train SRFlow using REDS dataset. After training the RRDBN network on REDS (with PSNR around 29...

training for x4 super resolution

2

Dear @Alan-xw , thank you for your code. I want to train LP-KPN model for superresolution task in which the input lr images are 4 times smaller than GT. I...