profile
viewpoint
Chaofeng Chen chaofengc The University of Hong Kong Hong Kong chaofengc.github.io

chaofengc/PSFRGAN 159

PyTorch codes for "Progressive Semantic-Aware Style Transformation for Blind Face Restoration"

chaofengc/Face-SPARNet 66

Pytorch codes for "Learning Spatial Attention for Face Super-Resolution", TIP 2020.

chaofengc/Face-Sketch-Wild 59

Semi-Supervised Learning for Face Sketch Synthesis in the Wild, ACCV2018

chaofengc/Face-Sketch 41

Face Sketch Synthesis with Style Transfer using Pyramid Column Feature

chaofengc/Configuration 5

vim and tmux configuration

chaofengc/BradleyTerryModel-Pytorch 0

Simple bradley terry model in pytorch

chaofengc/flow-code-python 0

Python I/O for optical flow files (.flo)

chaofengc/pytorch-CycleGAN-and-pix2pix 0

Image-to-Image Translation in PyTorch

startedlab-ml/nn

started time in 19 hours

PublicEvent

startedcszn/BSRNet

started time in 2 days

startedcszn/BSRNet

started time in 2 days

PublicEvent

startedchaofengc/PSFRGAN

started time in 3 days

startedpetuum/autodist

started time in 3 days

startedsniklaus/pytorch-hed

started time in 3 days

startedautonomousvision/graf

started time in 4 days

startedchaofengc/Face-SPARNet

started time in 4 days

startedPaddlePaddle/PaddleOCR

started time in 4 days

startedPaddlePaddle/PaddleGAN

started time in 4 days

startedarogozhnikov/einops

started time in 4 days

startedchaofengc/Face-SPARNet

started time in 4 days

startedml-tooling/best-of-ml-python

started time in 4 days

startedDingXiaoH/RepVGG

started time in 4 days

startedActiveVisionLab/DualRC-Net

started time in 5 days

startedchaofengc/Face-SPARNet

started time in 5 days

issue commentchaofengc/Face-SPARNet

Getting Some Errrors

If you set default Gnorm to in, you should remove the --Gnorm in the command.

From the error message "Norm type 'in' not support.", I guess the single quotes might be the problem. You may try to remove the quote. If this does not solve the problem, you may try to print the norm_type to debug the NormLayer class in blocks.py and see what happened.

BTW, the path separator may also cause error, because windowns use \ while Ubuntu use /.

use --Gnorm in [for windows users]

FlowDownTheRiver

comment created time in 5 days

issue commentchaofengc/PSFRGAN

there is a error when translate the psfrgan_latest_net_G.pth to onnx.

thanks , but i can not find the operator "mv", did you use the torch.mv in the code?

zhangyunming

comment created time in 5 days

startedChen-Cai-OSU/awesome-equivariant-network

started time in 5 days

created repositorylucidrains/TPDNE

Open sourcing the simple script that powers thispersondoesnotexist

created time in 5 days

created repositorylucidrains/big-sleep

A simple command line tool for text to image generation, using OpenAI's CLIP and a BigGAN

created time in 5 days

issue commentchaofengc/Face-SPARNet

Getting Some Errrors

I have another question,is the Face-Sparnet repo also compatible with test_enhance_dir_align.py,test_enhance_dir_unalign.py in PSFRGAN repo,if I use these command lines and the py file together?

FlowDownTheRiver

comment created time in 5 days

startedgoogle/neural-tangents

started time in 5 days

issue commentchaofengc/Face-SPARNet

Getting Some Errrors

ok I finally got it working as you suggested. it is the quotes,I removed the --Gnorm and argument,launched the code and get it working like this :

(worked) python test.py --gpus 1 --model sparnethd --name SPARNetHD_V4_Attn2D --res_depth 10 --att_name spar --load_size 512 --dataset_name single --dataroot test_dirs/CelebA-TestN/ --pretrain_model_path ./pretrain_models/SPARNetHD_V4_Attn2D_net_H-epoch10.pth --save_as_dir results_CelebA-TestN/SPARNetHD_V4_Attn2D/

(worked) python test_enhance_single_unalign.py --gpus 1 --model sparnethd --name SPARNetHD_V4_Attn2D --res_depth 10 --att_name spar --pretrain_model_path .\pretrain_models\SPARNetHD_V4_Attn2D_net_H-epoch10.pth --test_img_path .\test_images\test_hzgg.jpg --results_dir test_hzgg_results

(didn't work) python test.py --gpus 1 --model sparnethd --name SPARNetHD_V4_Attn2D --res_depth 10 --att_name spar --Gnorm 'in' --load_size 512 --dataset_name single --dataroot test_dirs/CelebA-TestN/ --pretrain_model_path ./pretrain_models/SPARNetHD_V4_Attn2D_net_H-epoch10.pth --save_as_dir results_CelebA-TestN/SPARNetHD_V4_Attn2D/

FlowDownTheRiver

comment created time in 5 days

starteduniversome/inr-gan

started time in 5 days

startedyinboc/liif

started time in 5 days

startedvsitzmann/awesome-implicit-representations

started time in 5 days

startedvsitzmann/siren

started time in 5 days

more