v/GFPGAN
1
0
Fork 0
mirror of https://github.com/TencentARC/GFPGAN.git synced 2025-05-16 07:10:24 -07:00
Code Issues Projects Releases Wiki Activity

update trainining

Browse Source
This commit is contained in:
Xintao 2021-06-18 10:07:45 +08:00
parent 2bbdcc1c84
commit c466b9bfdd
4 changed files with 38 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
README.md
View File

@ -81,6 +81,17 @@ python inference_gfpgan_full.py --model_path experiments/pretrained_models/GFPGA
We provide complete training codes for GFPGAN. <br> We provide complete training codes for GFPGAN. <br>
You could improve it according to your own needs. You could improve it according to your own needs.
1. Dataset preparation: [FFHQ](https://github.com/NVlabs/ffhq-dataset)
1. Download pre-trained models and other data. Put them in the `experiments/pretrained_models` folder.
1. [Pretrained StyleGAN2 model: StyleGAN2_512_Cmul1_FFHQ_B12G4_scratch_800k.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/StyleGAN2_512_Cmul1_FFHQ_B12G4_scratch_800k.pth)
1. [Component locations of FFHQ: FFHQ_eye_mouth_landmarks_512.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/FFHQ_eye_mouth_landmarks_512.pth)
1. [A simple ArcFace model: arcface_resnet18.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/arcface_resnet18.pth)
1. Modify the configuration file `train_gfpgan_v1.yml` accordingly.
1. Training
> python -m torch.distributed.launch --nproc_per_node=4 --master_port=22021 train.py -opt train_gfpgan_v1.yml --launcher pytorch > python -m torch.distributed.launch --nproc_per_node=4 --master_port=22021 train.py -opt train_gfpgan_v1.yml --launcher pytorch
## :scroll: License and Acknowledgement ## :scroll: License and Acknowledgement

11
README_CN.md
View File

@ -81,6 +81,17 @@ python inference_gfpgan_full.py --model_path experiments/pretrained_models/GFPGA
We provide complete training codes for GFPGAN. <br> We provide complete training codes for GFPGAN. <br>
You could improve it according to your own needs. You could improve it according to your own needs.
1. Dataset preparation: [FFHQ](https://github.com/NVlabs/ffhq-dataset)
1. Download pre-trained models and other data. Put them in the `experiments/pretrained_models` folder.
1. [Pretrained StyleGAN2 model: StyleGAN2_512_Cmul1_FFHQ_B12G4_scratch_800k.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/StyleGAN2_512_Cmul1_FFHQ_B12G4_scratch_800k.pth)
1. [Component locations of FFHQ: FFHQ_eye_mouth_landmarks_512.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/FFHQ_eye_mouth_landmarks_512.pth)
1. [A simple ArcFace model: arcface_resnet18.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/arcface_resnet18.pth)
1. Modify the configuration file `train_gfpgan_v1.yml` accordingly.
1. Training
> python -m torch.distributed.launch --nproc_per_node=4 --master_port=22021 train.py -opt train_gfpgan_v1.yml --launcher pytorch > python -m torch.distributed.launch --nproc_per_node=4 --master_port=22021 train.py -opt train_gfpgan_v1.yml --launcher pytorch
## :scroll: License and Acknowledgement ## :scroll: License and Acknowledgement

7
experiments/pretrained_models/README.md Normal file
View File

@ -0,0 +1,7 @@
# Pre-trained Models and Other Data
Download pre-trained models and other data. Put them in this folder.
1. [Pretrained StyleGAN2 model: StyleGAN2_512_Cmul1_FFHQ_B12G4_scratch_800k.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/StyleGAN2_512_Cmul1_FFHQ_B12G4_scratch_800k.pth)
1. [Component locations of FFHQ: FFHQ_eye_mouth_landmarks_512.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/FFHQ_eye_mouth_landmarks_512.pth)
1. [A simple ArcFace model: arcface_resnet18.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/arcface_resnet18.pth)

14
train_gfpgan_v1.yml
View File

@ -9,9 +9,11 @@ datasets:
train: train:
name: FFHQ name: FFHQ
type: FFHQDegradationDataset type: FFHQDegradationDataset
dataroot_gt: datasets/ffhq/ffhq_512.lmdb # dataroot_gt: datasets/ffhq/ffhq_512.lmdb
dataroot_gt: datasets/ffhq/ffhq_512
io_backend: io_backend:
type: lmdb # type: lmdb
type: disk
use_hflip: true use_hflip: true
mean: [0.5, 0.5, 0.5] mean: [0.5, 0.5, 0.5]
@ -44,10 +46,12 @@ datasets:
prefetch_mode: ~ prefetch_mode: ~
val: val:
name: validation1020_512 # Please modify accordingly to use your own validation
# Or comment the val block if do not need validation during training
name: validation
type: PairedImageDataset type: PairedImageDataset
dataroot_lq: datasets/faces/validation1020_512/input # TODO: modify before release dataroot_lq: datasets/faces/validation/input
dataroot_gt: datasets/faces/validation1020_512/input dataroot_gt: datasets/faces/validation/reference
io_backend: io_backend:
type: disk type: disk
mean: [0.5, 0.5, 0.5] mean: [0.5, 0.5, 0.5]