update trainining

Author: xinntao

README.md

@@ -81,6 +81,17 @@ python inference_gfpgan_full.py --model_path experiments/pretrained_models/GFPGA
 We provide complete training codes for GFPGAN. <br>
 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
 
 ## :scroll: License and Acknowledgement

README_CN.md

@@ -81,6 +81,17 @@ python inference_gfpgan_full.py --model_path experiments/pretrained_models/GFPGA
 We provide complete training codes for GFPGAN. <br>
 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
 
 ## :scroll: License and Acknowledgement

experiments/pretrained_models/README.md

@@ -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)

train_gfpgan_v1.yml

@@ -9,9 +9,11 @@ datasets:
   train:
     name: FFHQ
     type: FFHQDegradationDataset
-    dataroot_gt: datasets/ffhq/ffhq_512.lmdb
+    # dataroot_gt: datasets/ffhq/ffhq_512.lmdb
+    dataroot_gt: datasets/ffhq/ffhq_512
     io_backend:
-      type: lmdb
+      # type: lmdb
+      type: disk
 
     use_hflip: true
     mean: [0.5, 0.5, 0.5]
@@ -44,10 +46,12 @@ datasets:
     prefetch_mode: ~
 
   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
-    dataroot_lq: datasets/faces/validation1020_512/input  # TODO: modify before release
-    dataroot_gt: datasets/faces/validation1020_512/input
+    dataroot_lq: datasets/faces/validation/input
+    dataroot_gt: datasets/faces/validation/reference
     io_backend:
       type: disk
     mean: [0.5, 0.5, 0.5]