change bg_tile default to 400, update readme

README.md

@@ -88,6 +88,8 @@ wget https://github.com/TencentARC/GFPGAN/releases/download/v0.2.0/GFPGANCleanv1
 python inference_gfpgan.py --upscale 2 --test_path inputs/whole_imgs --save_root results
 ```
 
+If you want want to use the original model in our paper, please see [PaperModel.md](PaperModel.md) for installation and inference.
+
 ## :european_castle: Model Zoo
 
 - [GFPGANCleanv1-NoCE-C2.pth](https://github.com/TencentARC/GFPGAN/releases/download/v0.2.0/GFPGANCleanv1-NoCE-C2.pth): No colorization; no CUDA extensions are required. It is still in training. Trained with more data with pre-processing.

inference_gfpgan.py

@@ -17,7 +17,7 @@ def main():
     parser.add_argument('--channel', type=int, default=2)
     parser.add_argument('--model_path', type=str, default='experiments/pretrained_models/GFPGANCleanv1-NoCE-C2.pth')
     parser.add_argument('--bg_upsampler', type=str, default='realesrgan')
-    parser.add_argument('--bg_tile', type=int, default=0)
+    parser.add_argument('--bg_tile', type=int, default=400)
     parser.add_argument('--test_path', type=str, default='inputs/whole_imgs')
     parser.add_argument('--suffix', type=str, default=None, help='Suffix of the restored faces')
     parser.add_argument('--only_center_face', action='store_true')

requirements.txt

@@ -1,4 +1,5 @@
-facexlib
+basicsr>=1.3.3.10
+facexlib>=0.2.0.2
 lmdb
 numpy
 opencv-python