update README: update installation

README.md

@@ -36,6 +36,7 @@ Blind face restoration usually relies on facial priors, such as facial geometry
 - Python >= 3.7 (Recommend to use [Anaconda](https://www.anaconda.com/download/#linux) or [Miniconda](https://docs.conda.io/en/latest/miniconda.html))
 - [PyTorch >= 1.7](https://pytorch.org/)
 - NVIDIA GPU + [CUDA](https://developer.nvidia.com/cuda-downloads)
+- Linux (We have not tested on Windows)
 
 ### Installation
 
@@ -48,11 +49,33 @@ Blind face restoration usually relies on facial priors, such as facial geometry
 
 1. Install dependent packages
 
+    As StyleGAN2 uses customized PyTorch C++ extensions, you need to **compile them during installation** or **load then just-in-time(JIT)**.
+    You can refer to [BasicSR-INSTALL.md](https://github.com/xinntao/BasicSR/blob/master/INSTALL.md) for more details.
+
+    **Option 1: Load extensions just-in-time(JIT)** (For those just want to do simple inferences, may have less issues)
+
+    ```bash
+    # Install basicsr - https://github.com/xinntao/BasicSR
+    # We use BasicSR for both training and inference
+    pip install basicsr
+
+    # Install facexlib - https://github.com/xinntao/facexlib
+    # We use face detection and face restoration helper in the facexlib package
+    pip install facexlib
+
+    pip install -r requirements.txt
+
+    # remember to set BASICSR_JIT=True before your running commands
+    ```
+
+    **Option 2: Compile extensions during installation** (For those need to train/inference for many times)
+
     ```bash
     # Install basicsr - https://github.com/xinntao/BasicSR
     # We use BasicSR for both training and inference
     # Set BASICSR_EXT=True to compile the cuda extensions in the BasicSR - It may take several minutes to compile, please be patient
-    BASICSR_EXT=True pip install basicsr
+    # Add -vvv for detailed log prints
+    BASICSR_EXT=True pip install basicsr -vvv
 
     # Install facexlib - https://github.com/xinntao/facexlib
     # We use face detection and face restoration helper in the facexlib package
@@ -69,12 +92,23 @@ Download pre-trained models: [GFPGANv1.pth](https://github.com/TencentARC/GFPGAN
 wget https://github.com/TencentARC/GFPGAN/releases/download/v0.1.0/GFPGANv1.pth -P experiments/pretrained_models
 ```
 
-```bash
+- Option 1: Load extensions just-in-time(JIT)
-python inference_gfpgan_full.py --model_path experiments/pretrained_models/GFPGANv1.pth --test_path inputs/whole_imgs
 
-# for aligned images
+    ```bash
-python inference_gfpgan_full.py --model_path experiments/pretrained_models/GFPGANv1.pth --test_path inputs/cropped_faces --aligned
+    BASICSR_JIT=True python inference_gfpgan_full.py --model_path experiments/pretrained_models/GFPGANv1.pth --test_path inputs/whole_imgs
-```
+
+    # for aligned images
+    BASICSR_JIT=True python inference_gfpgan_full.py --model_path experiments/pretrained_models/GFPGANv1.pth --test_path inputs/cropped_faces --aligned
+    ```
+
+- Option 2: Have successfully compiled extensions during installation
+
+    ```bash
+    python inference_gfpgan_full.py --model_path experiments/pretrained_models/GFPGANv1.pth --test_path inputs/whole_imgs
+
+    # for aligned images
+    python inference_gfpgan_full.py --model_path experiments/pretrained_models/GFPGANv1.pth --test_path inputs/cropped_faces --aligned
+    ```
 
 ## :computer: Training
 
@@ -94,6 +128,10 @@ You could improve it according to your own needs.
 
 > python -m torch.distributed.launch --nproc_per_node=4 --master_port=22021 train.py -opt train_gfpgan_v1.yml --launcher pytorch
 
+or load extensions just-in-time(JIT)
+
+> BASICSR_JIT=True 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
 
 GFPGAN is realeased under Apache License Version 2.0.