inference_codeformer.py

import os
import cv2
import argparse
import glob
import torch
from torchvision.transforms.functional import normalize
from basicsr.utils import imwrite, img2tensor, tensor2img
from basicsr.utils.download_util import load_file_from_url
from facelib.utils.face_restoration_helper import FaceRestoreHelper
from facelib.utils.misc import is_gray
import torch.nn.functional as F

from basicsr.utils.registry import ARCH_REGISTRY

pretrain_model_url = {
    'restoration': 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth',
}

def set_realesrgan():
    from basicsr.archs.rrdbnet_arch import RRDBNet
    from basicsr.utils.realesrgan_utils import RealESRGANer

    cuda_is_available = torch.cuda.is_available()
    half = True if cuda_is_available else False
    model = RRDBNet(
        num_in_ch=3,
        num_out_ch=3,
        num_feat=64,
        num_block=23,
        num_grow_ch=32,
        scale=2,
    )
    upsampler = RealESRGANer(
        scale=2,
        model_path="https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/RealESRGAN_x2plus.pth",
        model=model,
        tile=args.bg_tile,
        tile_pad=40,
        pre_pad=0,
        half=half, # need to set False in CPU mode
    )

    if not cuda_is_available:  # CPU
        import warnings
        warnings.warn('Running on CPU now! Make sure your PyTorch version matches your CUDA.'
                        'The unoptimized RealESRGAN is slow on CPU. '
                        'If you want to disable it, please remove `--bg_upsampler` and `--face_upsample` in command.',
                        category=RuntimeWarning)
    return upsampler

if __name__ == '__main__':
    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
    parser = argparse.ArgumentParser()

    parser.add_argument('--w', type=float, default=0.5, help='Balance the quality and fidelity')
    parser.add_argument('--upscale', type=int, default=2, help='The final upsampling scale of the image. Default: 2')
    parser.add_argument('--test_path', type=str, default='./inputs/cropped_faces')
    parser.add_argument('--has_aligned', action='store_true', help='Input are cropped and aligned faces')
    parser.add_argument('--only_center_face', action='store_true', help='Only restore the center face')
    # large det_model: 'YOLOv5l', 'retinaface_resnet50'
    # small det_model: 'YOLOv5n', 'retinaface_mobile0.25'
    parser.add_argument('--detection_model', type=str, default='retinaface_resnet50')
    parser.add_argument('--draw_box', action='store_true')
    parser.add_argument('--bg_upsampler', type=str, default='None', help='background upsampler. Optional: realesrgan')
    parser.add_argument('--face_upsample', action='store_true', help='face upsampler after enhancement.')
    parser.add_argument('--bg_tile', type=int, default=400, help='Tile size for background sampler. Default: 400')
    parser.add_argument('--save_video_fps', type=int, default=24, help='frame rate for saving video. Default: 24')

    args = parser.parse_args()

    # ------------------------ input & output ------------------------
    w = args.w
    if args.test_path.endswith(('jpg', 'png')): # input single img path
        input_img_list = [args.test_path]
        result_root = f'results/test_img_{w}'
    elif args.test_path.endswith(('mp4', 'mov', 'avi')): # input video path
        input_img_list = []
        vidcap = cv2.VideoCapture(args.test_path)
        success, image = vidcap.read()
        while success:
            input_img_list.append(image)
            success, image = vidcap.read()
        input_video = True
        video_name = os.path.basename(args.test_path)[:-4]
        result_root = f'results/{video_name}_{w}'
    else: # input img folder
        if args.test_path.endswith('/'):  # solve when path ends with /
            args.test_path = args.test_path[:-1]
        # scan all the jpg and png images
        input_img_list = sorted(glob.glob(os.path.join(args.test_path, '*.[jp][pn]g')))
        result_root = f'results/{os.path.basename(args.test_path)}_{w}'
    
    test_img_num = len(input_img_list)
    # ------------------ set up background upsampler ------------------
    if args.bg_upsampler == 'realesrgan':
        bg_upsampler = set_realesrgan()
    else:
        bg_upsampler = None

    # ------------------ set up face upsampler ------------------
    if args.face_upsample:
        face_upsampler = None
        # if bg_upsampler is not None:
        #     face_upsampler = bg_upsampler
        # else:
        #     face_upsampler = set_realesrgan()
    else:
        face_upsampler = None

    # ------------------ set up CodeFormer restorer -------------------
    net = ARCH_REGISTRY.get('CodeFormer')(dim_embd=512, codebook_size=1024, n_head=8, n_layers=9, 
                                            connect_list=['32', '64', '128', '256']).to(device)
    
    # ckpt_path = 'weights/CodeFormer/codeformer.pth'
    ckpt_path = load_file_from_url(url=pretrain_model_url['restoration'], 
                                    model_dir='weights/CodeFormer', progress=True, file_name=None)
    checkpoint = torch.load(ckpt_path)['params_ema']
    net.load_state_dict(checkpoint)
    net.eval()

    # ------------------ set up FaceRestoreHelper -------------------
    # large det_model: 'YOLOv5l', 'retinaface_resnet50'
    # small det_model: 'YOLOv5n', 'retinaface_mobile0.25'
    if not args.has_aligned: 
        print(f'Face detection model: {args.detection_model}')
    if bg_upsampler is not None: 
        print(f'Background upsampling: True, Face upsampling: {args.face_upsample}')
    else:
        print(f'Background upsampling: False, Face upsampling: {args.face_upsample}')

    face_helper = FaceRestoreHelper(
        args.upscale,
        face_size=512,
        crop_ratio=(1, 1),
        det_model = args.detection_model,
        save_ext='png',
        use_parse=True,
        device=device)

    # -------------------- start to processing ---------------------
    for i, img_path in enumerate(input_img_list):
        # clean all the intermediate results to process the next image
        face_helper.clean_all()
        
        if isinstance(img_path, str):
            img_name = os.path.basename(img_path)
            basename, ext = os.path.splitext(img_name)
            print(f'[{i+1}/{test_img_num}] Processing: {img_name}')
            img = cv2.imread(img_path, cv2.IMREAD_COLOR)
        else: # for video processing
            basename = str(i).zfill(6)
            img_name = f'{video_name}_{basename}' if input_video else basename
            print(f'[{i+1}/{test_img_num}] Processing: {img_name}')
            img = img_path

        if args.has_aligned: 
            # the input faces are already cropped and aligned
            img = cv2.resize(img, (512, 512), interpolation=cv2.INTER_LINEAR)
            face_helper.is_gray = is_gray(img, threshold=5)
            if face_helper.is_gray:
                print('Grayscale input: True')
            face_helper.cropped_faces = [img]
        else:
            face_helper.read_image(img)
            # get face landmarks for each face
            num_det_faces = face_helper.get_face_landmarks_5(
                only_center_face=args.only_center_face, resize=640, eye_dist_threshold=5)
            print(f'\tdetect {num_det_faces} faces')
            # align and warp each face
            face_helper.align_warp_face()

        # face restoration for each cropped face
        for idx, cropped_face in enumerate(face_helper.cropped_faces):
            # prepare data
            cropped_face_t = img2tensor(cropped_face / 255., bgr2rgb=True, float32=True)
            normalize(cropped_face_t, (0.5, 0.5, 0.5), (0.5, 0.5, 0.5), inplace=True)
            cropped_face_t = cropped_face_t.unsqueeze(0).to(device)

            try:
                with torch.no_grad():
                    output = net(cropped_face_t, w=w, adain=True)[0]
                    restored_face = tensor2img(output, rgb2bgr=True, min_max=(-1, 1))
                del output
                torch.cuda.empty_cache()
            except Exception as error:
                print(f'\tFailed inference for CodeFormer: {error}')
                restored_face = tensor2img(cropped_face_t, rgb2bgr=True, min_max=(-1, 1))

            restored_face = restored_face.astype('uint8')
            face_helper.add_restored_face(restored_face)

        # paste_back
        if not args.has_aligned:
            # upsample the background
            if bg_upsampler is not None:
                # Now only support RealESRGAN for upsampling background
                bg_img = bg_upsampler.enhance(img, outscale=args.upscale)[0]
            else:
                bg_img = None
            face_helper.get_inverse_affine(None)
            # paste each restored face to the input image
            if args.face_upsample and face_upsampler is not None: 
                restored_img = face_helper.paste_faces_to_input_image(upsample_img=bg_img, draw_box=args.draw_box, face_upsampler=face_upsampler)
            else:
                restored_img = face_helper.paste_faces_to_input_image(upsample_img=bg_img, draw_box=args.draw_box)

        # save faces
        for idx, (cropped_face, restored_face) in enumerate(zip(face_helper.cropped_faces, face_helper.restored_faces)):
            # save cropped face
            if not args.has_aligned: 
                save_crop_path = os.path.join(result_root, 'cropped_faces', f'{basename}_{idx:02d}.png')
                imwrite(cropped_face, save_crop_path)
            # save restored face
            if args.has_aligned:
                save_face_name = f'{basename}.png'
            else:
                save_face_name = f'{basename}_{idx:02d}.png'
            save_restore_path = os.path.join(result_root, 'restored_faces', save_face_name)
            imwrite(restored_face, save_restore_path)

        # save restored img
        if not args.has_aligned and restored_img is not None:
            save_restore_path = os.path.join(result_root, 'final_results', f'{basename}.png')
            imwrite(restored_img, save_restore_path)

    # save enhanced video
    if input_video:
        # load images
        video_frames = []
        img_list = sorted(glob.glob(os.path.join(result_root, 'final_results', '*.[jp][pn]g')))
        for img_path in img_list:
            img = cv2.imread(img_path)
            video_frames.append(img)
        # write images to video
        h, w = video_frames[0].shape[:2]
        save_restore_path = os.path.join(result_root, f'{video_name}.mp4')
        writer = cv2.VideoWriter(save_restore_path, cv2.VideoWriter_fourcc(*"mp4v"),
                                    args.save_video_fps, (w, h))            
        for f in video_frames:
            writer.write(f)
        writer.release()

    print(f'\nAll results are saved in {result_root}')