init

align_face.py

@@ -0,0 +1,140 @@
+"""
+brief: face alignment with FFHQ method (https://github.com/NVlabs/ffhq-dataset)
+author: lzhbrian (https://lzhbrian.me)
+date: 2020.1.5
+note: code is heavily borrowed from 
+    https://github.com/NVlabs/ffhq-dataset
+    http://dlib.net/face_landmark_detection.py.html
+
+requirements:
+    apt install cmake
+    conda install Pillow numpy scipy
+    pip install dlib
+    # download face landmark model from: 
+    # http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2
+"""
+
+import numpy as np
+import PIL
+import PIL.Image
+import sys
+import os
+import glob
+import scipy
+import scipy.ndimage
+import dlib
+
+
+# download model from: http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2
+predictor = dlib.shape_predictor('./shape_predictor_68_face_landmarks.dat')
+
+def get_landmark(filepath):
+    """get landmark with dlib
+    :return: np.array shape=(68, 2)
+    """
+    detector = dlib.get_frontal_face_detector()
+
+    img = dlib.load_rgb_image(filepath)
+    dets = detector(img, 1)
+
+    print("Number of faces detected: {}".format(len(dets)))
+    for k, d in enumerate(dets):
+        print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
+            k, d.left(), d.top(), d.right(), d.bottom()))
+        # Get the landmarks/parts for the face in box d.
+        shape = predictor(img, d)
+        print("Part 0: {}, Part 1: {} ...".format(shape.part(0), shape.part(1)))
+
+
+    t = list(shape.parts())
+    a = []
+    for tt in t:
+        a.append([tt.x, tt.y])
+    lm = np.array(a)
+    # lm is a shape=(68,2) np.array
+    return lm
+
+
+def align_face(filepath):
+    """
+    :param filepath: str
+    :return: PIL Image
+    """
+
+    lm = get_landmark(filepath)
+
+    lm_chin          = lm[0  : 17]  # left-right
+    lm_eyebrow_left  = lm[17 : 22]  # left-right
+    lm_eyebrow_right = lm[22 : 27]  # left-right
+    lm_nose          = lm[27 : 31]  # top-down
+    lm_nostrils      = lm[31 : 36]  # top-down
+    lm_eye_left      = lm[36 : 42]  # left-clockwise
+    lm_eye_right     = lm[42 : 48]  # left-clockwise
+    lm_mouth_outer   = lm[48 : 60]  # left-clockwise
+    lm_mouth_inner   = lm[60 : 68]  # left-clockwise
+
+    # Calculate auxiliary vectors.
+    eye_left     = np.mean(lm_eye_left, axis=0)
+    eye_right    = np.mean(lm_eye_right, axis=0)
+    eye_avg      = (eye_left + eye_right) * 0.5
+    eye_to_eye   = eye_right - eye_left
+    mouth_left   = lm_mouth_outer[0]
+    mouth_right  = lm_mouth_outer[6]
+    mouth_avg    = (mouth_left + mouth_right) * 0.5
+    eye_to_mouth = mouth_avg - eye_avg
+
+    # Choose oriented crop rectangle.
+    x = eye_to_eye - np.flipud(eye_to_mouth) * [-1, 1]
+    x /= np.hypot(*x)
+    x *= max(np.hypot(*eye_to_eye) * 2.0, np.hypot(*eye_to_mouth) * 1.8)
+    y = np.flipud(x) * [-1, 1]
+    c = eye_avg + eye_to_mouth * 0.1
+    quad = np.stack([c - x - y, c - x + y, c + x + y, c + x - y])
+    qsize = np.hypot(*x) * 2
+
+
+    # read image
+    img = PIL.Image.open(filepath)
+
+    output_size=1024
+    transform_size=4096
+    enable_padding=True
+
+    # Shrink.
+    shrink = int(np.floor(qsize / output_size * 0.5))
+    if shrink > 1:
+        rsize = (int(np.rint(float(img.size[0]) / shrink)), int(np.rint(float(img.size[1]) / shrink)))
+        img = img.resize(rsize, PIL.Image.ANTIALIAS)
+        quad /= shrink
+        qsize /= shrink
+
+    # Crop.
+    border = max(int(np.rint(qsize * 0.1)), 3)
+    crop = (int(np.floor(min(quad[:,0]))), int(np.floor(min(quad[:,1]))), int(np.ceil(max(quad[:,0]))), int(np.ceil(max(quad[:,1]))))
+    crop = (max(crop[0] - border, 0), max(crop[1] - border, 0), min(crop[2] + border, img.size[0]), min(crop[3] + border, img.size[1]))
+    if crop[2] - crop[0] < img.size[0] or crop[3] - crop[1] < img.size[1]:
+        img = img.crop(crop)
+        quad -= crop[0:2]
+
+    # Pad.
+    pad = (int(np.floor(min(quad[:,0]))), int(np.floor(min(quad[:,1]))), int(np.ceil(max(quad[:,0]))), int(np.ceil(max(quad[:,1]))))
+    pad = (max(-pad[0] + border, 0), max(-pad[1] + border, 0), max(pad[2] - img.size[0] + border, 0), max(pad[3] - img.size[1] + border, 0))
+    if enable_padding and max(pad) > border - 4:
+        pad = np.maximum(pad, int(np.rint(qsize * 0.3)))
+        img = np.pad(np.float32(img), ((pad[1], pad[3]), (pad[0], pad[2]), (0, 0)), 'reflect')
+        h, w, _ = img.shape
+        y, x, _ = np.ogrid[:h, :w, :1]
+        mask = np.maximum(1.0 - np.minimum(np.float32(x) / pad[0], np.float32(w-1-x) / pad[2]), 1.0 - np.minimum(np.float32(y) / pad[1], np.float32(h-1-y) / pad[3]))
+        blur = qsize * 0.02
+        img += (scipy.ndimage.gaussian_filter(img, [blur, blur, 0]) - img) * np.clip(mask * 3.0 + 1.0, 0.0, 1.0)
+        img += (np.median(img, axis=(0,1)) - img) * np.clip(mask, 0.0, 1.0)
+        img = PIL.Image.fromarray(np.uint8(np.clip(np.rint(img), 0, 255)), 'RGB')
+        quad += pad[:2]
+
+    # Transform.
+    img = img.transform((transform_size, transform_size), PIL.Image.QUAD, (quad + 0.5).flatten(), PIL.Image.BILINEAR)
+    if output_size < transform_size:
+        img = img.resize((output_size, output_size), PIL.Image.ANTIALIAS)
+
+    # Save aligned image.
+    return img

align_face_multi.py

@@ -0,0 +1,180 @@
+"""
+brief: face alignment with FFHQ method (https://github.com/NVlabs/ffhq-dataset)
+author: lzhbrian (https://lzhbrian.me)
+date: 2020.1.5
+note: code is heavily borrowed from 
+    https://github.com/NVlabs/ffhq-dataset
+    http://dlib.net/face_landmark_detection.py.html
+
+requirements:
+    apt install cmake
+    conda install Pillow numpy scipy
+    pip install dlib
+    # download face landmark model from: 
+    # http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2
+"""
+
+import numpy as np
+import PIL
+import PIL.Image
+import sys
+import os
+import glob
+import scipy
+import scipy.ndimage
+import dlib
+import argparse
+import multiprocessing
+
+
+# download model from: http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2
+# predictor = dlib.shape_predictor('./shape_predictor_68_face_landmarks.dat')
+
+def get_landmark(filepath):
+    """get landmark with dlib
+    :return: np.array shape=(68, 2)
+    """
+    detector = dlib.get_frontal_face_detector()
+
+    img = dlib.load_rgb_image(filepath)
+    dets = detector(img, 1)
+
+    print("Number of faces detected: {}".format(len(dets)))
+    for k, d in enumerate(dets):
+        print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
+            k, d.left(), d.top(), d.right(), d.bottom()))
+        # Get the landmarks/parts for the face in box d.
+        shape = predictor(img, d)
+        print("Part 0: {}, Part 1: {} ...".format(shape.part(0), shape.part(1)))
+
+
+    t = list(shape.parts())
+    a = []
+    for tt in t:
+        a.append([tt.x, tt.y])
+    lm = np.array(a)
+    # lm is a shape=(68,2) np.array
+    return lm
+
+
+def align_face(filepath):
+    """
+    :param filepath: str
+    :return: PIL Image
+    """
+
+    lm = get_landmark(filepath)
+
+    lm_chin          = lm[0  : 17]  # left-right
+    lm_eyebrow_left  = lm[17 : 22]  # left-right
+    lm_eyebrow_right = lm[22 : 27]  # left-right
+    lm_nose          = lm[27 : 31]  # top-down
+    lm_nostrils      = lm[31 : 36]  # top-down
+    lm_eye_left      = lm[36 : 42]  # left-clockwise
+    lm_eye_right     = lm[42 : 48]  # left-clockwise
+    lm_mouth_outer   = lm[48 : 60]  # left-clockwise
+    lm_mouth_inner   = lm[60 : 68]  # left-clockwise
+
+    # Calculate auxiliary vectors.
+    eye_left     = np.mean(lm_eye_left, axis=0)
+    eye_right    = np.mean(lm_eye_right, axis=0)
+    eye_avg      = (eye_left + eye_right) * 0.5
+    eye_to_eye   = eye_right - eye_left
+    mouth_left   = lm_mouth_outer[0]
+    mouth_right  = lm_mouth_outer[6]
+    mouth_avg    = (mouth_left + mouth_right) * 0.5
+    eye_to_mouth = mouth_avg - eye_avg
+
+    # Choose oriented crop rectangle.
+    x = eye_to_eye - np.flipud(eye_to_mouth) * [-1, 1]
+    x /= np.hypot(*x)
+    x *= max(np.hypot(*eye_to_eye) * 2.0, np.hypot(*eye_to_mouth) * 1.8)
+    y = np.flipud(x) * [-1, 1]
+    c = eye_avg + eye_to_mouth * 0.1
+    quad = np.stack([c - x - y, c - x + y, c + x + y, c + x - y])
+    qsize = np.hypot(*x) * 2
+
+
+    # read image
+    img = PIL.Image.open(filepath)
+
+    output_size=1024
+    transform_size=4096
+    enable_padding=True
+
+    # Shrink.
+    shrink = int(np.floor(qsize / output_size * 0.5))
+    if shrink > 1:
+        rsize = (int(np.rint(float(img.size[0]) / shrink)), int(np.rint(float(img.size[1]) / shrink)))
+        img = img.resize(rsize, PIL.Image.LANCZOS)
+        quad /= shrink
+        qsize /= shrink
+
+    # Crop.
+    border = max(int(np.rint(qsize * 0.1)), 3)
+    crop = (int(np.floor(min(quad[:,0]))), int(np.floor(min(quad[:,1]))), int(np.ceil(max(quad[:,0]))), int(np.ceil(max(quad[:,1]))))
+    crop = (max(crop[0] - border, 0), max(crop[1] - border, 0), min(crop[2] + border, img.size[0]), min(crop[3] + border, img.size[1]))
+    if crop[2] - crop[0] < img.size[0] or crop[3] - crop[1] < img.size[1]:
+        img = img.crop(crop)
+        quad -= crop[0:2]
+
+    # Pad.
+    pad = (int(np.floor(min(quad[:,0]))), int(np.floor(min(quad[:,1]))), int(np.ceil(max(quad[:,0]))), int(np.ceil(max(quad[:,1]))))
+    pad = (max(-pad[0] + border, 0), max(-pad[1] + border, 0), max(pad[2] - img.size[0] + border, 0), max(pad[3] - img.size[1] + border, 0))
+    if enable_padding and max(pad) > border - 4:
+        pad = np.maximum(pad, int(np.rint(qsize * 0.3)))
+        img = np.pad(np.float32(img), ((pad[1], pad[3]), (pad[0], pad[2]), (0, 0)), 'reflect')
+        h, w, _ = img.shape
+        y, x, _ = np.ogrid[:h, :w, :1]
+        mask = np.maximum(1.0 - np.minimum(np.float32(x) / pad[0], np.float32(w-1-x) / pad[2]), 1.0 - np.minimum(np.float32(y) / pad[1], np.float32(h-1-y) / pad[3]))
+        blur = qsize * 0.02
+        img += (scipy.ndimage.gaussian_filter(img, [blur, blur, 0]) - img) * np.clip(mask * 3.0 + 1.0, 0.0, 1.0)
+        img += (np.median(img, axis=(0,1)) - img) * np.clip(mask, 0.0, 1.0)
+        img = PIL.Image.fromarray(np.uint8(np.clip(np.rint(img), 0, 255)), 'RGB')
+        quad += pad[:2]
+
+    # Transform.
+    img = img.transform((transform_size, transform_size), PIL.Image.QUAD, (quad + 0.5).flatten(), PIL.Image.BILINEAR)
+    if output_size < transform_size:
+        img = img.resize((output_size, output_size), PIL.Image.LANCZOS)
+
+    # Save aligned image.
+    return img
+
+def arg_parser():
+    parser = argparse.ArgumentParser(description='align face')
+    parser.add_argument('--input_dir', type=str, required=True, help='input directory')
+    parser.add_argument('--output_dir', type=str, default=None, help='output directory')
+    parser.add_argument('--num_workers', type=int, default=4, help='number of workers')
+    parser.add_argument('--predictor_path', type=str, default='./shape_predictor_68_face_landmarks.dat', help='path to dlib predictor')
+    return parser
+
+if __name__ == "__main__":
+    IMG_EXTENSIONS = ['.jpg', '.jpeg', '.png', '.JPG', '.JPEG', '.PNG']
+    parser = arg_parser()
+    args = parser.parse_args()
+    input_dir = args.input_dir
+    output_dir = args.output_dir if args.output_dir else os.path.join(input_dir, 'aligned')
+    os.makedirs(output_dir, exist_ok=True)
+    num_workers = args.num_workers
+    predictor_path = args.predictor_path
+    predictor = dlib.shape_predictor(predictor_path)
+
+    input_images = []
+    # walk through input_dir
+    for root, _, fnames in sorted(os.walk(input_dir)):
+        for fname in sorted(fnames):
+            if any(fname.endswith(extension) for extension in IMG_EXTENSIONS):
+                path = os.path.join(root, fname)
+                input_images.append(path)
+
+    # align face
+    def align_face_worker(filepath):
+        # print(filepath)
+        img = align_face(filepath)
+        img.save(os.path.join(output_dir, os.path.basename(filepath)))
+
+    with multiprocessing.Pool(num_workers) as p:
+        p.map(align_face_worker, input_images)
+
+    print('done')

env.yml

@@ -0,0 +1,55 @@
+name: ffhq_align_face
+channels:
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=main
+  - _openmp_mutex=5.1=1_gnu
+  - blas=1.0=mkl
+  - bzip2=1.0.8=h7b6447c_0
+  - ca-certificates=2023.12.12=h06a4308_0
+  - freetype=2.12.1=h4a9f257_0
+  - giflib=5.2.1=h5eee18b_3
+  - intel-openmp=2023.1.0=hdb19cb5_46306
+  - jpeg=9e=h5eee18b_1
+  - lcms2=2.12=h3be6417_0
+  - ld_impl_linux-64=2.38=h1181459_1
+  - lerc=3.0=h295c915_0
+  - libdeflate=1.17=h5eee18b_1
+  - libffi=3.4.4=h6a678d5_0
+  - libgcc-ng=11.2.0=h1234567_1
+  - libgfortran-ng=11.2.0=h00389a5_1
+  - libgfortran5=11.2.0=h1234567_1
+  - libgomp=11.2.0=h1234567_1
+  - libpng=1.6.39=h5eee18b_0
+  - libstdcxx-ng=11.2.0=h1234567_1
+  - libtiff=4.5.1=h6a678d5_0
+  - libuuid=1.41.5=h5eee18b_0
+  - libwebp=1.3.2=h11a3e52_0
+  - libwebp-base=1.3.2=h5eee18b_0
+  - lz4-c=1.9.4=h6a678d5_0
+  - mkl=2023.1.0=h213fc3f_46344
+  - mkl-service=2.4.0=py310h5eee18b_1
+  - mkl_fft=1.3.8=py310h5eee18b_0
+  - mkl_random=1.2.4=py310hdb19cb5_0
+  - ncurses=6.4=h6a678d5_0
+  - numpy=1.26.3=py310h5f9d8c6_0
+  - numpy-base=1.26.3=py310hb5e798b_0
+  - openjpeg=2.4.0=h3ad879b_0
+  - openssl=3.0.13=h7f8727e_0
+  - pillow=10.0.1=py310ha6cbd5a_0
+  - pip=23.3.1=py310h06a4308_0
+  - python=3.10.13=h955ad1f_0
+  - readline=8.2=h5eee18b_0
+  - scipy=1.11.4=py310h5f9d8c6_0
+  - setuptools=68.2.2=py310h06a4308_0
+  - sqlite=3.41.2=h5eee18b_0
+  - tbb=2021.8.0=hdb19cb5_0
+  - tk=8.6.12=h1ccaba5_0
+  - tzdata=2023d=h04d1e81_0
+  - wheel=0.41.2=py310h06a4308_0
+  - xz=5.4.5=h5eee18b_0
+  - zlib=1.2.13=h5eee18b_0
+  - zstd=1.5.5=hc292b87_0
+  - pip:
+      - dlib==19.24.2
+prefix: /playpen-nas-ssd/luchao/software/miniconda3/envs/ffhq_align_face

shape_predictor_68_face_landmarks.dat

@@ -0,0 +1 @@
+/playpen-nas-ssd/luchao/pretrained_weights/dlib/shape_predictor_68_face_landmarks.dat