ffhq

ffhq_dataset/README.md

@@ -0,0 +1,6 @@
+Download *shape_predictor_68_face_landmarks.dat* here 
+
+```bash
+wget http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2
+bzip2 -dk shape_predictor_68_face_landmarks.dat.bz2
+```

ffhq_dataset/face_alignment.py

@@ -0,0 +1,81 @@
+import numpy as np
+import scipy.ndimage
+import os
+import PIL.Image
+
+
+def image_align(image, face_landmarks, output_size=1024, transform_size=4096, enable_padding=True):
+        # Align function from FFHQ dataset pre-processing step
+        # https://github.com/NVlabs/ffhq-dataset/blob/master/download_ffhq.py
+
+        lm = np.array(face_landmarks)
+        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
+
+        img = PIL.Image.fromarray(image)
+
+        # 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 = np.uint8(np.clip(np.rint(img), 0, 255))
+            img = PIL.Image.fromarray(img, '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)
+
+        img_np = np.array(img)
+        return img_np

ffhq_dataset/gen_aligned_image.py

@@ -0,0 +1,24 @@
+import os
+
+from .face_alignment import image_align
+from .landmarks_detector import LandmarksDetector
+
+
+cur_dir = os.path.split(os.path.realpath(__file__))[0]
+model_path = os.path.join(cur_dir, 'shape_predictor_68_face_landmarks.dat')
+
+
+class FaceAlign:
+    def __init__(self, predictor_model_path=model_path):
+        self.landmarks_detector = LandmarksDetector(predictor_model_path)
+
+    def get_crop_image(self, image):
+        lms = []
+        for i, face_landmarks in enumerate(self.landmarks_detector.get_landmarks(image), start=1):
+            lms.append(face_landmarks)
+        if len(lms) < 1:
+            return None
+        out_image = image_align(image, lms[0])
+
+        return out_image
+

ffhq_dataset/landmarks_detector.py

@@ -0,0 +1,22 @@
+import dlib
+import cv2
+
+
+class LandmarksDetector:
+    def __init__(self, predictor_model_path):
+        """
+        :param predictor_model_path: path to shape_predictor_68_face_landmarks.dat file
+        """
+        self.detector = dlib.get_frontal_face_detector()
+        self.shape_predictor = dlib.shape_predictor(predictor_model_path)
+
+    def get_landmarks(self, image):
+        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+        dets = self.detector(gray, 1)
+
+        for detection in dets:
+            try:
+                face_landmarks = [(item.x, item.y) for item in self.shape_predictor(gray, detection).parts()]
+                yield face_landmarks
+            except:
+                print("Exception in get_landmarks()!")