utils.py

from PIL import Image
import torch
import numpy as np
import dlib
import scipy

def image_grid(imgs, rows, cols):
    assert len(imgs) == rows*cols

    w, h = imgs[0].size
    grid = Image.new('RGB', size=(cols*w, rows*h))
    grid_w, grid_h = grid.size
    
    for i, img in enumerate(imgs):
        grid.paste(img, box=(i%cols*w, i//cols*h))
    return grid


def get_generator(seed, device):

    if seed is not None:
        if isinstance(seed, list):
            generator = [
                torch.Generator(device).manual_seed(seed_item) for seed_item in seed
            ]
        else:
            generator = torch.Generator(device).manual_seed(seed)
    else:
        generator = None

    return generator

def get_landmark_pil(pil_image, predictor, detector):
    """Get 68 facial landmarks as a NumPy array of shape (68, 2)."""
    img_np = np.array(pil_image.convert("RGB"))
    dets = detector(img_np, 1)
    if not dets:
        return None
    # Handle mmod or frontal detector output
    det = dets[0].rect if hasattr(dets[0], 'rect') else dets[0]
    shape = predictor(img_np, det)
    coords = [(pt.x, pt.y) for pt in shape.parts()]
    return np.array(coords)


def align_face(pil_image, predictor, detector):
    """Align a face from a PIL.Image, returning an aligned PIL.Image of size 512x512."""
    lm = get_landmark_pil(pil_image, predictor, detector)
    if lm is None:
        return pil_image
    # Define landmark regions
    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   

    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

    # Compute oriented crop
    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

    # Prepare image
    img = pil_image.convert("RGB")
    transform_size = 512
    output_size = 512
    enable_padding = True

    # Shrink image for speed
    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, Image.Resampling.LANCZOS)
        quad /= shrink
        qsize /= shrink

    # Crop around face
    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 = Image.fromarray(np.uint8(np.clip(np.rint(img), 0, 255)), 'RGB')
        quad += pad[:2]

    # Transform image
    img = img.transform((transform_size, transform_size), Image.QUAD, (quad + 0.5).flatten(), Image.BILINEAR)
    if output_size < transform_size:
        img = img.resize((output_size, output_size), Image.Resampling.LANCZOS)

    # Resize to final output
    return img