Files
faceswap_pytorch/dataset/training_data.py
2019-02-01 15:30:41 +08:00

62 lines
2.4 KiB
Python

import numpy
from utils.umeyama import umeyama
import cv2
random_transform_args = {
'rotation_range': 10,
'zoom_range': 0.05,
'shift_range': 0.05,
'random_flip': 0.4,
}
def random_transform(image, rotation_range, zoom_range, shift_range, random_flip):
h, w = image.shape[0:2]
rotation = numpy.random.uniform(-rotation_range, rotation_range)
scale = numpy.random.uniform(1 - zoom_range, 1 + zoom_range)
tx = numpy.random.uniform(-shift_range, shift_range) * w
ty = numpy.random.uniform(-shift_range, shift_range) * h
mat = cv2.getRotationMatrix2D((w // 2, h // 2), rotation, scale)
mat[:, 2] += (tx, ty)
result = cv2.warpAffine(image, mat, (w, h), borderMode=cv2.BORDER_REPLICATE)
if numpy.random.random() < random_flip:
result = result[:, ::-1]
return result
# get pair of random warped images from aligened face image
def random_warp(image):
assert image.shape == (256, 256, 3)
range_ = numpy.linspace(128 - 80, 128 + 80, 5)
mapx = numpy.broadcast_to(range_, (5, 5))
mapy = mapx.T
mapx = mapx + numpy.random.normal(size=(5, 5), scale=5)
mapy = mapy + numpy.random.normal(size=(5, 5), scale=5)
interp_mapx = cv2.resize(mapx, (80, 80))[8:72, 8:72].astype('float32')
interp_mapy = cv2.resize(mapy, (80, 80))[8:72, 8:72].astype('float32')
# just crop the image, remove the top left bottom right 8 pixels (in order to get the pure face)
warped_image = cv2.remap(image, interp_mapx, interp_mapy, cv2.INTER_LINEAR)
src_points = numpy.stack([mapx.ravel(), mapy.ravel()], axis=-1)
dst_points = numpy.mgrid[0:65:16, 0:65:16].T.reshape(-1, 2)
mat = umeyama(src_points, dst_points, True)[0:2]
target_image = cv2.warpAffine(image, mat, (64, 64))
return warped_image, target_image
def get_training_data(images, batch_size):
indices = numpy.random.randint(len(images), size=batch_size)
for i, index in enumerate(indices):
image = images[index]
image = random_transform(image, **random_transform_args)
warped_img, target_img = random_warp(image)
if i == 0:
warped_images = numpy.empty((batch_size,) + warped_img.shape, warped_img.dtype)
target_images = numpy.empty((batch_size,) + target_img.shape, warped_img.dtype)
warped_images[i] = warped_img
target_images[i] = target_img
return warped_images, target_images