def discrim_l2(self, y, y_, step):
"""
facial semantic feature loss
evaluate loss use l1 at pixel space
:param y: input photo, numpy array [H, W, C]
:param y_: generated image, tensor [B, C, W, H]
:param step: train step
:return: l1 loss in pixel space
"""
img1 = parse_evaluate(y.astype(np.uint8),
cp=self.parsing,
cuda=self.cuda)
y_ = y_.cpu().detach().numpy()
y_ = np.squeeze(y_, axis=0)
y_ = np.swapaxes(y_, 0, 2) * 255
img2 = parse_evaluate(y_.astype(np.uint8),
cp=self.parsing,
cuda=self.cuda)
edge_img1 = utils.img_edge(img1).astype(np.float32)
edge_img2 = utils.img_edge(img2).astype(np.float32)
w_g = 1.0
w_r = 1.0
if step % self.args.eval_prev_freq == 0:
path = os.path.join(self.prev_path, "l2_{0}.jpg".format(step))
edge1_v3 = 255. - ops.fill_grey(edge_img1)
edge2_v3 = 255. - ops.fill_grey(edge_img2)
merge = ops.merge_4image(y,
y_,
edge1_v3,
edge2_v3,
transpose=False)
cv2.imwrite(path, merge)
return np.mean(np.abs(w_r * edge_img1 - w_g * edge_img2))
def process_item(self, path, save, cuda):
"""
预处理 change database to 64x64 edge pictures
:param path: 图片路径 512x512
:param save: 是否将处理好的图片保存本地
:param cuda: gpu speedup
"""
# log.info(path)
img = utils.evalute_face(path, self.args.parsing_checkpoint, cuda)
img = utils.img_edge(img)
if img.shape[0] != 64:
img = cv2.resize(img, (64, 64), interpolation=cv2.INTER_AREA)
if save:
cv2.imwrite(path, img)
return img
def capture(path, tensor1, tensor2, parse, cuda):
"""
imitator 快照
:param cuda: use gpu
:param path: save path
:param tensor1: input photo
:param tensor2: generated image
:param parse: parse checkpoint's path
"""
img1 = ops.tensor_2_image(tensor1)[0].swapaxes(0, 1).astype(np.uint8)
img2 = ops.tensor_2_image(tensor2)[0].swapaxes(0, 1).astype(np.uint8)
img1 = cv2.resize(img1, (512, 512), interpolation=cv2.INTER_LINEAR)
img3 = utils.faceparsing_ndarray(img1, parse, cuda)
img4 = utils.img_edge(img3)
img4 = 255 - ops.fill_gray(img4)
image = ops.merge_4image(img1, img2, img3, img4, transpose=False)
cv2.imwrite(path, image)
def inference(self, cp_name, photo_path, cuda):
"""
feature extractor: 由图片生成捏脸参数
:param cuda: gpu speed up
:param cp_name: checkpoint's path
:param photo_path: input photo's path
:return: params [1, params_cnt]
"""
img = cv2.imread(photo_path)
scaled = align.align_face(img, size=(64, 64))
self.load_checkpoint(cp_name, training=False, cuda=cuda)
img = utils.faceparsing_ndarray(scaled, self.args.parsing_checkpoint, cuda)
img = utils.img_edge(img)
with torch.no_grad:
input = torch.from_numpy(img)
input = input.view([1, 1, 64, 64])
params_ = self(input)
log.info(params_)
return params_
elif args.phase == "faceparsing":
log.info("faceparsing")
im = utils.evalute_face("./output/face/db_0000_3.jpg",
args.parsing_checkpoint, cuda)
cv2.imwrite("./output/eval.jpg", im)
elif args.phase == "align":
path = '../export/star'
for file in os.listdir(path):
p = os.path.join(path, file)
log.info(p)
p2 = os.path.join(path, "a-" + file)
al = align.face_features(p, p2)
ev = utils.parse_evaluate(al, args.parsing_checkpoint, cuda=cuda)
p = os.path.join(path, "b-" + file)
cv2.imwrite(p, ev)
ev = 255 - utils.img_edge(ev)
p = os.path.join(path, "c-" + file)
cv2.imwrite(p, ev)
elif args.phase == "dataset":
dataset = FaceDataset(args, "test")
dataset.pre_process(cuda)
elif args.phase == "preview":
log.info("preview picture")
path = "../export/regular/model.jpg"
img = cv2.imread(path)
img2 = utils.parse_evaluate(img, args.parsing_checkpoint, cuda)
img3 = utils.img_edge(img2)
img3_ = ops.fill_grey(img3)
img4 = align.face_features(path)
log.info("{0} {1} {2} {3}".format(img.shape, img2.shape, img3_.shape,
img4.shape))
def image_transfer(self, im_path):
if im_path.find('.jpg') >= 0:
img = utils.evalute_face(im_path, self.cp, False)
img = utils.img_edge(img)
img = cv2.resize(img, (64, 64), interpolation=cv2.INTER_AREA)
cv2.imwrite(im_path, img)
for file in os.listdir(path):
p = os.path.join(path, file)
log.info(p)
p2 = os.path.join(path, "a_" + file)
al = align.face_features(p, p2)
ev = utils.faceparsing_ndarray(al,
args.parsing_checkpoint,
cuda=cuda)
elif args.phase == "dataset":
dataset = FaceDataset(args, "test")
dataset.pre_process(cuda)
elif args.phase == "preview":
log.info("preview picture")
path = "../export/regular/model.jpg"
img = cv2.imread(path)
img2 = utils.faceparsing_ndarray(img, args.parsing_checkpoint, cuda)
img3 = utils.img_edge(img2)
img3_ = ops.fill_gray(img3)
img4 = align.face_features(path)
log.info("{0} {1} {2} {3}".format(img.shape, img2.shape, img3_.shape,
img4.shape))
ops.merge_4image(img, img2, img3_, img4, show=True)
elif args.phase == "evaluate":
log.info("evaluation mode start")
evl = Evaluate(args, cuda=cuda)
img = cv2.imread(args.eval_image).astype(np.float32)
x_ = evl.itr_train(img)
evl.output(x_, img)
else:
log.error("not known phase %s", args.phase)
