Spaces:
Paused
Paused
| # insightface | |
| from __future__ import division | |
| import onnxruntime | |
| import cv2 | |
| import numpy as np | |
| from skimage import transform as trans | |
| def transform(data, center, output_size, scale, rotation): | |
| scale_ratio = scale | |
| rot = float(rotation) * np.pi / 180.0 | |
| t1 = trans.SimilarityTransform(scale=scale_ratio) | |
| cx = center[0] * scale_ratio | |
| cy = center[1] * scale_ratio | |
| t2 = trans.SimilarityTransform(translation=(-1 * cx, -1 * cy)) | |
| t3 = trans.SimilarityTransform(rotation=rot) | |
| t4 = trans.SimilarityTransform(translation=(output_size / 2, | |
| output_size / 2)) | |
| t = t1 + t2 + t3 + t4 | |
| M = t.params[0:2] | |
| cropped = cv2.warpAffine(data, | |
| M, (output_size, output_size), | |
| borderValue=0.0) | |
| return cropped, M | |
| def trans_points2d(pts, M): | |
| new_pts = np.zeros(shape=pts.shape, dtype=np.float32) | |
| for i in range(pts.shape[0]): | |
| pt = pts[i] | |
| new_pt = np.array([pt[0], pt[1], 1.], dtype=np.float32) | |
| new_pt = np.dot(M, new_pt) | |
| new_pts[i] = new_pt[0:2] | |
| return new_pts | |
| class Landmark106: | |
| def __init__(self, model_file, device="cuda"): | |
| if device == "cuda": | |
| providers = ["CUDAExecutionProvider", "CPUExecutionProvider"] | |
| else: | |
| providers = ["CPUExecutionProvider"] | |
| self.session = onnxruntime.InferenceSession(model_file, providers=providers) | |
| self.input_mean = 0.0 | |
| self.input_std = 1.0 | |
| self.input_size = (192, 192) | |
| input_cfg = self.session.get_inputs()[0] | |
| input_name = input_cfg.name | |
| outputs = self.session.get_outputs() | |
| output_names = [] | |
| for out in outputs: | |
| output_names.append(out.name) | |
| self.input_name = input_name | |
| self.output_names = output_names | |
| self.lmk_num = 106 | |
| def get(self, img, bbox): | |
| w, h = (bbox[2] - bbox[0]), (bbox[3] - bbox[1]) | |
| center = (bbox[2] + bbox[0]) / 2, (bbox[3] + bbox[1]) / 2 | |
| rotate = 0 | |
| _scale = self.input_size[0] / (max(w, h)*1.5) | |
| aimg, M = transform(img, center, self.input_size[0], _scale, rotate) | |
| input_size = tuple(aimg.shape[0:2][::-1]) | |
| blob = cv2.dnn.blobFromImage(aimg, 1.0/self.input_std, input_size, (self.input_mean, self.input_mean, self.input_mean), swapRB=True) | |
| pred = self.session.run(self.output_names, {self.input_name : blob})[0][0] | |
| pred = pred.reshape((-1, 2)) | |
| if self.lmk_num < pred.shape[0]: | |
| pred = pred[self.lmk_num*-1:,:] | |
| pred[:, 0:2] += 1 | |
| pred[:, 0:2] *= (self.input_size[0] // 2) | |
| IM = cv2.invertAffineTransform(M) | |
| pred = trans_points2d(pred, IM) | |
| return pred | |