Spaces:
Sleeping
Sleeping
File size: 4,198 Bytes
a891a57 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 |
# -*- coding: utf-8 -*-
# @Organization : insightface.ai
# @Author : Jia Guo
# @Time : 2021-05-04
# @Function :
from __future__ import division
import numpy as np
import cv2
import onnx
import onnxruntime
from ..utils import face_align
from ..utils import transform
from ..data import get_object
__all__ = [
'Landmark',
]
class Landmark:
def __init__(self, model_file=None, session=None):
assert model_file is not None
self.model_file = model_file
self.session = session
find_sub = False
find_mul = False
model = onnx.load(self.model_file)
graph = model.graph
for nid, node in enumerate(graph.node[:8]):
#print(nid, node.name)
if node.name.startswith('Sub') or node.name.startswith('_minus'):
find_sub = True
if node.name.startswith('Mul') or node.name.startswith('_mul'):
find_mul = True
if nid<3 and node.name=='bn_data':
find_sub = True
find_mul = True
if find_sub and find_mul:
#mxnet arcface model
input_mean = 0.0
input_std = 1.0
else:
input_mean = 127.5
input_std = 128.0
self.input_mean = input_mean
self.input_std = input_std
#print('input mean and std:', model_file, self.input_mean, self.input_std)
if self.session is None:
self.session = onnxruntime.InferenceSession(self.model_file, None)
input_cfg = self.session.get_inputs()[0]
input_shape = input_cfg.shape
input_name = input_cfg.name
self.input_size = tuple(input_shape[2:4][::-1])
self.input_shape = input_shape
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
assert len(self.output_names)==1
output_shape = outputs[0].shape
self.require_pose = False
#print('init output_shape:', output_shape)
if output_shape[1]==3309:
self.lmk_dim = 3
self.lmk_num = 68
self.mean_lmk = get_object('meanshape_68.pkl')
self.require_pose = True
else:
self.lmk_dim = 2
self.lmk_num = output_shape[1]//self.lmk_dim
self.taskname = 'landmark_%dd_%d'%(self.lmk_dim, self.lmk_num)
def prepare(self, ctx_id, **kwargs):
if ctx_id<0:
self.session.set_providers(['CPUExecutionProvider'])
def get(self, img, face):
bbox = face.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)
#print('param:', img.shape, bbox, center, self.input_size, _scale, rotate)
aimg, M = face_align.transform(img, center, self.input_size[0], _scale, rotate)
input_size = tuple(aimg.shape[0:2][::-1])
#assert input_size==self.input_size
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]
if pred.shape[0] >= 3000:
pred = pred.reshape((-1, 3))
else:
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)
if pred.shape[1] == 3:
pred[:, 2] *= (self.input_size[0] // 2)
IM = cv2.invertAffineTransform(M)
pred = face_align.trans_points(pred, IM)
face[self.taskname] = pred
if self.require_pose:
P = transform.estimate_affine_matrix_3d23d(self.mean_lmk, pred)
s, R, t = transform.P2sRt(P)
rx, ry, rz = transform.matrix2angle(R)
pose = np.array( [rx, ry, rz], dtype=np.float32 )
face['pose'] = pose #pitch, yaw, roll
return pred
|