File size: 10,732 Bytes
89cf463 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 |
import numpy as np
import os.path as osp
import cv2
import onnxruntime # gpu
import os
def softmax(z):
assert len(z.shape) == 2
s = np.max(z, axis=1)
s = s[:, np.newaxis] # necessary step to do broadcasting
e_x = np.exp(z - s)
div = np.sum(e_x, axis=1)
div = div[:, np.newaxis] # dito
return e_x / div
def distance2bbox(points, distance, max_shape=None):
"""Decode distance prediction to bounding box.
Args:
points (Tensor): Shape (n, 2), [x, y].
distance (Tensor): Distance from the given point to 4
boundaries (left, top, right, bottom).
max_shape (tuple): Shape of the image.
Returns:
Tensor: Decoded bboxes.
"""
x1 = points[:, 0] - distance[:, 0]
y1 = points[:, 1] - distance[:, 1]
x2 = points[:, 0] + distance[:, 2]
y2 = points[:, 1] + distance[:, 3]
if max_shape is not None:
x1 = x1.clamp(min=0, max=max_shape[1])
y1 = y1.clamp(min=0, max=max_shape[0])
x2 = x2.clamp(min=0, max=max_shape[1])
y2 = y2.clamp(min=0, max=max_shape[0])
return np.stack([x1, y1, x2, y2], axis=-1)
def distance2kps(points, distance, max_shape=None):
"""Decode distance prediction to bounding box.
Args:
points (Tensor): Shape (n, 2), [x, y].
distance (Tensor): Distance from the given point to 4
boundaries (left, top, right, bottom).
max_shape (tuple): Shape of the image.
Returns:
Tensor: Decoded bboxes.
"""
preds = []
for i in range(0, distance.shape[1], 2):
px = points[:, i % 2] + distance[:, i]
py = points[:, i % 2 + 1] + distance[:, i + 1]
if max_shape is not None:
px = px.clamp(min=0, max=max_shape[1])
py = py.clamp(min=0, max=max_shape[0])
preds.append(px)
preds.append(py)
return np.stack(preds, axis=-1)
class SCRFD:
def __init__(self, model_file=None, session=None):
self.model_file = model_file
self.session = session
self.taskname = 'detection'
self.batched = False
if self.session is None:
# CPUExecutionProvider CUDAExecutionProvider
# self.session = onnxruntime.InferenceSession(self.model_file, None, providers=["CPUExecutionProvider"])
self.session = onnxruntime.InferenceSession(self.model_file, None, providers=["CUDAExecutionProvider"])
self.center_cache = {}
self.nms_thresh = 0.4
self._init_vars()
def _init_vars(self):
input_cfg = self.session.get_inputs()[0]
input_shape = input_cfg.shape
if isinstance(input_shape[2], str):
self.input_size = None
else:
self.input_size = tuple(input_shape[2:4][::-1])
input_name = input_cfg.name
outputs = self.session.get_outputs()
if len(outputs[0].shape) == 3:
self.batched = True
output_names = []
for o in outputs:
output_names.append(o.name)
self.input_name = input_name
self.output_names = output_names
self.use_kps = False
self._num_anchors = 1
if len(outputs) == 6:
self.fmc = 3
self._feat_stride_fpn = [8, 16, 32]
self._num_anchors = 2
elif len(outputs) == 9:
self.fmc = 3
self._feat_stride_fpn = [8, 16, 32]
self._num_anchors = 2
self.use_kps = True
elif len(outputs) == 10:
self.fmc = 5
self._feat_stride_fpn = [8, 16, 32, 64, 128]
self._num_anchors = 1
elif len(outputs) == 15:
self.fmc = 5
self._feat_stride_fpn = [8, 16, 32, 64, 128]
self._num_anchors = 1
self.use_kps = True
def prepare(self, ctx_id, **kwargs):
if ctx_id < 0:
self.session.set_providers(['CPUExecutionProvider'])
nms_thresh = kwargs.get('nms_thresh', None)
if nms_thresh is not None:
self.nms_thresh = nms_thresh
input_size = kwargs.get('input_size', None)
if input_size is not None:
if self.input_size is not None:
print('warning: det_size is already set in scrfd model, ignore')
else:
self.input_size = input_size
def forward(self, img, thresh):
scores_list = []
bboxes_list = []
kpss_list = []
input_size = tuple(img.shape[0:2][::-1])
blob = cv2.dnn.blobFromImage(img, 1.0 / 128, input_size, (127.5, 127.5, 127.5), swapRB=False)
net_outs = self.session.run(self.output_names, {self.input_name: blob})
input_height = blob.shape[2]
input_width = blob.shape[3]
fmc = self.fmc
for idx, stride in enumerate(self._feat_stride_fpn):
# If model support batch dim, take first output
if self.batched:
scores = net_outs[idx][0]
bbox_preds = net_outs[idx + fmc][0]
bbox_preds = bbox_preds * stride
if self.use_kps:
kps_preds = net_outs[idx + fmc * 2][0] * stride
# If model doesn't support batching take output as is
else:
scores = net_outs[idx]
bbox_preds = net_outs[idx + fmc]
bbox_preds = bbox_preds * stride
if self.use_kps:
kps_preds = net_outs[idx + fmc * 2] * stride
height = input_height // stride
width = input_width // stride
K = height * width
key = (height, width, stride)
if key in self.center_cache:
anchor_centers = self.center_cache[key]
else:
# solution-1, c style:
# anchor_centers = np.zeros( (height, width, 2), dtype=np.float32 )
# for i in range(height):
# anchor_centers[i, :, 1] = i
# for i in range(width):
# anchor_centers[:, i, 0] = i
# solution-2:
# ax = np.arange(width, dtype=np.float32)
# ay = np.arange(height, dtype=np.float32)
# xv, yv = np.meshgrid(np.arange(width), np.arange(height))
# anchor_centers = np.stack([xv, yv], axis=-1).astype(np.float32)
# solution-3:
anchor_centers = np.stack(np.mgrid[:height, :width][::-1], axis=-1).astype(np.float32)
# print(anchor_centers.shape)
anchor_centers = (anchor_centers * stride).reshape((-1, 2))
if self._num_anchors > 1:
anchor_centers = np.stack([anchor_centers] * self._num_anchors, axis=1).reshape((-1, 2))
if len(self.center_cache) < 100:
self.center_cache[key] = anchor_centers
pos_inds = np.where(scores >= thresh)[0]
bboxes = distance2bbox(anchor_centers, bbox_preds)
pos_scores = scores[pos_inds]
pos_bboxes = bboxes[pos_inds]
scores_list.append(pos_scores)
bboxes_list.append(pos_bboxes)
if self.use_kps:
kpss = distance2kps(anchor_centers, kps_preds)
# kpss = kps_preds
kpss = kpss.reshape((kpss.shape[0], -1, 2))
pos_kpss = kpss[pos_inds]
kpss_list.append(pos_kpss)
return scores_list, bboxes_list, kpss_list
def detect(self, img, thresh=0.5, input_size=None, max_num=0, metric='default'):
assert input_size is not None or self.input_size is not None
input_size = self.input_size if input_size is None else input_size
im_ratio = float(img.shape[0]) / img.shape[1]
model_ratio = float(input_size[1]) / input_size[0]
if im_ratio > model_ratio:
new_height = input_size[1]
new_width = int(new_height / im_ratio)
else:
new_width = input_size[0]
new_height = int(new_width * im_ratio)
det_scale = float(new_height) / img.shape[0]
resized_img = cv2.resize(img, (new_width, new_height))
det_img = np.zeros((input_size[1], input_size[0], 3), dtype=np.uint8)
det_img[:new_height, :new_width, :] = resized_img
scores_list, bboxes_list, kpss_list = self.forward(det_img, thresh)
scores = np.vstack(scores_list)
scores_ravel = scores.ravel()
order = scores_ravel.argsort()[::-1]
bboxes = np.vstack(bboxes_list) / det_scale
if self.use_kps:
kpss = np.vstack(kpss_list) / det_scale
pre_det = np.hstack((bboxes, scores)).astype(np.float32, copy=False)
pre_det = pre_det[order, :]
keep = self.nms(pre_det)
det = pre_det[keep, :]
if self.use_kps:
kpss = kpss[order, :, :]
kpss = kpss[keep, :, :]
else:
kpss = None
if max_num > 0 and det.shape[0] > max_num:
area = (det[:, 2] - det[:, 0]) * (det[:, 3] -
det[:, 1])
img_center = img.shape[0] // 2, img.shape[1] // 2
offsets = np.vstack([
(det[:, 0] + det[:, 2]) / 2 - img_center[1],
(det[:, 1] + det[:, 3]) / 2 - img_center[0]
])
offset_dist_squared = np.sum(np.power(offsets, 2.0), 0)
if metric == 'max':
values = area
else:
values = area - offset_dist_squared * 2.0 # some extra weight on the centering
bindex = np.argsort(
values)[::-1] # some extra weight on the centering
bindex = bindex[0:max_num]
det = det[bindex, :]
if kpss is not None:
kpss = kpss[bindex, :]
return det, kpss
def nms(self, dets):
thresh = self.nms_thresh
x1 = dets[:, 0]
y1 = dets[:, 1]
x2 = dets[:, 2]
y2 = dets[:, 3]
scores = dets[:, 4]
areas = (x2 - x1 + 1) * (y2 - y1 + 1)
order = scores.argsort()[::-1]
keep = []
while order.size > 0:
i = order[0]
keep.append(i)
xx1 = np.maximum(x1[i], x1[order[1:]])
yy1 = np.maximum(y1[i], y1[order[1:]])
xx2 = np.minimum(x2[i], x2[order[1:]])
yy2 = np.minimum(y2[i], y2[order[1:]])
w = np.maximum(0.0, xx2 - xx1 + 1)
h = np.maximum(0.0, yy2 - yy1 + 1)
inter = w * h
ovr = inter / (areas[i] + areas[order[1:]] - inter)
inds = np.where(ovr <= thresh)[0]
order = order[inds + 1]
return keep
|