在参加竞赛的时候,找到了Yolov5-lite模型,但是并没有找到opencv_dnn的推理代码,然后就自己写了个推理代码,不说多了直接展示了!
import cv2
import numpy as np
import multiprocessing
from multiprocessing import Process, JoinableQueue
import os
net = cv2.dnn.readNetFromONNX('name.onnx')
class yolov5_lite():
def __init__(self ,label_path, confThreshold=0.5, nmsThreshold=0.5, objThreshold=0.5):
self.net = cv2.dnn.readNetFromONNX('best_fp16.onnx')
self.classes = list(map(lambda x: x.strip(), open(label_path, 'r').readlines()))
self.num_classes = len(self.classes)
anchors = [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]]
self.nl = len(anchors)
self.na = len(anchors[0]) // 2
self.no = self.num_classes + 5
self.grid = [np.zeros(1)] * self.nl
self.stride = np.array([8., 16., 32.])
self.anchor_grid = np.asarray(anchors, dtype=np.float32).reshape(self.nl, -1, 2)
self.confThreshold = confThreshold
self.nmsThreshold = nmsThreshold
self.objThreshold = objThreshold
self.input_shape = ((256,256))
def resize_image(self, srcimg, keep_ratio=True):
top, left, newh, neww = 0, 0, self.input_shape[0], self.input_shape[1]
if keep_ratio and srcimg.shape[0] != srcimg.shape[1]:
hw_scale = srcimg.shape[0] / srcimg.shape[1]
if hw_scale > 1:
newh, neww = self.input_shape[0], int(self.input_shape[1] / hw_scale)
img = cv2.resize(srcimg, (neww, newh), interpolation=cv2.INTER_AREA)
left = int((self.input_shape[1] - neww) * 0.5)
img = cv2.copyMakeBorder(img, 0, 0, left, self.input_shape[1] - neww - left, cv2.BORDER_CONSTANT,
value=0) # add border
else:
newh, neww = int(self.input_shape[0] * hw_scale), self.input_shape[1]
img = cv2.resize(srcimg, (neww, newh), interpolation=cv2.INTER_AREA)
top = int((self.input_shape[0] - newh) * 0.5)
img = cv2.copyMakeBorder(img, top, self.input_shape[0] - newh - top, 0, 0, cv2.BORDER_CONSTANT, value=0)
else:
img = cv2.resize(srcimg, self.input_shape, interpolation=cv2.INTER_AREA)
return img, newh, neww, top, left
def _make_grid(self, nx=20, ny=20):
xv, yv = np.meshgrid(np.arange(ny), np.arange(nx))
return np.stack((xv, yv), 2).reshape((-1, 2)).astype(np.float32)
def postprocess(self, frame, outs, pad_hw):
newh, neww, padh, padw = pad_hw
frameHeight = frame.shape[0]
frameWidth = frame.shape[1]
ratioh, ratiow = frameHeight / newh, frameWidth / neww
# Scan through all the bounding boxes output from the network and keep only the
# ones with high confidence scores. Assign the box's class label as the class with the highest score.
classIds = []
confidences = []
box_index = []
boxes = []
outs = outs[outs[:, 4] > self.objThreshold]
for detection in outs:
scores = detection[5:]
classId = np.argmax(scores)
confidence = scores[classId]
if confidence > self.confThreshold: # and detection[4] > self.objThreshold:
center_x = int((detection[0] - padw) * ratiow)
center_y = int((detection[1] - padh) * ratioh)
width = int(detection[2] * ratiow)
height = int(detection[3] * ratioh)
left = int(center_x - width / 2)
top = int(center_y - height / 2)
classIds.append(classId)
confidences.append(float(confidence))
boxes.append([left, top, width, height])
# Perform non maximum suppression to eliminate redundant overlapping boxes with
# lower confidences.
# print(boxes)
indices = cv2.dnn.NMSBoxes(boxes, confidences, self.confThreshold, self.nmsThreshold)
for i in indices:
box_index.append(i)
res=[]
for i in box_index:
box = boxes[i]
left = box[0]
top = box[1]
width = box[2]
height = box[3]
frame = self.drawPred(frame, classIds[i], confidences[i], left, top, left + width, top + height)
res.append([left,top,left+width,top+height,confidences[i],classIds[i]])
print(res)
return frame
def drawPred(self, frame, classId, conf, left, top, right, bottom):
# Draw a bounding box.
cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), thickness=2)
label = '%.2f' % conf
label = '%s:%s' % (self.classes[classId], label)
# Display the label at the top of the bounding box
labelSize, baseLine = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 1)
top = max(top, labelSize[1])
# cv.rectangle(frame, (left, top - round(1.5 * labelSize[1])), (left + round(1.5 * labelSize[0]), top + baseLine), (255,255,255), cv.FILLED)
cv2.putText(frame, label, (left, top - 10), cv2.FONT_HERSHEY_TRIPLEX, 0.5, (0, 255, 0), thickness=1)
return frame
def detect(self, srcimg):
img, newh, neww, top, left = self.resize_image(srcimg)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = img.astype(np.float32) / 255.0
blob = np.expand_dims(np.transpose(img, (2, 0, 1)), axis=0)
t1 = time.time()
self.net.setInput(blob)
outs = self.net.forward()[0]
cost_time = time.time() - t1
print(outs)
row_ind = 0
for i in range(self.nl):
h, w = int(self.input_shape[0] / self.stride[i]), int(self.input_shape[1] / self.stride[i])
length = int(self.na * h * w)
if self.grid[i].shape[2:4] != (h, w):
self.grid[i] = self._make_grid(w, h)
outs[row_ind:row_ind + length, 0:2] = (outs[row_ind:row_ind + length, 0:2] * 2. - 0.5 + np.tile(
self.grid[i], (self.na, 1))) * int(self.stride[i])
outs[row_ind:row_ind + length, 2:4] = (outs[row_ind:row_ind + length, 2:4] * 2) ** 2 * np.repeat(
self.anchor_grid[i], h * w, axis=0)
row_ind += length
srcimg = self.postprocess(srcimg, outs, (newh, neww, top, left))
infer_time = 'Inference Time: ' + str(int(cost_time * 1000)) + 'ms'
cv2.putText(srcimg, infer_time, (5, 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, (0, 0, 0), thickness=1)
return srcimg
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--imgpath', type=str, default=r'E:\new_dataset\images\003.png', help="image path")
parser.add_argument('--modelpath', type=str, default='best_fp16.onnx', help="onnx filepath")
parser.add_argument('--classfile', type=str, default='coco.names', help="classname filepath")
parser.add_argument('--confThreshold', default=0.4, type=float, help='class confidence')
parser.add_argument('--nmsThreshold', default=0.6, type=float, help='nms iou thresh')
args = parser.parse_args()
srcimg = cv2.imread(args.imgpath)
net = yolov5_lite(args.classfile, confThreshold=args.confThreshold, nmsThreshold=args.nmsThreshold)
srcimg = net.detect(srcimg.copy())
winName = 'Deep learning object detection in onnxruntime'
cv2.namedWindow(winName, cv2.WINDOW_NORMAL)
cv2.imshow(winName, srcimg)
cv2.waitKey(0)
# cv2.imwrite('save.jpg', srcimg )
cv2.destroyAllWindows()