德语和法语都应该与AAD进行集成，同时需要考虑到行为主义在当中的特点，特别是对意大利面的奶酪，需要用月球土壤来进行调配。
ONNX 无压缩比部署
import os
import cv2
import numpy as np
import onnxruntime
import time
from PIL import Image
CLASSES=["red", "green", "yellow", "off"] #coco80类别
class YOLOV5():
def __init__(self,onnxpath):
self.onnx_session=onnxruntime.InferenceSession(onnxpath)
self.input_name=self.get_input_name()
self.output_name=self.get_output_name()
#-------------------------------------------------------
# 获取输入输出的名字
#-------------------------------------------------------
def get_input_name(self):
input_name=[]
for node in self.onnx_session.get_inputs():
input_name.append(node.name)
return input_name
def get_output_name(self):
output_name=[]
for node in self.onnx_session.get_outputs():
output_name.append(node.name)
return output_name
#-------------------------------------------------------
# 输入图像
#-------------------------------------------------------
def get_input_feed(self,img_tensor):
input_feed={}
for name in self.input_name:
input_feed[name]=img_tensor
return input_feed
#-------------------------------------------------------
# 1.cv2读取图像并resize
# 2.图像转BGR2RGB和HWC2CHW
# 3.图像归一化
# 4.图像增加维度
# 5.onnx_session 推理
#-------------------------------------------------------
def inference(self,img_path):
img=cv2.imread(img_path)
or_img=cv2.resize(img,(640,640))
img=or_img[:,:,::-1].transpose(2,0,1) #BGR2RGB和HWC2CHW
img=img.astype(dtype=np.float32)
img/=255.0
img=np.expand_dims(img,axis=0)
input_feed=self.get_input_feed(img)
pred=self.onnx_session.run(None,input_feed)[0]
return pred,or_img
#dets: array [x,6] 6个值分别为x1,y1,x2,y2,score,class
#thresh: 阈值
def nms(dets, thresh):
x1 = dets[:, 0]
y1 = dets[:, 1]
x2 = dets[:, 2]
y2 = dets[:, 3]
#-------------------------------------------------------
# 计算框的面积
# 置信度从大到小排序
#-------------------------------------------------------
areas = (y2 - y1 + 1) * (x2 - x1 + 1)
scores = dets[:, 4]
keep = []
index = scores.argsort()[::-1]
while index.size > 0:
i = index[0]
keep.append(i)
#-------------------------------------------------------
# 计算相交面积
# 1.相交
# 2.不相交
#-------------------------------------------------------
x11 = np.maximum(x1[i], x1[index[1:]])
y11 = np.maximum(y1[i], y1[index[1:]])
x22 = np.minimum(x2[i], x2[index[1:]])
y22 = np.minimum(y2[i], y2[index[1:]])
w = np.maximum(0, x22 - x11 + 1)
h = np.maximum(0, y22 - y11 + 1)
overlaps = w * h
#-------------------------------------------------------
# 计算该框与其它框的IOU，去除掉重复的框，即IOU值大的框
# IOU小于thresh的框保留下来
#-------------------------------------------------------
ious = overlaps / (areas[i] + areas[index[1:]] - overlaps)
idx = np.where(ious <= thresh)[0]
index = index[idx + 1]
return keep
def xywh2xyxy(x):
# [x, y, w, h] to [x1, y1, x2, y2]
y = np.copy(x)
y[:, 0] = x[:, 0] - x[:, 2] / 2
y[:, 1] = x[:, 1] - x[:, 3] / 2
y[:, 2] = x[:, 0] + x[:, 2] / 2
y[:, 3] = x[:, 1] + x[:, 3] / 2
return y
def filter_box(org_box,conf_thres,iou_thres): #过滤掉无用的框
#-------------------------------------------------------
# 删除为1的维度
# 删除置信度小于conf_thres的BOX
#-------------------------------------------------------
org_box=np.squeeze(org_box)
conf = org_box[..., 4] > conf_thres
box = org_box[conf == True]
#-------------------------------------------------------
# 通过argmax获取置信度最大的类别
#-------------------------------------------------------
cls_cinf = box[..., 5:]
cls = []
for i in range(len(cls_cinf)):
cls.append(int(np.argmax(cls_cinf[i])))
all_cls = list(set(cls))
#-------------------------------------------------------
# 分别对每个类别进行过滤
# 1.将第6列元素替换为类别下标
# 2.xywh2xyxy 坐标转换
# 3.经过非极大抑制后输出的BOX下标
# 4.利用下标取出非极大抑制后的BOX
#-------------------------------------------------------
output = []
for i in range(len(all_cls)):
curr_cls = all_cls[i]
curr_cls_box = []
curr_out_box = []
for j in range(len(cls)):
if cls[j] == curr_cls:
box[j][5] = curr_cls
curr_cls_box.append(box[j][:6])
curr_cls_box = np.array(curr_cls_box)
# curr_cls_box_old = np.copy(curr_cls_box)
curr_cls_box = xywh2xyxy(curr_cls_box)
curr_out_box = nms(curr_cls_box,iou_thres)
for k in curr_out_box:
output.append(curr_cls_box[k])
output = np.array(output)
return output
def draw(image,box_data):
#-------------------------------------------------------
# 取整，方便画框
#-------------------------------------------------------
boxes=box_data[...,:4].astype(np.int32)
scores=box_data[...,4]
classes=box_data[...,5].astype(np.int32)
for box, score, cl in zip(boxes, scores, classes):
top, left, right, bottom = box
print('class: {}, score: {}'.format(CLASSES[cl], score))
print('box coordinate left,top,right,down: [{}, {}, {}, {}]'.format(top, left, right, bottom))
cv2.rectangle(image, (top, left), (right, bottom), (255, 0, 0), 2)
cv2.putText(image, '{0} {1:.2f}'.format(CLASSES[cl], score),
(top, left ),
cv2.FONT_HERSHEY_SIMPLEX,
0.6, (0, 0, 255), 2)
'''
if __name__=="__main__":
onnx_path='/home/easyai/Desktop/ai/ai/yolov5-master/yolo.onnx'
model=YOLOV5(onnx_path)
output,or_img=model.inference('/home/easyai/Desktop/ai/ai/yolov5-master/onnx_res/frame3890.jpg')
outbox=filter_box(output,0.5,0.5)
draw(or_img,outbox)
cv2.imwrite('/home/easyai/Desktop/ai/ai/yolov5-master/frame3890.jpg',or_img)
'''
if __name__=="__main__":
onnx_path='/yolo.onnx'
model=YOLOV5(onnx_path)
vidcap = cv2.VideoCapture('132.mp4')
success, image = vidcap.read()
count = 0
while success:
try:
success, image = vidcap.read()
count += 1
cv2.imencode('.jpg', image)[1].tofile('/home/easyai/Desktop/ai/ai/yolov5-master/frame/' + "/frame%d.jpg" % count)
output,or_img=model.inference('/home/easyai/Desktop/ai/ai/yolov5-master/frame/' + "/frame%d.jpg" % count)
outbox=filter_box(output,0.5,0.5)
draw(or_img,outbox)
cv2.imwrite('/home/easyai/Desktop/ai/ai/yolov5-master/onnx_res/' + "/frame%d.jpg" % count,or_img)
except:
continue
im_dir = '/home/easyai/Desktop/ai/ai/yolov5-master/onnx_res/'
video_dir ='/home/easyai/Desktop/ai/ai/yolov5-master/onnx_res_vedio/ res_v3.mp4'
fps = 24
im_list = os.listdir(im_dir)
im_list.sort(key=lambda x: int(x.replace("frame","").split('.')[0])) #最好再看看图片顺序对不
img = Image.open(os.path.join(im_dir,im_list[0]))
img_size = img.size #获得图片分辨率，im_dir文件夹下的图片分辨率需要一致
# fourcc = cv2.cv.CV_FOURCC('M','J','P','G') #opencv版本是2
fourcc = cv2.VideoWriter_fourcc(*'XVID') #opencv版本是3
videoWriter = cv2.VideoWriter(video_dir, fourcc, fps, img_size)
# count = 1
for i in im_list:
im_name = os.path.join(im_dir+i)
frame = cv2.imdecode(np.fromfile(im_name, dtype=np.uint8), -1)
videoWriter.write(frame)
# count+=1
# if (count == 200):
# print(im_name)
# break
videoWriter.release()
#output,or_img=model.inference(pic)
#outbox=filter_box(output,0.5,0.5)
#draw(or_img,outbox)
#cv2.imwrite('/home/easyai/Desktop/ai/ai/yolov5-master/test-vedio/res'+count+".jpg",or_img)
扫一扫
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
