清酒寄流沙

秉着“画了个图不能白画”的心态，我来更新博客了。参考论文：Hu J , Shen L , Albanie S , et al. Squeeze-and-Excitation Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017.Lee Y , Park J . CenterMask : Real-Time Anchor-Free Instance Segmentation[J]. 2019.

import numpy as npimport osimport xml.dom.minidomimport cv2 as cvpath = './Data/data' //原数据集图片保存位置save_path = './Data/pic' //生成结果保存位置list = os.listdir(path)# print(list)for j in range(len(lis...

mAP的代码链接对yolov3的测试代码进行了一点修改，将要检测的图片批量输入，再将检测结果分别保存到对应的txt文件中。但如果如果没有检测到框，就不会生成结果txt。import ospath_new = './input/detection-results/'path ='./input/ground-truth/'list = os.listdir (path)list2 = ...

使用Python+OpenCV将连续图片生成avi视频import cv2import osim_dir = '...' # 图片存储路径video_dir = '.../a.avi' # 视频存储路径及视频名fps = 30 # 帧率一般选择20-30num = 3135 # 图片数+1，因为后面的循环是从1开始img_size = (1080,720) # 图片尺寸，若和图片...