方法1：纯python语言实现：简介方便、速度慢
方法2：直接利用Cython模块编译
方法3：先将全部变量定义为静态类型，再利用Cython模块编译
方法4：在方法3的基础上再加入cuda加速模块， 再利用Cython模块编译，即利用gpu加速
一. 几点说明
1. 简单说明Cython：
Cython是一个快速生成Python扩展模块的工具，从语法层面上来讲是Python语法和C语言语法的混血，当Python性能遇到瓶颈时，Cython直接将C的原生速度植入Python程序，这样使Python程序无需使用C重写，能快速整合原有的Python程序，这样使得开发效率和执行效率都有很大的提高，而这些中间的部分，都是Cython帮我们做了。
2. 简单介绍NMS：
Faster-RCNN中有两处使用NMS，第一处是训练+预测的时候，利用ProposalCreator来生成proposal的时候，因为只需要一部分proposal，所以利用NMS进行筛选。第二处使用是预测的时候，当得到300个分类与坐标偏移结果的时候，需要对每个类别逐一进行非极大值抑制。也许有人问为什么对于每个类别不直接取置信度最高的那一个？因为一张图中某个类别可能不止一个，例如一张图中有多个人，直接取最高置信度的只能预测其中的一个人，而通过NMS理想情况下可以使得每个人（每类中的每个个体）都会有且仅有一个bbox框。
二. 四种方法实现
1. 纯python实现：nms_py.py
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Mon May 7 21:45:37 2018
@author: lps
"""
import numpy as np
boxes=np.array([[100,100,210,210,0.72],
[250,250,420,420,0.8],
[220,220,320,330,0.92],
[100,100,210,210,0.72],
[230,240,325,330,0.81],
[220,230,315,340,0.9]])
def py_cpu_nms(dets, thresh):
# dets:(m,5) thresh:scaler
x1 = dets[:,0]
y1 = dets[:,1]
x2 = dets[:,2]
y2 = dets[:,3]
areas = (y2-y1+1) * (x2-x1+1)
scores = dets[:,4]
keep = []
index = scores.argsort()[::-1]
while index.size >0:
i = index[0] # every time the first is the biggst, and add it directly
keep.append(i)
x11 = np.maximum(x1[i], x1[index[1:]]) # calculate the points of overlap
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) # the weights of overlap
h = np.maximum(0, y22-y11+1) # the height of overlap
overlaps = w*h
ious = overlaps / (areas[i]+areas[index[1:]] - overlaps)
idx = np.where(ious<=thresh)[0]
index = index[idx+1] # because index start from 1
return keep
import matplotlib.pyplot as plt
def plot_bbox(dets, c='k'):
x1 = dets[:,0]
y1 = dets[:,1]
x2 = dets[:,2]
y2 = dets[:,3]
plt.pl<em style="color:transparent">本文来源[email protected]搞@^&代*@码)网9</em>ot([x1,x2], [y1,y1], c)
plt.plot([x1,x1], [y1,y2], c)
plt.plot([x1,x2], [y2,y2], c)
plt.plot([x2,x2], [y1,y2], c)
plt.title("after nms")
plot_bbox(boxes,'k') # before nms
keep = py_cpu_nms(boxes, thresh=0.7)
plot_bbox(boxes[keep], 'r')# after nms
结果大致这样：
新建nms文件夹，将nms_py.py 和__init__.py（空）文件放在其内成为包，可以调用。然后在nms文件夹外新建测试运行时间脚本 test_num.py：
import numpy as np
import time
from nms.nums_py import py_cpu_nms # for cpu
#from nms.gpu_nms import gpu_nms # for gpu
np.random.seed( 1 ) # keep fixed
num_rois = 6000
minxy = np.random.randint(50,145,size=(num_rois ,2))
maxxy = np.random.randint(150,200,size=(num_rois ,2))
score = 0.8*np.random.random_sample((num_rois ,1))+0.2
boxes_new = np.concatenate((minxy,maxxy,score), axis=1).astype(np.float32)
def nms_test_time(boxes_new):
thresh = [0.7,0.8,0.9]
T = 50
for i in range(len(thresh)):
since = time.time()
for t in range(T):
keep = py_cpu_nms(boxes_new, thresh=thresh[i]) # for cpu
# keep = gpu_nms(boxes_new, thresh=thresh[i]) # for gpu
print("thresh={:.1f}, time wastes:{:.4f}".format(thresh[i], (time.time()-since)/T))
return keep
if __name__ =="__main__":
nms_test_time(boxes_new)
搞代码网（gaodaima.com）提供的所有资源部分来自互联网，如果有侵犯您的版权或其他权益，请说明详细缘由并提供版权或权益证明然后发送到邮箱[email protected]，我们会在看到邮件的第一时间内为您处理，或直接联系QQ：872152909。本网站采用BY-NC-SA协议进行授权
转载请注明原文链接：Python 非极大值抑制(NMS)的四种实现详解
转载请注明原文链接：Python 非极大值抑制(NMS)的四种实现详解
