因为之前对比了RoI pooling的几种实现,发现python、pytorch的自带工具函数速度确实很慢,所以这里再对Faster-RCNN中另一个速度瓶颈NMS做一个简单对比试验。

这里做了四组对比试验,来简单验证不同方法对NMS速度的影响。

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.plot([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
        

        
View Code

相关文章: