sampling·py
import random
import torch
import torch.nn as nn
from torch.autograd import Variable
from torch.autograd import Function
from bbox import bboxIOU
__all__ = ["buildPredBoxes", "sampleEzDetect"]
def buildPredBoxes(config):
predBoxes = []
for i in range(len(config.mboxes)):
l = config.mboxes[i][0]
wid = config.featureSize[l][0]
hei = config.featureSize[l][1]
wbox = config.mboxes[i][1]
hbox = config.mboxes[i][2]
for y in range(hei):
for x in range(wid):
xc = (x + 0.5) / wid #x y位置都取每个feature map像素的中心点来计算
yc = (y + 0.5) / hei
''' #计算一个以(xc, yc)为中心，宽度为wbox，高度为hbox的矩形框（或称为边界框）在归一化坐标系（通常是[0, 1]范围内）中的实际边界坐标。
xmin = max(0, xc-wbox/2)
ymin = max(0, yc-hbox/2)
xmax = min(1, xc+wbox/2)
ymax = min(1, yc+hbox/2)
'''
xmin = xc-wbox/2
ymin = yc-hbox/2
xmax = xc+wbox/2
ymax = yc+hbox/2
predBoxes.append([xmin, ymin, xmax, ymax])
return predBoxes
def sampleEzDetect(config, bboxes): #在voc_dataset.py的vocDataset类中用到的sampleEzDetect函数
## preparing pred boxes
predBoxes = config.predBoxes 从某个配置对象（config）中获取名为 predBoxes 的属性或数据
## preparing groud truth
truthBoxes = []
for i in range(len(bboxes)):
truthBoxes.append( [bboxes[i][1], bboxes[i][2], bboxes[i][3], bboxes[i][4]] )
## computing iou
iouMatrix = []
for i in predBoxes:
ious = []
for j in truthBoxes:
ious.append( bboxIOU(i, j) )
iouMatrix.append(ious)
iouMatrix = torch.FloatTensor( iouMatrix )
iouMatrix2 = iouMatrix.clone() 创建副本
ii = 0
selectedSamples = torch.FloatTensor(128*1024)
## positive samples from bi-direction match
for i in range(len(bboxes)):
iouViewer = iouMatrix.view(-1)
iouValues, iouSequence = torch.max(iouViewer, 0)
predIndex = iouSequence[0] // len(bboxes)#这行代码使用整数除法（//）来计算 iouSequence[0] 除以 len(bboxes) 的商，并将结果赋值给 predIndex。这个操作通常用于获取某种“类别”或“组”的索引，其中 iouSequence[0] 可能是一个复合索引，包含了类别和边界框索引的信息。通过除以边界框的数量，我们可以得到与类别或组相关的索引部分。
bboxIndex = iouSequence[0] % len(bboxes)#这行代码使用模运算（%）来计算 iouSequence[0] 除以 len(bboxes) 的余数，并将结果赋值给 bboxIndex。这个操作用于获取与具体边界框相关的索引部分。由于模运算的结果总是在 0 到 len(bboxes)-1 的范围内，因此 bboxIndex 可以直接用作 bboxes 列表中边界框的索引
if ( iouValues[0] > 0.1):
selectedSamples[ii*6 + 1] = bboxes[bboxIndex][0]
selectedSamples[ii*6 + 2] = bboxes[bboxIndex][1]
selectedSamples[ii*6 + 3] = bboxes[bboxIndex][2]
selectedSamples[ii*6 + 4] = bboxes[bboxIndex][3]
selectedSamples[ii*6 + 5] = bboxes[bboxIndex][4]
selectedSamples[ii*6 + 6] = predIndex #将 bboxes 列表中某个边界框（由 bboxIndex 索引）的坐标值复制到 selectedSamples 列表中的特定位置
ii = ii + 1
else:
break
iouMatrix[:, bboxIndex] = -1# iouMatrix 中所有行在 bboxIndex 列的值设置为 -1
iouMatrix[predIndex, :] = -1#您正在标记与特定预测或分类（由 predIndex 索引）相关的所有IoU值为无效或未定义。
iouMatrix2[predIndex,:] = -1#它同样将 predIndex 行的所有值设置为 -1
## also samples with high iou
for i in range(len(predBoxes)):
v,_ = iouMatrix2[i].max(0)
predIndex = i
bboxIndex = _[0]
if ( v[0] > 0.7): #anchor与真实值iou大于0.7的为正样本
selectedSamples[ii*6 + 1] = bboxes[bboxIndex][0]
selectedSamples[ii*6 + 2] = bboxes[bboxIndex][1]
selectedSamples[ii*6 + 3] = bboxes[bboxIndex][2]
selectedSamples[ii*6 + 4] = bboxes[bboxIndex][3]
selectedSamples[ii*6 + 5] = bboxes[bboxIndex][4]
selectedSamples[ii*6 + 6] = predIndex
ii = ii + 1
elif (v[0] > 0.5):
selectedSamples[ii*6 + 1] = bboxes[bboxIndex][0] * -1
selectedSamples[ii*6 + 2] = bboxes[bboxIndex][1]
selectedSamples[ii*6 + 3] = bboxes[bboxIndex][2]
selectedSamples[ii*6 + 4] = bboxes[bboxIndex][3]
selectedSamples[ii*6 + 5] = bboxes[bboxIndex][4]
selectedSamples[ii*6 + 6] = predIndex
ii = ii + 1
selectedSamples[0] = ii
return selectedSamples
encodeBox和decodeBox的过程
def encodeBox(config, box, predBox):
pcx = (predBox[0] + predBox[2]) / 2 （边界框中心点x坐标）是通过取边界框左右坐标的平均值来计算的
pcy = (predBox[1] + predBox[3]) / 2
pw = (predBox[2] - predBox[0])（边界框中心点x坐标）是通过取边界框左右坐标的平均值来计算的
ph = (predBox[3] - predBox[1])（边界框高度）是通过取边界框上下坐标的差值来计算的，
ecx = (box[0] + box[2]) / 2 - pcx
ecy = (box[1] + box[3]) / 2 - pcy
ecx = ecx / pw * 10
ecy = ecy / ph * 10
ew = (box[2] - box[0]) / pw
eh = (box[3] - box[1]) / ph
ew = math.log(ew) * 5
eh = math.log(eh) * 5
return[ecx, ecy, ew, eh]
def decodeAllBox(config, allBox):
newBoxes = torch.FloatTensor(allBox.size())
batchSize = newBoxes.size()[0]
for k in range(len(config.predBoxes)):
predBox = config.predBoxes[k]
pcx = (predBox[0] + predBox[2]) / 2
pcy = (predBox[1] + predBox[3]) / 2
pw = (predBox[2] - predBox[0])
ph = (predBox[3] - predBox[1])
for i in range(batchSize):
box = allBox[i, k, :]
dcx = box[0] / 10 * pw + pcx
dcy = box[1] / 10 * ph + pcy 计算了矩形框左上角（由box[0]和box[1]表示）相对于某个中心点（pcx, pcy）的新位置
dw = math.exp(box[2]/5) * pw
dh = math.exp(box[3]/5) * ph计算宽度与高度
newBoxes[i, k, 0] = max(0, dcx - dw/2)
newBoxes[i, k, 1] = max(0, dcy - dh/2)
newBoxes[i, k, 2] = min(1, dcx + dw/2)
newBoxes[i, k, 3] = min(1, dcy + dh/2)
if config.gpu :
newBoxes = newBoxes.cuda()
return newBoxes
import sys
import math
import torch
__all__ = ["bboxIOU", "encodeBox", "decodeAllBox", "doNMS"]
def doNMS(config, classMap, allBoxes, threshold):
winBoxes = []
predBoxes = config.predBoxes
for c in range(1, config.classNumber):
fscore = classMap[:, c]
#print(fscore)
v,s = torch.sort(fscore, 0, descending=True)
print(">>>>>>>>>>>>>>>",c,v[0])
for i in range(len(v)):
if ( v[i] < threshold):
continue
k = s[i]
boxA = [allBoxes[k, 0], allBoxes[k, 1], allBoxes[k, 2], allBoxes[k, 3]]
for j in range(i+1, len(v)):
if ( v[j] < threshold):
continue
k = s[j]
boxB = [allBoxes[k, 0], allBoxes[k, 1], allBoxes[k, 2], allBoxes[k, 3]]
iouValue = bboxIOU(boxA, boxB)
if ( iouValue > 0.5):
v[j] = 0
for i in range(len(v)):
if ( v[i] < threshold):
continue
k = s[i]
#box = [predBoxes[k][0], predBoxes[k][1], predBoxes[k][2], predBoxes[k][3]]
box = [allBoxes[k, 0], allBoxes[k, 1], allBoxes[k, 2], allBoxes[k, 3]]
winBoxes.append(box)
return winBoxes
标签：box,训练,bboxIndex,selectedSamples,ii,细节,bboxes,SSD,predBox From： https://www.cnblogs.com/candice1/p/18351495