yolov3预训练权重_水果识别-训练

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
 
# sets=[('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test')] 
# classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
 
sets=[('2007', 'train')] 这里只用到训练，数据集命名为VOC2017
classes = ["apple", "pear", "banana"] 只用了三个类别作为展示
 
 
def convert(size, box):
   dw = 1./(size[0])
   dh = 1./(size[1])
   x = (box[0] + box[1])/2.0 - 1
   y = (box[2] + box[3])/2.0 - 1
   w = box[1] - box[0]
   h = box[3] - box[2]
   x = x*dw
   w = w*dw
   y = y*dh
   h = h*dh
   return (x,y,w,h)
 
def convert_annotation(year, image_id):
   in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id))
   out_file = open('VOCdevkit/VOC%s/labels/%s.txt'%(year, image_id), 'w')
   tree=ET.parse(in_file)
   root = tree.getroot()
   size = root.find('size')
   w = int(size.find('width').text)
   h = int(size.find('height').text)
 
   for obj in root.iter('object'):
       difficult = obj.find('difficult').text
       cls = obj.find('name').text
       if cls not in classes or int(difficult)==1:
           continue
       cls_id = classes.index(cls)
       xmlbox = obj.find('bndbox')
       b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
       bb = convert((w,h), b)
       out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + 'n')
 
wd = getcwd()
 
for year, image_set in sets:
   if not os.path.exists('VOCdevkit/VOC%s/labels/'%(year)):
       os.makedirs('VOCdevkit/VOC%s/labels/'%(year))
   image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split()
   list_file = open('%s_%s.txt'%(year, image_set), 'w')
   for image_id in image_ids:
       list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpgn'%(wd, year, image_id))
       convert_annotation(year, image_id)
   list_file.close()

[net]
# Testing
# batch=1
# subdivisions=1
# Training       # 训练的时候把Testing的参数注释掉，把Training的参数取消注释
batch=64
subdivisions=16
width=416
height=416
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1
 
learning_rate=0.001          # 根据需要修改学习率，就是梯度下降的速率，越大训练速度越快但会牺牲准确率
burn_in=1000
max_batches = 100000     # 训练的总次数
policy=steps
steps=100,10000,70000,80000,90000        # 训练到相应次数后学习率变化
scales=10,10,.1,.1,.1        # 学习率变化情况，是累乘操作
 
......
 
 
[convolutional]
size=1
stride=1
pad=1
filters=24           # filters = 3*(calsses + 5)
activation=linear
 
[yolo]
mask = 0,1,2
anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
classes=3        # 修改类别数量
num=9
jitter=.3
ignore_thresh = .5
truth_thresh = 1
random=1         # 为1时会启用Multi-Scale Training，随机使用不同尺寸的图片进行训练，显存小可以置为0

apple
pear
banana

classes= 3 //类别数量
train  = /home/embedded/lm/darknet/scripts/2007_train.txt    //指定训练样本
// valid  = /home/pjreddie/data/voc/2007_test.txt  指定测试数据，训练用不到
names = /home/embedded/lm/darknet/data/voc.names //指向上一步修改的voc.names文件
backup = /home/embedded/lm/darknet/backup/yolov3_voc_weights //指定训练后的权值放在哪儿

./darknet detector train cfg/voc.data cfg/yolov3_voc.cfg

./darknet detector train cfg/voc.data cfg/yolov3_voc.cfg yolo.weights