手把手教物体检测——RFBNethttps://github.解压后在RFBNet的data文件夹下新建VOCdevki

下载代码

github.com/ruinmessi/R…

解压后在RFBNet的data文件夹下新建VOCdevkit文件夹，将VOC数据集放进去。
修改类别。

在voc0712.py中的VOC_CLASSES中的类别修改为自己数据集的类别。修改后：

VOC_CLASSES = ( '__background__' , # always index 0
'aircraft' , 'oiltank' )

注意：第一个类别是背景，不用修改。

修改config.py的文件路径。

RBFNet默认的路径是linux的路径，我使用的是Win10，需要修改路径，否则找不到数据集。

将：

# gets home dir cross platform

home = os.path.expanduser("~")

ddir = os.path.join(home,"data/VOCdevkit/")

# note: if you used our download scripts, this should be right

VOCroot = ddir # path to VOCdevkit root dir

COCOroot = os.path.join(home,"data/COCO/")

改为：

# gets home dir cross platform

ddir = "data/VOCdevkit/"

# note: if you used our download scripts, this should be right

VOCroot = ddir # path to VOCdevkit root dir

COCOroot = "data/COCO/"

修改utils->nms_wrapper.py

这个文件的作用的调用nms中文件，nms指的是非极大值抑制。

nms文件夹是集中nms编写的方式，采用py的即可，性能上不会有太大的影响。

将：

from .nms.cpu_nms import cpu_nms, cpu_soft_nms

from .nms.gpu_nms import gpu_nms

修改为：

from .nms.py_cpu_nms import py_cpu_nms

将：

def nms(dets, thresh, force_cpu=False):

    """Dispatch to either CPU or GPU NMS implementations."""

    if dets.shape[0] == 0:

        return []

    if force_cpu:

        #return cpu_soft_nms(dets, thresh, method = 0)

        return cpu_nms(dets, thresh)

    return gpu_nms(dets, thresh)

修改为：

def nms(dets, thresh, force_cpu=False):

    """Dispatch to either CPU or GPU NMS implementations."""

    if dets.shape[0] == 0:

        return []

    if force_cpu:

        #return cpu_soft_nms(dets, thresh, method = 0)

        return py_cpu_nms(dets, thresh)

    return py_cpu_nms(dets, thresh)

新建weights文件，下载vgg16模型放到里面。

下载地址： s3.amazonaws.com/amdegroot-m…

修改data->coco.py

将：

from utils.pycocotools.coco import COCO
from utils.pycocotools.cocoeval import COCOeval
from utils.pycocotools import mask as COCOmask

修改为：

from pycocotools.coco import COCO
from pycocotools.cocoeval import COCOeval
from pycocotools import mask as COCOmask

删除utils->pycocotools文件夹。

修改train_RFB.py

修改全局参数：

parser = argparse.ArgumentParser(
description= 'Receptive Field Block Net Training' )
parser.add_argument( '-v' , '--version' , default= 'RFB_vgg' ,
help= 'RFB_vgg ,RFB_E_vgg or RFB_mobile version.' )
parser.add_argument( '-s' , '--size' , default= '512' ,
help= '300 or 512 input size.' )
parser.add_argument( '-d' , '--dataset' , default= 'VOC' ,
help= 'VOC or COCO dataset' )
parser.add_argument(
'--basenet' , default= './weights/vgg16_reducedfc.pth' , help= 'pretrained base model' )
parser.add_argument( '--jaccard_threshold' , default=0.5,
type=float, help= 'Min Jaccard index for matching' )
parser.add_argument( '-b' , '--batch_size' , default=2,
type=int, help= 'Batch size for training' )
parser.add_argument( '--num_workers' , default=2,
type=int, help= 'Number of workers used in dataloading' )
parser.add_argument( '--cuda' , default=True,
type=bool, help= 'Use cuda to train model' )
parser.add_argument( '--ngpu' , default=1, type=int, help= 'gpus' )
parser.add_argument( '--lr' , '--learning-rate' ,
default=4e-3, type=float, help= 'initial learning rate' )
parser.add_argument( '--momentum' , default=0.9, type=float, help= 'momentum' )
parser.add_argument(
'--resume_net' , default=None, help= 'resume net for retraining' )
parser.add_argument( '--resume_epoch' , default=0,
type=int, help= 'resume iter for retraining' )
parser.add_argument( '-max' , '--max_epoch' , default=300,
type=int, help= 'max epoch for retraining' )
parser.add_argument( '--weight_decay' , default=5e-4,
type=float, help= 'Weight decay for SGD' )
parser.add_argument( '--gamma' , default=0.1,
type=float, help= 'Gamma update for SGD' )
parser.add_argument( '--log_iters' , default=True,
type=bool, help= 'Print the loss at each iteration' )
parser.add_argument( '--save_folder' , default= './weights/' ,
help= 'Location to save checkpoint models' )

将：

if args.dataset == 'VOC':

    train_sets = [('2007', 'trainval'), ('2012', 'trainval')]

    cfg = (VOC_300, VOC_512)[args.size == '512']

else:

    train_sets = [('2014', 'train'),('2014', 'valminusminival')]

    cfg = (COCO_300, COCO_512)[args.size == '512']

修改为：

if args.dataset == 'VOC':

    train_sets = [('2007', 'trainval'), 

    cfg = (VOC_300, VOC_512)[args.size == '512']

else:

    train_sets = [('2014', 'train'),('2014', 'valminusminival')]

    cfg = (COCO_300, COCO_512)[args.size == '512']

将82行：

num_classes = (21, 81)[args.dataset == 'COCO' ]

修改为：

num_classes = (3, 81)[args.dataset == 'COCO' ]#如果是COCO就选择81,3是本次的类别+1（背景）

结果：

前5个Epoch将学习率从小升到初始值，是用来对模型进行热身。

测试，并验证测试结果。

修改test_RFB.py

修改全局参数

parser.add_argument( '-v' , '--version' , default= 'RFB_vgg' ,
help= 'RFB_vgg ,RFB_E_vgg or RFB_mobile version.' )#和训练的模型保持一致。
parser.add_argument( '-s' , '--size' , default= '512' ,
help= '300 or 512 input size.' )#和训练是选用的大小保持一致。
parser.add_argument( '-d' , '--dataset' , default= 'VOC' ,
help= 'VOC or COCO version' )
parser.add_argument( '-m' , '--trained_model' , default= 'weights/Final_RFB_vgg_VOC.pth' ,
type=str, help= 'Trained state_dict file path to open' )#选择训练好的模型
parser.add_argument( '--cuda' , default=False, type=bool,
help= 'Use cuda to train model' )
parser.add_argument( '--cpu' , default=True, type=bool,
help= 'Use cpu nms' )
parser.add_argument( '--retest' , default=False, type=bool,
help= 'test cache results' )
args = parser.parse_args()

将148行：

num_classes = (21, 81)[args.dataset == 'COCO' ]

修改为：

num_classes = (3, 81)[args.dataset == 'COCO' ]

将71行：

num_classes = (21, 81)[args.dataset == 'COCO' ]

修改为：

num_classes = (3, 81)[args.dataset == 'COCO' ]

修改voc0712.py的281行

将：

annopath = os.path.join(
rootpath,
'Annotations' ,
'{:s}.xml' )

修改为：annopath = rootpath+'/Annotations/{:s}.xml'#解决验证时找不到测试集xml的问题。

运行test_RFB.py结果如下：

测试单张图片，并展示结果。

from __future__ import print_function
import torch
import torch.backends.cudnn as cudnn
import os
import argparse
import numpy as np
from matplotlib import pyplot as plt
from data import AnnotationTransform, COCODetection, VOCDetection, BaseTransform, VOC_300, VOC_512, COCO_300, COCO_512, \
COCO_mobile_300
from layers.functions import Detect, PriorBox
from utils.nms_wrapper import nms
import cv2
from data import VOC_CLASSES as labels
from collections import OrderedDict
import time
#功能：测试单一的一张图片
parser = argparse.ArgumentParser(description= 'Receptive Field Block Net' )
parser.add_argument( '-v' , '--version' , default= 'RFB_vgg' ,
help= 'RFB_vgg ,RFB_E_vgg or RFB_mobile version.' )
parser.add_argument( '-s' , '--size' , default= '512' ,
help= '300 or 512 input size.' )
parser.add_argument( '-n' , '--num_classes' , default= '3' ,
help= '300 or 512 input size.' )
parser.add_argument( '-d' , '--dataset' , default= 'VOC' ,
help= 'VOC or COCO version' )
parser.add_argument( '-m' , '--trained_model' , default= 'weights/RFB_vgg_VOC_epoches_160.pth' ,
type=str, help= 'Trained state_dict file path to open' )
parser.add_argument( '--save_folder' , default= 'eval/' , type=str,
help= 'Dir to save results' )
parser.add_argument( '--cuda' , default=True, type=bool,
help= 'Use cuda to train model' )
parser.add_argument( '--cpu' , default=False, type=bool,
help= 'Use cpu nms' )
parser.add_argument( '--retest' , default=False, type=bool,
help= 'test cache results' )
args = parser.parse_args()

if not os.path.exists(args.save_folder):
os.mkdir(args.save_folder)
if args.dataset == 'VOC' :
cfg = (VOC_300, VOC_512)[args.size == '512' ]
else:
cfg = (COCO_300, COCO_512)[args.size == '512' ]
if args.version == 'RFB_vgg' :
from models.RFB_Net_vgg import build_net
elif args.version == 'RFB_E_vgg' :
from models.RFB_Net_E_vgg import build_net
elif args.version == 'RFB_mobile' :
from models.RFB_Net_mobile import build_net

cfg = COCO_mobile_300
else:
print( 'Unkown version!' )
priorbox = PriorBox(cfg)
with torch.no_grad():
priors = priorbox.forward()
if args.cuda:
priors = priors.cuda()
t1=time.time()
imagePath = "data/VOCdevkit/aircraft_27.jpg"
# load net
img_dim = int(args.size)
num_classes = int(args.num_classes)
net = build_net( 'test' , img_dim, num_classes) # initialize detector
state_dict = torch.load(args.trained_model)
# create new OrderedDict that does not contain `module.`
new_state_dict = OrderedDict()
for k, v in state_dict.items():
head = k[:7]
if head == 'module.' :
name = k[7:] # remove `module.`
else:
name = k
new_state_dict[name] = v
net.load_state_dict(new_state_dict)
net.eval()
print( 'Finished loading model!' )
if args.cuda:
net = net.cuda()
cudnn.benchmark = True
else:
net = net.cpu()
top_k = 200
detector = Detect(num_classes, 0, cfg)
save_folder = os.path.join(args.save_folder, args.dataset)
if not os.path.exists(save_folder):
os.mkdir(save_folder)
# dump predictions and assoc. ground truth to text file for now
det_file = os.path.join(save_folder, 'detections.pkl' )
image = cv2.imread(imagePath, cv2.IMREAD_COLOR)
rgb_means = ((104, 117, 123), (103.94, 116.78, 123.68))[args.version == 'RFB_mobile' ]
scale = torch.Tensor([image.shape[1], image.shape[0],
image.shape[1], image.shape[0]])
transform = BaseTransform(net.size, rgb_means, (2, 0, 1))
with torch.no_grad():
x = transform(image).unsqueeze(0)
if args.cuda:
x = x.cuda()
scale = scale.cuda()
out = net(x) # forward pass
boxes, scores = detector.forward(out, priors)
boxes = boxes[0]
scores = scores[0]
boxes *= scale
boxes = boxes.cpu().numpy()
scores = scores.cpu().numpy()

result = []
for j in range(1, num_classes):
inds = np.where(scores[:, j] > 0.99)[0]
if len(inds) == 0:
continue
label_name = labels[j]
c_bboxes = boxes[inds]
c_scores = scores[inds, j]
c_dets = np.hstack((c_bboxes, c_scores[:, np.newaxis])).astype(
np.float32, copy=False)
keep = nms(c_dets, 0.45, force_cpu=args.cpu)
c_dets = c_dets[keep, :]
for listbox in c_dets:
temp = []
temp.append(label_name)
temp.append(listbox[4])
temp.append(int(listbox[0]))
temp.append(int(listbox[1]))
temp.append(int(listbox[2]))
temp.append(int(listbox[3]))
result.append(temp)
print(result)
t2=time.time()
print(t2-t1)
isShowResult = True
if isShowResult:
plt.figure(figsize=(10, 10))
colors = plt.cm.hsv(np.linspace(0, 1, num_classes)).tolist()
rgb_image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
plt.imshow(rgb_image) # plot the image for matplotlib
currentAxis = plt.gca()
for listbox in result:
label_name = listbox[0]
i = labels.index(label_name)
score = listbox[1]
coords = (listbox[2], listbox[3]), listbox[4] - listbox[2] + 1, listbox[5] - listbox[3] + 1
display_txt = '%s: %.2f' % (label_name, score)
color = colors[i]
currentAxis.add_patch(plt.Rectangle(*coords, fill=False, edgecolor=color, linewidth=2))
currentAxis.text(listbox[2], listbox[3], display_txt, bbox={ 'facecolor' : color, 'alpha' : 0.5})
plt.show()