手把手教物体检测——RFBNet

大家好，欢迎来到IT知识分享网。

​

​​

https://github.com/ruinmessi/RFBNet

1. 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。
2. 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。

1. 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/"

1. 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)

1. 新建weights文件，下载vgg16模型放到里面。

下载地址：https://s3.amazonaws.com/amdegroot-models/vgg16_reducedfc.pth

1. 修改data->coco.py

将：

from utils.pycocotools.coco import COCOfrom utils.pycocotools.cocoeval import COCOevalfrom utils.pycocotools import mask as COCOmask

修改为：

from pycocotools.coco import COCOfrom pycocotools.cocoeval import COCOevalfrom pycocotools import mask as COCOmask

删除utils->pycocotools文件夹 。

1. 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。

1. 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：

​

1. 测试单张图片，并展示结果。

from __future__ import print_functionimport torchimport torch.backends.cudnn as cudnnimport osimport argparseimport numpy as npfrom matplotlib import pyplot as pltfrom data import AnnotationTransform, COCODetection, VOCDetection, BaseTransform, VOC_300, VOC_512, COCO_300, COCO_512, \
COCO_mobile_300from layers.functions import Detect, PriorBoxfrom utils.nms_wrapper import nmsimport cv2from data import VOC_CLASSES as labelsfrom collections import OrderedDictimport 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_netelif args.version == ‘RFB_E_vgg’:
from models.RFB_Net_E_vgg import build_netelif args.version == ‘RFB_mobile’:
from models.RFB_Net_mobile import build_net
cfg = COCO_mobile_300else:
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 netimg_dim = int(args.size)num_classes = int(args.num_classes)net = build_net(‘test’, img_dim, num_classes) # initialize detectorstate_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 = 200detector = 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 nowdet_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 passboxes, 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()

​