手把手教物体检测——RFBNet
- 下载代码
https://github.com/ruinmessi/RFBNet
- 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：https://s3.amazonaws.com/amdegroot-models/vgg16_reducedfc.pth
- 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()
