目录
模型介绍
模型使用
下载源码:
在data文件夹下新建VOCdevkit文件夹,导入VOC格式的数据集。如下图:
下载权重文件,放在weights(如果没有就在根目录新建)文件夹下面。
修改voc0712.py里面的类别。
选择配置文件。
删除pycocotools
修改nms_wrapper.py
修改train.py
修改test.py
可视化结果
物体检测模型M2Det,是北京大学&阿里达摩院提出的Single-shot目标检测新模型,使用multi-level特征。在MS-COCO benchmark上,M2Det的单尺度版本和多尺度版本AP分别达到41.0和44.2 。
该模型的特点:
https://github.com/qijiezhao/M2Det”。
将:
VOC_CLASSES = ( '__background__', # always index 0
'aeroplane', 'bicycle', 'bird', 'boat',
'bottle', 'bus', 'car', 'cat', 'chair',
'cow', 'diningtable', 'dog', 'horse',
'motorbike', 'person', 'pottedplant',
'sheep', 'sofa', 'train', 'tvmonitor')
修改为:
VOC_CLASSES = ( '__background__', # always index 0
'aircraft', 'oiltank')
本例采用configs->m2det512_vgg.py配置文件
model = dict(
type = 'm2det',
input_size = 512,
init_net = True,
pretrained = 'weights/vgg16_reducedfc.pth',
m2det_config = dict(
backbone = 'vgg16',
net_family = 'vgg', # vgg includes ['vgg16','vgg19'], res includes ['resnetxxx','resnextxxx']
base_out = [22,34], # [22,34] for vgg, [2,4] or [3,4] for res families
planes = 256,
num_levels = 8,
num_scales = 6,
sfam = False,
smooth = True,
num_classes = 3,#更改类别,按照数据集里面的类别数量+1(背景)
),
rgb_means = (104, 117, 123),
p = 0.6,
anchor_config = dict(
step_pattern = [8, 16, 32, 64, 128, 256],
size_pattern = [0.06, 0.15, 0.33, 0.51, 0.69, 0.87, 1.05],
),
save_eposhs = 10,
weights_save = 'weights/' #保存权重文件的目录
)
train_cfg = dict(
cuda = True,#是否使用cuda
warmup = 5,
per_batch_size = 2,#修改batchsize,按照自己显卡的能力修改
lr = [0.004, 0.002, 0.0004, 0.00004, 0.000004],#学利率调整,调整依据step_lr的epoch数值。
gamma = 0.1,
end_lr = 1e-6,
step_lr = dict(
COCO = [90, 110, 130, 150, 160],
VOC = [100, 150, 200, 250, 300], # unsolve
),
print_epochs = 10,#每个10个epoch保存一个模型。
num_workers= 2,#线程数,根据CPU调整
)
test_cfg = dict(
cuda = True,
topk = 0,
iou = 0.45,
soft_nms = True,
score_threshold = 0.1,
keep_per_class = 50,
save_folder = 'eval'
)
loss = dict(overlap_thresh = 0.5,
prior_for_matching = True,
bkg_label = 0,
neg_mining = True,
neg_pos = 3,
neg_overlap = 0.5,
encode_target = False)
optimizer = dict(type='SGD', momentum=0.9, weight_decay=0.0005)#激活函数。
#修改dataset,本例采用VOC2007数据集,将COCO的删除即可,删除VOC2012
dataset = dict(
VOC = dict(
train_sets = [('2007', 'trainval')],
eval_sets = [('2007', 'test')],
)
)
import os
import os
home = ""#home路径,默认是linux的,本例采用win10,讲其修改为“”
VOCroot = os.path.join(home,"data/VOCdevkit/")
COCOroot = os.path.join(home,"data/coco/")
在安装pycocotools工具前提下,将程序自带的pycocotools工具包删除。
修改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
将:
from .nms.cpu_nms import cpu_nms, cpu_soft_nms
from .nms.gpu_nms import gpu_nms
# def nms(dets, thresh, force_cpu=False):
# """Dispatch to either CPU or GPU NMS implementations."""
# if dets.shape[0] == 0:
# return []
# if cfg.USE_GPU_NMS and not force_cpu:
# return gpu_nms(dets, thresh, device_id=cfg.GPU_ID)
# else:
# return cpu_nms(dets, thresh)
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 = 1)
#return cpu_nms(dets, thresh)
return gpu_nms(dets, thresh)
修改为:
from .nms.py_cpu_nms import py_cpu_nms
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 py_cpu_nms(dets, thresh, method = 1)
return py_cpu_nms(dets, thresh)
修改选定配置的文件
parser.add_argument('-c', '--config', default='configs/m2det512_vgg.py')
修改数据的格式
parser.add_argument('-d', '--dataset', default='VOC', help='VOC or COCO dataset')
然后就可以开始训练了。
parser = argparse.ArgumentParser(description='M2Det Testing')
parser.add_argument('-c', '--config', default='configs/m2det512_vgg.py', type=str)#选择配置文件,和训练的配置文件对应
parser.add_argument('-d', '--dataset', default='VOC', help='VOC or COCO version')
parser.add_argument('-m', '--trained_model', default='weights/M2Det_VOC_size512_netvgg16_epoch30.pth', type=str, help='Trained state_dict file path to open')
parser.add_argument('--test', action='store_true', help='to submit a test file')
修改voc0712.py282行的xml路径。将:
annopath = os.path.join(
rootpath,
'Annotations',
'{:s}.xml')
改为:
annopath = rootpath+'/Annotations/{:s}.xml'
测试结果:
修改demo.py中超参数
parser.add_argument('-c', '--config', default='configs/m2det512_vgg.py', type=str)
parser.add_argument('-f', '--directory', default='imgs/', help='the path to demo images')
parser.add_argument('-m', '--trained_model', default='weights/M2Det_VOC_size512_netvgg16_epoch30.pth', type=str, help='Trained state_dict file path to open')
然后将部分测试图片放到imgs文件夹下面,运行demo.py.