Comments (18)
nms = True
from centernet-pytorch.
nms = True
谢谢回复, 代码没有修改过,centernet.py里的nms确实是True,模型也是链接的‘centernet_resnet50_voc.pth’。
from centernet-pytorch.
那太奇怪了,我再试一下,我并没有修改过,你的测试集确认正确吗
from centernet-pytorch.
那太奇怪了,我再试一下,我并没有修改过,你的测试集确认正确吗
测试集是VOC2007 test,并且全部用于测试,总共是4952个文件。运行你的yolov4-mobilenet,可以得到readme里的mAP。
from centernet-pytorch.
yolov4-mobilenet?这个不是centernet的库吗
yolov4-mobilenet默认是mobilenet0.25本就这么低啊。人家参数就几十万。。
from centernet-pytorch.
你问的是keras版本么
from centernet-pytorch.
yolov4-mobilenet?这个不是centernet的库吗
yolov4-mobilenet默认是mobilenet0.25本就这么低啊。人家参数就几十万。。
我的意思是用的相同的测试集在yolov4-mobilenet项目上能得到相应readme的结果,说明测试集是没问题的。
这个centernet项目里只能得到0.67 mAP,readme里的是0.77.
都是pytorch版本
from centernet-pytorch.
ok,我试试。
from centernet-pytorch.
我试了一下,还是77%
关闭nms是62%,是不是版本不同会影响性能啊。我不太懂。。。
from centernet-pytorch.
我试了一下,还是77%
关闭nms是62%,是不是版本不同会影响性能啊。我不太懂。。。
刚找了旧的GPU,试了下pytorch 1.60, 1.2.0,还有30系显卡上的1.70,都是一样0.67(nms为false 是0.44)的结果。。。请问你是把VOC2007_test里的所有sample都用于测试吗,总共4952个sample。(voc2centernet.py里trainval_percent=0, train_percent=1生成的)
`72.91% = aeroplane AP || score_threhold=0.5 : F1=0.63 ; Recall=46.67% ; Precision=96.38%
75.09% = bicycle AP || score_threhold=0.5 : F1=0.60 ; Recall=43.62% ; Precision=97.35%
63.98% = bird AP || score_threhold=0.5 : F1=0.59 ; Recall=44.23% ; Precision=87.12%
57.96% = boat AP || score_threhold=0.5 : F1=0.46 ; Recall=30.80% ; Precision=90.00%
48.31% = bottle AP || score_threhold=0.5 : F1=0.37 ; Recall=23.03% ; Precision=90.76%
76.97% = bus AP || score_threhold=0.5 : F1=0.70 ; Recall=56.34% ; Precision=90.91%
81.13% = car AP || score_threhold=0.5 : F1=0.66 ; Recall=50.12% ; Precision=97.25%
77.69% = cat AP || score_threhold=0.5 : F1=0.72 ; Recall=61.73% ; Precision=87.70%
49.49% = chair AP || score_threhold=0.5 : F1=0.26 ; Recall=15.08% ; Precision=91.94%
76.38% = cow AP || score_threhold=0.5 : F1=0.54 ; Recall=38.11% ; Precision=93.00%
61.19% = diningtable AP || score_threhold=0.5 : F1=0.38 ; Recall=23.79% ; Precision=90.74%
71.62% = dog AP || score_threhold=0.5 : F1=0.59 ; Recall=43.56% ; Precision=93.42%
82.00% = horse AP || score_threhold=0.5 : F1=0.70 ; Recall=55.17% ; Precision=96.48%
74.64% = motorbike AP || score_threhold=0.5 : F1=0.63 ; Recall=48.00% ; Precision=91.76%
76.86% = person AP || score_threhold=0.5 : F1=0.55 ; Recall=38.60% ; Precision=98.09%
30.12% = pottedplant AP || score_threhold=0.5 : F1=0.07 ; Recall=3.75% ; Precision=94.74%
70.23% = sheep AP || score_threhold=0.5 : F1=0.59 ; Recall=43.80% ; Precision=89.08%
63.93% = sofa AP || score_threhold=0.5 : F1=0.51 ; Recall=35.98% ; Precision=86.87%
78.31% = train AP || score_threhold=0.5 : F1=0.72 ; Recall=58.87% ; Precision=92.74%
70.03% = tvmonitor AP || score_threhold=0.5 : F1=0.54 ; Recall=37.66% ; Precision=96.67%
mAP = 67.94%`
from centernet-pytorch.
我赌五毛钱,是不是你的权值是老权值,你什么时候下载的。
我这里尝试了很多遍确实是77,或者你留个邮箱,我把我的库直接整个发给你。
from centernet-pytorch.
你百度网盘的权值和github的代码重下试试,以前的权值是用rgb图片训练的,后来的权值是用bgr图片训练的
from centernet-pytorch.
问题找到了,原来我把resnet50 的backbone换成了pytorch官方的,导致一部分layer的weight无法载入。😂
感谢一直耐心的回复,也很欣赏这种细致的风格。已经star了
from centernet-pytorch.
好的加油兄弟
from centernet-pytorch.
问题找到了,原来我把resnet50 的backbone换成了pytorch官方的,导致一部分layer的weight无法载入。
感谢一直耐心的回复,也很欣赏这种细致的风格。已经star了
你好,我能看一下你“原来我把resnet50 的backbone换成了pytorch官方的,导致一部分layer的weight无法载入。joy”
的错误代码吗?
邮箱:[email protected]
谢谢
from centernet-pytorch.
问题找到了,原来我把resnet50 的backbone换成了pytorch官方的,导致一部分layer的weight无法载入。
感谢一直耐心的回复,也很欣赏这种细致的风格。已经star了你好,我能看一下你“原来我把resnet50 的backbone换成了pytorch官方的,导致一部分layer的weight无法载入。joy”
的错误代码吗?
邮箱:[email protected]
谢谢
并不会报错,部分weight无法的载入是我的推测,注释部分是载入官方resnet
def resnet50(pretrain = True):
model = ResNet(Bottleneck, [3, 4, 6, 3])
if pretrain:
state_dict = load_state_dict_from_url(model_urls['resnet50'])
model.load_state_dict(state_dict)
features = list([model.conv1, model.bn1, model.relu, model.maxpool, model.layer1, model.layer2, model.layer3, model.layer4])
features = nn.Sequential(*features)
# official resnet50
# from torchvision import models
# model = models.resnet50(pretrained=pretrain)
# features = nn.Sequential(*list(model.children())[: -2])
from centernet-pytorch.
问题找到了,原来我把resnet50 的backbone换成了pytorch官方的,导致一部分layer的weight无法载入。
感谢一直耐心的回复,也很欣赏这种细致的风格。已经star了你好,我能看一下你“原来我把resnet50 的backbone换成了pytorch官方的,导致一部分layer的weight无法载入。joy”
的错误代码吗?
邮箱:[email protected]
谢谢并不会报错,部分weight无法的载入是我的推测,注释部分是载入官方resnet
def resnet50(pretrain = True): model = ResNet(Bottleneck, [3, 4, 6, 3]) if pretrain: state_dict = load_state_dict_from_url(model_urls['resnet50']) model.load_state_dict(state_dict) features = list([model.conv1, model.bn1, model.relu, model.maxpool, model.layer1, model.layer2, model.layer3, model.layer4]) features = nn.Sequential(*features) # official resnet50 # from torchvision import models # model = models.resnet50(pretrained=pretrain) # features = nn.Sequential(*list(model.children())[: -2])
好嘞
from centernet-pytorch.
0 0
NP
from centernet-pytorch.
Related Issues (20)
- 评测指标 HOT 1
- map指标 HOT 2
- RuntimeError: DataLoader worker (pid 57154) is killed by signal: Segmentation fault. HOT 6
- 二分类,训练的val数据的结果一直都是F1=0.17 ; Recall=9.09% ; Precision=100.00%? HOT 6
- 第一次尝试的新手提问 HOT 1
- 结果mAP很小很小,也就1%,这是什么原因啊 HOT 3
- 请问我改mobilenetv3的时候运行到第7批次就自动停止了是怎么回事呢 HOT 3
- 大佬您好!分类效果很差,都是一个类别是什么原因? HOT 8
- ResNet18权重文件 HOT 1
- 请问如何输出mAP_75和mAP_90 HOT 2
- 导儿,可以加入mosaic, mixup数据增强吗? HOT 2
- 关于summery.py中测试CenterNet_HourglassNet HOT 2
- 怎么修改做下游任务比如关键点识别 HOT 1
- 为什么用训练时用测试集验证map为67%,在get_map中用测试集验证达到81%,同一个数据集怎么差别这么大 HOT 7
- 修改input_shape后,还能使用centernet_resnet50_voc.pth预训练权重吗 HOT 4
- 关于hourglassnet
- mAP
- mAP计算过程中预测结果异常 HOT 10
- 改动centernet的head HOT 2
- 视频检测没有框 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from centernet-pytorch.