Giter Club home page Giter Club logo

Comments (18)

bubbliiiing avatar bubbliiiing commented on June 4, 2024

nms = True

from centernet-pytorch.

fangliang425 avatar fangliang425 commented on June 4, 2024

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.

bubbliiiing avatar bubbliiiing commented on June 4, 2024

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.

fangliang425 avatar fangliang425 commented on June 4, 2024

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.

bubbliiiing avatar bubbliiiing commented on June 4, 2024

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.

bubbliiiing avatar bubbliiiing commented on June 4, 2024

你问的是keras版本么

from centernet-pytorch.

fangliang425 avatar fangliang425 commented on June 4, 2024

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.

bubbliiiing avatar bubbliiiing commented on June 4, 2024

ok,我试试。

from centernet-pytorch.

bubbliiiing avatar bubbliiiing commented on June 4, 2024

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.

fangliang425 avatar fangliang425 commented on June 4, 2024

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.

bubbliiiing avatar bubbliiiing commented on June 4, 2024

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.

bubbliiiing avatar bubbliiiing commented on June 4, 2024

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.

fangliang425 avatar fangliang425 commented on June 4, 2024

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.

bubbliiiing avatar bubbliiiing commented on June 4, 2024

好的加油兄弟

from centernet-pytorch.

JiangZQYW avatar JiangZQYW commented on June 4, 2024

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.

fangliang425 avatar fangliang425 commented on June 4, 2024

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.

JiangZQYW avatar JiangZQYW commented on June 4, 2024

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.

bubbliiiing avatar bubbliiiing commented on June 4, 2024

0 0
NP

from centernet-pytorch.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.