GithubHelp home page GithubHelp logo

Comments (14)

cooko107 avatar cooko107 commented on July 21, 2024

i met the same question with u and i found that the loss_box always be nan lisk this:
iter: 2 / 40000, total loss: nan

rpn_loss_cls: 0.716178
rpn_loss_box: nan
loss_cls: 3.397649
loss_box: nan

plz tell me if u solve the problem .

from faster-rcnn-tensorflow-python3.

lccate avatar lccate commented on July 21, 2024

I also met the question, because the picture is too big, originally, the size of my picture is about 9801000, i resized it as 512512, it's ok

from faster-rcnn-tensorflow-python3.

XN-0808 avatar XN-0808 commented on July 21, 2024

I also met the question, because the picture is too big, originally, the size of my picture is about 980_1000, i resized it as 512_512, it's ok

This problem may be related to the size of the image, but my image size is normal, but the same problem occurs

from faster-rcnn-tensorflow-python3.

lccate avatar lccate commented on July 21, 2024

I also met the question, because the picture is too big, originally, the size of my picture is about 980_1000, i resized it as 512_512, it's ok

This problem may be related to the size of the image, but my image size is normal, but the same problem occurs

是用的自己的数据集吗,可能是标注的问题,标注的时候注意不要紧贴图片边缘

from faster-rcnn-tensorflow-python3.

XN-0808 avatar XN-0808 commented on July 21, 2024

I also met the question, because the picture is too big, originally, the size of my picture is about 980_1000, i resized it as 512_512, it's ok

This problem may be related to the size of the image, but my image size is normal, but the same problem occurs

是用的自己的数据集吗,可能是标注的问题,标注的时候注意不要紧贴图片边缘

我有点抓狂了,我一共跑了三个数据集,开始的是PascalVOC2007,没问题,第二个数据集出现了pdb问题,确实如你所说的Bbox紧贴边缘,没时间重新标注图片,还好在修改pascal_voc.py和imdb.py代码之后,运行成功。但是在跑第三个数据集的时候又出现了pdb问题,我自认为紧贴边缘的问题已经解决了,现在这个问题又出现了,请问你知道还有可能的原因吗?或者你还在其他数据集上试过吗?
第二个问题就是,这份代码不能计算mAp,你知道怎么修改吗?

from faster-rcnn-tensorflow-python3.

niuniu111 avatar niuniu111 commented on July 21, 2024

from faster-rcnn-tensorflow-python3.

lccate avatar lccate commented on July 21, 2024

I also met the question, because the picture is too big, originally, the size of my picture is about 980_1000, i resized it as 512_512, it's ok

This problem may be related to the size of the image, but my image size is normal, but the same problem occurs

是用的自己的数据集吗,可能是标注的问题,标注的时候注意不要紧贴图片边缘

我有点抓狂了,我一共跑了三个数据集,开始的是PascalVOC2007,没问题,第二个数据集出现了pdb问题,确实如你所说的Bbox紧贴边缘,没时间重新标注图片,还好在修改pascal_voc.py和imdb.py代码之后,运行成功。但是在跑第三个数据集的时候又出现了pdb问题,我自认为紧贴边缘的问题已经解决了,现在这个问题又出现了,请问你知道还有可能的原因吗?或者你还在其他数据集上试过吗?
第二个问题就是,这份代码不能计算mAp,你知道怎么修改吗?

是训练一开始就出现pdb的问题还是训练了几次iteration后才出现这个问题

from faster-rcnn-tensorflow-python3.

niuniu111 avatar niuniu111 commented on July 21, 2024

from faster-rcnn-tensorflow-python3.

XN-0808 avatar XN-0808 commented on July 21, 2024

I also met the question, because the picture is too big, originally, the size of my picture is about 980_1000, i resized it as 512_512, it's ok

This problem may be related to the size of the image, but my image size is normal, but the same problem occurs

是用的自己的数据集吗,可能是标注的问题,标注的时候注意不要紧贴图片边缘

我有点抓狂了,我一共跑了三个数据集,开始的是PascalVOC2007,没问题,第二个数据集出现了pdb问题,确实如你所说的Bbox紧贴边缘,没时间重新标注图片,还好在修改pascal_voc.py和imdb.py代码之后,运行成功。但是在跑第三个数据集的时候又出现了pdb问题,我自认为紧贴边缘的问题已经解决了,现在这个问题又出现了,请问你知道还有可能的原因吗?或者你还在其他数据集上试过吗?
第二个问题就是,这份代码不能计算mAp,你知道怎么修改吗?

是训练一开始就出现pdb的问题还是训练了几次iteration后才出现这个问题

是在训练了几个iteration出现的问题

from faster-rcnn-tensorflow-python3.

lccate avatar lccate commented on July 21, 2024

我是训练一会儿再出现的,我跑的是cityperson数据集,你跑的是这个数据吗

------------------ 原始邮件 ------------------ 发件人: "ccate"[email protected]; 发送时间: 2018年12月10日(星期一) 下午5:26 收件人: "dBeker/Faster-RCNN-TensorFlow-Python3.5"[email protected]; 抄送: "唯y1╮拥有"[email protected]; "Author"[email protected]; 主题: Re: [dBeker/Faster-RCNN-TensorFlow-Python3.5] I met a strangequstion,and don't know how to fix it,I hope to get your help,Thanks (#29) I also met the question, because the picture is too big, originally, the size of my picture is about 980_1000, i resized it as 512_512, it's ok This problem may be related to the size of the image, but my image size is normal, but the same problem occurs 是用的自己的数据集吗,可能是标注的问题,标注的时候注意不要紧贴图片边缘 我有点抓狂了,我一共跑了三个数据集,开始的是PascalVOC2007,没问题,第二个数据集出现了pdb问题,确实如你所说的Bbox紧贴边缘,没时间重新标注图片,还好在修改pascal_voc.py和imdb.py代码之后,运行成功。但是在跑第三个数据集的时候又出现了pdb问题,我自认为紧贴边缘的问题已经解决了,现在这个问题又出现了,请问你知道还有可能的原因吗?或者你还在其他数据集上试过吗? 第二个问题就是,这份代码不能计算mAp,你知道怎么修改吗? 是训练一开始就出现pdb的问题还是训练了几次iteration后才出现这个问题 — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or mute the thread.

把data/cache/里面的pkl文件删掉再重新跑一下试试

from faster-rcnn-tensorflow-python3.

lccate avatar lccate commented on July 21, 2024

I also met the question, because the picture is too big, originally, the size of my picture is about 980_1000, i resized it as 512_512, it's ok

This problem may be related to the size of the image, but my image size is normal, but the same problem occurs

是用的自己的数据集吗,可能是标注的问题,标注的时候注意不要紧贴图片边缘

我有点抓狂了,我一共跑了三个数据集,开始的是PascalVOC2007,没问题,第二个数据集出现了pdb问题,确实如你所说的Bbox紧贴边缘,没时间重新标注图片,还好在修改pascal_voc.py和imdb.py代码之后,运行成功。但是在跑第三个数据集的时候又出现了pdb问题,我自认为紧贴边缘的问题已经解决了,现在这个问题又出现了,请问你知道还有可能的原因吗?或者你还在其他数据集上试过吗?
第二个问题就是,这份代码不能计算mAp,你知道怎么修改吗?

是训练一开始就出现pdb的问题还是训练了几次iteration后才出现这个问题

是在训练了几个iteration出现的问题

把data/cache/里面的pkl文件删掉再重新跑一下试试

from faster-rcnn-tensorflow-python3.

niuniu111 avatar niuniu111 commented on July 21, 2024

from faster-rcnn-tensorflow-python3.

XN-0808 avatar XN-0808 commented on July 21, 2024

I also met the question, because the picture is too big, originally, the size of my picture is about 980_1000, i resized it as 512_512, it's ok

This problem may be related to the size of the image, but my image size is normal, but the same problem occurs

是用的自己的数据集吗,可能是标注的问题,标注的时候注意不要紧贴图片边缘

我有点抓狂了,我一共跑了三个数据集,开始的是PascalVOC2007,没问题,第二个数据集出现了pdb问题,确实如你所说的Bbox紧贴边缘,没时间重新标注图片,还好在修改pascal_voc.py和imdb.py代码之后,运行成功。但是在跑第三个数据集的时候又出现了pdb问题,我自认为紧贴边缘的问题已经解决了,现在这个问题又出现了,请问你知道还有可能的原因吗?或者你还在其他数据集上试过吗?
第二个问题就是,这份代码不能计算mAp,你知道怎么修改吗?

是训练一开始就出现pdb的问题还是训练了几次iteration后才出现这个问题

是在训练了几个iteration出现的问题

把data/cache/里面的pkl文件删掉再重新跑一下试试

我试过了行不通,难道真的要resize再重新标注吗。。。。。。

from faster-rcnn-tensorflow-python3.

dBeker avatar dBeker commented on July 21, 2024

Use English in issues ffs!

from faster-rcnn-tensorflow-python3.

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.