Comments (14)
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.
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.
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.
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.
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.
from faster-rcnn-tensorflow-python3.
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.
from faster-rcnn-tensorflow-python3.
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.
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.
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.
from faster-rcnn-tensorflow-python3.
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.
Use English in issues ffs!
from faster-rcnn-tensorflow-python3.
Related Issues (20)
- Didn't get the checkpoint file HOT 2
- ResourceExhaustedError when allocating HOT 1
- 'NoneType' is not iterable: error during training HOT 9
- Unable to find vcvarsall.bat HOT 7
- TypeError: argument of type 'NoneType' is not iterable HOT 1
- AttributeError: 'NoneType' object has no attribute 'astype' HOT 1
- convert the ckpt model to pb model
- if v.name.split(':')[0] in var_keep_dic: TypeError: argument of type 'NoneType' is not iterable HOT 3
- InvalidArgumentError (see above for traceback): Incompatible shapes: [64,8] vs. [0,8]
- [Summary of the question]How to test the model after training? I can't find the .py to test the model.
- AttributeError: module 'lib' has no attribute 'datasets'
- Feature extracted network HOT 1
- How to draw the Recall-IoU curve?
- ModuleNotFoundError: No module named 'lib.utils.cython_bbox' HOT 4
- how to change the number of anchors? HOT 1
- KeError:Chair
- 怎么融合faster rcnn中第一层和第五层的特征作为第五层的输出?
- 请问怎样对视频目标进行检测?
- KeyError: 'image'
- AssertionError: Path does not exist: …………data/VOCdevkit2007/VOC2007/JPEGImages/showImages_(100).jpg
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 faster-rcnn-tensorflow-python3.