roomnet
roomnet copied to clipboard
GitBoSun
Not getting correct outputs
Hi, thank you for the code. I followed your instructions and managed to train a model using the vanilla network. However, my test results are not correct. The room classification label is mostly correct, but the layout is almost always wrong. See the examples below...
See my training loss curves below. The classification loss goes down to almost zero but the layout loss is still quite high. Do you know why this might be?
Hi! @ricshaw Can u run this program dicrectly successfully? Did u not encounter this error call "IOError: [Errno 2] No such file or directory: 'rcnn/test/2.npz'"
Hey, I encountered that error too. The author hasn't provided that file, and anyway I think it is just some test code. To make it run I had to comment out the lines from "out=np.load('rcnn/test/2.npz')" up to "os.makedirs(outpath)" in the file get_res.py. I also had to comment the lines at the bottom of get_res.py from "for i in range(20)" to the end of the file.
The run did not succeed although annotated some code according to @ricshaw hints and the following error was prompted.
Not sure what this error means. It looks like you're running out of memory? How much ram do you have on your GPU? Perhaps try reducing the batch size (you'll have to change it in multiple files). Are you running vanilla net? I couldn't get resnet to work.
@ricshaw Can you properly guide us which steps you did till that results.? i mean which instructions of author you follow and how you train this model using the vanilla network.?
I'm also getting these types of outputs when running --test after ~30000 training epochs. My loss numbers are pretty much the same as @ricshaw. Seems very interesting to me that 2 of the 6 points are always very close to another 2 points, makes me think maybe some indices are getting swapped during the training process. I've encountered several other simple bugs in the code so this would be unsurprising to me.
EDIT: perhaps an issue with prepare_data.py? I personally used this script from the nestarz fork to grab and prepare the data.
@ricshaw Hi, I have the similar results with you. I think maybe there are bugs in the code. Have you fixed it?
@SlimeQ, I think your suspicion is right about issue with 'prepare_data.py' file. Its mentioned in the data section of Readme that during data preparation the images are horizontally flip for which 'cv2.flip()' function is used with flipCode = 1 which means vertical flip.
The correction would be using 'cv2.flip()' with flipCode=0 instead of 1.
Please correct me if I'm wrong here.
Note: flipCode argument in 'cv2.flip()' is not same as axis argument in 'np.flip()'
Modification: Apologies for the confusion. cv2.flip() function mentioned in the code is correct. I referred a site which mentioned it incorrectly. @thbupt thanks for pointing it out
@wenc13 @thbupt @DRAhmadFaraz I'm going to have another look at this. Does anyone have the data? They seem to have taken it down.
@wenc13 The link doesn't work anymore. Could you put the data online somewhere? Like Dropbox for example?
@wenc13 @ricshaw The link doesn't work anymore. Could you put the data online somewhere? Like Dropbox for example? thank you very mach it's my email :[email protected]
@ricshaw @wenc13 @xiaochengfuhuo I met the same problem. The link did not work now. Could you send me the data such as image.zip, *.mat, ground truth , my email: [email protected]
@wenc13 @ricshaw @xiaochengfuhuo @Wap8CN Hi guys, I am also working on this code and met with the same problem. The link for the LSUN data set is not working anymore. Could you please share me with the data? The *.mat and ground truth files would suffice. My email: [email protected]. Thank you so much!
https://storage.cloud.google.com/lsun_dataset/lsun_roomnet_dataset.zip 我上次用的的可以的 需要vpn
---Original--- From: "Muhan Zhao"[email protected] Date: Tue, Aug 6, 2019 03:11 AM To: "GitBoSun/roomnet"[email protected]; Cc: "Mention"[email protected];"xiaochengfuhuo"[email protected]; Subject: Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
@wenc13 @ricshaw @xiaochengfuhuo @Wap8CN Hi guys, I am also working on this code and met with the same problem. The link for the LSUN data set is not working anymore. Could you please share me with the data? The *.mat and ground truth files would suffice. My email: [email protected]. Thank you so much!
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or mute the thread.
@xiaochengfuhuo Thanks for the sharing! Eventually, I am switching to another room layout detection code provided in this repo. In my own opinion, the result he has is better than this repo. But thank you anyways.
@run-me No problem at all. Just a reminder that the repo I linked before just provide you a general position of the room layout. You have to write your own code to determine the exact key points from the image generated from his repo. Regarding this, you could take a look at the Physic Inspired Optimization part in this paper to extract the key points.
Hi @kimukook @DRAhmadFaraz @xiaochengfuhuo , How to run inference for the roomnet repo for single image. can you please help me out.
Thank you.
@run-me No problem at all. Just a reminder that the repo I linked before just provide you a general position of the room layout. You have to write your own code to determine the exact key points from the image generated from his repo. Regarding this, you could take a look at the Physic Inspired Optimization part in this paper to extract the key points.
@kimukook if you dont mind, can you explain more. which key points I need to consider? If you have any code snippet please share it.
Thanks
@lakshmankanakala Sorry I can not share my code since this is part of my internship work under NDA. The key points are those 11 types defined in this paper. So for each image, you have to optimize for the best key points position for each room type of those 11 type of rooms. And retrieve the best room layout based on your objective function. You can further refer this part to the Physic Inspired Optimization part of the paper shared in my last comment. Hope it helps :-)
thanks for your quick reply @kimukook , I have seen the paper. I have doubt i need to create those 11 types key points functions and based on the test image i need to correlate between the those 11 types. and then for optimization. Am I correct ? please tell me if I am wrong.
Thanks
@lakshmankanakala No you don't need to create functions for those 11 types. You just need to create one optimization solver which iteratively optimizes the key points for each of those 11 types, e.g. optimize room type 0 and get the best 8 key points from it, then optimize room type 1 then get the best 6 points. For each type you have to initialize the keypoints, iteratively move the keypoint and optimize the overlapping area of wall, ceiling, ground. You might consider the type of edges as well in your optimization.
Thanks @kimukook , I will try to do that optimization. if somewhere I facing the problem then I will ask you.
Thanks @kimukook for providing us with the insight. @lakshmankanakala let me know if you want to do a colab on cracking this keypoint optimization. I will be forking this repo and will be working on solving it over the weekend. Thanks guys :)
@ricshaw Sorry to bother you. i meeting the issue
can you help me to resolve it? thank you!
debug 一下 看下llist里面是什么东西 错误提示你读出的不是整型数据
---Original--- From: "qzj"<[email protected]> Date: Tue, Dec 3, 2019 09:34 AM To: "GitBoSun/roomnet"<[email protected]>; Cc: "Mention"<[email protected]>;"xiaochengfuhuo"<[email protected]>; Subject: Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
@ricshaw Sorry to bother you. i meeting the issue can you help me to resolve it? thank you!
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.
很高兴你能解答我的问题，但是我这里在get_res中debug了一下，lay输出的类型是一个narray，我查的是说新版的numpy有这样的变化 前面要加一个numpy.array(name[label]),但是我这样之后，还是会有同样的结果。
------------------ 原始邮件 ------------------ 发件人: "xiaochengfuhuo"<[email protected]>; 发送时间: 2019年12月3日(星期二) 上午9:38 收件人: "GitBoSun/roomnet"<[email protected]>; 抄送: "__Angel″Qh"<[email protected]>;"Comment"<[email protected]>; 主题: Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
debug 一下 看下llist里面是什么东西 错误提示你读出的不是整型数据
---Original--- From: "qzj"<[email protected]> Date: Tue, Dec 3, 2019 09:34 AM To: "GitBoSun/roomnet"<[email protected]>; Cc: "Mention"<[email protected]>;"xiaochengfuhuo"<[email protected]>; Subject: Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
@ricshaw Sorry to bother you. i meeting the issue can you help me to resolve it? thank you!
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe. — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.
我感觉是l_list的问题 没有输出整型
---Original--- From: "qzj"<[email protected]> Date: Tue, Dec 3, 2019 09:49 AM To: "GitBoSun/roomnet"<[email protected]>; Cc: "Mention"<[email protected]>;"xiaochengfuhuo"<[email protected]>; Subject: Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
很高兴你能解答我的问题，但是我这里在get_res中debug了一下，lay输出的类型是一个narray，我查的是说新版的numpy有这样的变化 前面要加一个numpy.array(name[label]),但是我这样之后，还是会有同样的结果。
------------------ 原始邮件 ------------------ 发件人: "xiaochengfuhuo"<[email protected]>; 发送时间: 2019年12月3日(星期二) 上午9:38 收件人: "GitBoSun/roomnet"<[email protected]>; 抄送: "__Angel″Qh"<[email protected]>;"Comment"<[email protected]>; 主题: Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
debug&nbsp; 一下&nbsp; &nbsp;看下llist里面是什么东西
错误提示你读出的不是整型数据
---Original---
From: "qzj"<[email protected]&gt;
Date: Tue, Dec 3, 2019 09:34 AM
To: "GitBoSun/roomnet"<[email protected]&gt;;
Cc: "Mention"<[email protected]&gt;;"xiaochengfuhuo"<[email protected]&gt;;
Subject: Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
@ricshaw Sorry to bother you. i meeting the issue
can you help me to resolve it? thank you!
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
这是我修改之后的结果 ，c_out是一个整数的数组，但是还是会有这个问题。
------------------ 原始邮件 ------------------ 发件人: "xiaochengfuhuo"<[email protected]>; 发送时间: 2019年12月3日(星期二) 上午9:55 收件人: "GitBoSun/roomnet"<[email protected]>; 抄送: "__Angel″Qh"<[email protected]>;"Comment"<[email protected]>; 主题: Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
我感觉是l_list的问题 没有输出整型
---Original--- From: "qzj"<[email protected]> Date: Tue, Dec 3, 2019 09:49 AM To: "GitBoSun/roomnet"<[email protected]>; Cc: "Mention"<[email protected]>;"xiaochengfuhuo"<[email protected]>; Subject: Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
很高兴你能解答我的问题，但是我这里在get_res中debug了一下，lay输出的类型是一个narray，我查的是说新版的numpy有这样的变化 前面要加一个numpy.array(name[label]),但是我这样之后，还是会有同样的结果。
------------------&nbsp;原始邮件&nbsp;------------------
发件人:&nbsp;"xiaochengfuhuo"<[email protected]&gt;;
发送时间:&nbsp;2019年12月3日(星期二) 上午9:38
收件人:&nbsp;"GitBoSun/roomnet"<[email protected]&gt;;
抄送:&nbsp;"__Angel″Qh"<[email protected]&gt;;"Comment"<[email protected]&gt;;
主题:&nbsp;Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
debug&amp;nbsp; 一下&amp;nbsp; &amp;nbsp;看下llist里面是什么东西
错误提示你读出的不是整型数据
---Original---
From: "qzj"<[email protected]&amp;gt;
Date: Tue, Dec 3, 2019 09:34 AM
To: "GitBoSun/roomnet"<[email protected]&amp;gt;;
Cc: "Mention"<[email protected]&amp;gt;;"xiaochengfuhuo"<[email protected]&amp;gt;;
Subject: Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
@ricshaw Sorry to bother you. i meeting the issue
can you help me to resolve it? thank you!
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
那就不知道了 这个代码我也好久没有弄过了
---Original--- From: "qzj"<[email protected]> Date: Tue, Dec 3, 2019 11:14 AM To: "GitBoSun/roomnet"<[email protected]>; Cc: "Mention"<[email protected]>;"xiaochengfuhuo"<[email protected]>; Subject: Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
这是我修改之后的结果 ，c_out是一个整数的数组，但是还是会有这个问题。
------------------ 原始邮件 ------------------ 发件人: "xiaochengfuhuo"<[email protected]>; 发送时间: 2019年12月3日(星期二) 上午9:55 收件人: "GitBoSun/roomnet"<[email protected]>; 抄送: "__Angel″Qh"<[email protected]>;"Comment"<[email protected]>; 主题: Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
我感觉是l_list的问题&nbsp; 没有输出整型
---Original---
From: "qzj"<[email protected]&gt;
Date: Tue, Dec 3, 2019 09:49 AM
To: "GitBoSun/roomnet"<[email protected]&gt;;
Cc: "Mention"<[email protected]&gt;;"xiaochengfuhuo"<[email protected]&gt;;
Subject: Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
很高兴你能解答我的问题，但是我这里在get_res中debug了一下，lay输出的类型是一个narray，我查的是说新版的numpy有这样的变化 前面要加一个numpy.array(name[label]),但是我这样之后，还是会有同样的结果。
------------------&amp;nbsp;原始邮件&amp;nbsp;------------------
发件人:&amp;nbsp;"xiaochengfuhuo"<[email protected]&amp;gt;;
发送时间:&amp;nbsp;2019年12月3日(星期二) 上午9:38
收件人:&amp;nbsp;"GitBoSun/roomnet"<[email protected]&amp;gt;;
抄送:&amp;nbsp;"__Angel″Qh"<[email protected]&amp;gt;;"Comment"<[email protected]&amp;gt;;
主题:&amp;nbsp;Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
debug&amp;amp;nbsp; 一下&amp;amp;nbsp; &amp;amp;nbsp;看下llist里面是什么东西
错误提示你读出的不是整型数据
---Original---
From: "qzj"<[email protected]&amp;amp;amp;gt;
Date: Tue, Dec 3, 2019 09:34 AM
To: "GitBoSun/roomnet"<[email protected]&amp;amp;amp;gt;;
Cc: "Mention"<[email protected]&amp;amp;amp;gt;;"xiaochengfuhuo"<[email protected]&amp;amp;amp;gt;;
Subject: Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
@ricshaw Sorry to bother you. i meeting the issue
can you help me to resolve it? thank you!
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
非常感谢你的帮助。我最后之得到了一部分结果，好像就只有20张，不知道你当初知道的结果有多少？
------------------ 原始邮件 ------------------ 发件人: "xiaochengfuhuo"<[email protected]>; 发送时间: 2019年12月3日(星期二) 中午11:35 收件人: "GitBoSun/roomnet"<[email protected]>; 抄送: "__Angel″Qh"<[email protected]>;"Comment"<[email protected]>; 主题: Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
那就不知道了 这个代码我也好久没有弄过了
---Original--- From: "qzj"<[email protected]> Date: Tue, Dec 3, 2019 11:14 AM To: "GitBoSun/roomnet"<[email protected]>; Cc: "Mention"<[email protected]>;"xiaochengfuhuo"<[email protected]>; Subject: Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
这是我修改之后的结果
，c_out是一个整数的数组，但是还是会有这个问题。
------------------&nbsp;原始邮件&nbsp;------------------
发件人:&nbsp;"xiaochengfuhuo"<[email protected]&gt;;
发送时间:&nbsp;2019年12月3日(星期二) 上午9:55
收件人:&nbsp;"GitBoSun/roomnet"<[email protected]&gt;;
抄送:&nbsp;"__Angel″Qh"<[email protected]&gt;;"Comment"<[email protected]&gt;;
主题:&nbsp;Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
我感觉是l_list的问题&amp;nbsp; 没有输出整型
---Original---
From: "qzj"<[email protected]&amp;gt;
Date: Tue, Dec 3, 2019 09:49 AM
To: "GitBoSun/roomnet"<[email protected]&amp;gt;;
Cc: "Mention"<[email protected]&amp;gt;;"xiaochengfuhuo"<[email protected]&amp;gt;;
Subject: Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
很高兴你能解答我的问题，但是我这里在get_res中debug了一下，lay输出的类型是一个narray，我查的是说新版的numpy有这样的变化 前面要加一个numpy.array(name[label]),但是我这样之后，还是会有同样的结果。
------------------&amp;amp;amp;nbsp;原始邮件&amp;amp;amp;nbsp;------------------
发件人:&amp;amp;amp;nbsp;"xiaochengfuhuo"<[email protected]&amp;amp;amp;gt;;
发送时间:&amp;amp;amp;nbsp;2019年12月3日(星期二) 上午9:38
收件人:&amp;amp;amp;nbsp;"GitBoSun/roomnet"<[email protected]&amp;amp;amp;gt;;
抄送:&amp;amp;amp;nbsp;"__Angel″Qh"<[email protected]&amp;amp;amp;gt;;"Comment"<[email protected]&amp;amp;amp;gt;;
主题:&amp;amp;amp;nbsp;Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
debug&amp;amp;amp;amp;nbsp; 一下&amp;amp;amp;amp;nbsp; &amp;amp;amp;amp;nbsp;看下llist里面是什么东西
错误提示你读出的不是整型数据
---Original---
From: "qzj"<[email protected]&amp;amp;amp;amp;gt;
Date: Tue, Dec 3, 2019 09:34 AM
To: "GitBoSun/roomnet"<[email protected]&amp;amp;amp;amp;gt;;
Cc: "Mention"<[email protected]&amp;amp;amp;amp;gt;;"xiaochengfuhuo"<[email protected]&amp;amp;amp;amp;gt;;
Subject: Re: [GitBoSun/roomnet] Not getting correct outputs (#6)
@ricshaw Sorry to bother you. i meeting the issue
can you help me to resolve it? thank you!
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
I'm late to the party but I think the prepare_data.py has a bug in line 73. For flipped images is the same equation:
layout[:,:,l_list[ltype]+flip_idx[ltype][i]-1]=guassian_2d(x_mean, y_mean)
I think it should be (but not 100% sure):
layout[:,:,l_list[flip_idx[ltype][i]]=guassian_2d(x_mean, y_mean)
That would skew the results like explained by OP.
@entrpn Can you elaborate what you meant? I also guess there's an issue on the script, but can't figure out how to deal with it. Anyone has an idea?
