Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

代码与文中的描述有冲突 #3

Open
epoch8260 opened this issue May 13, 2022 · 15 comments
Open

代码与文中的描述有冲突 #3

epoch8260 opened this issue May 13, 2022 · 15 comments

Comments

@epoch8260
Copy link

且复现后达不到文中的效果，请提供训练的checkpoint
@ggsDing
Copy link
Owner

ggsDing commented May 13, 2022

Hi,
There are two versions of the segmentation network. ED_FCN is a basic encoder-decoder FCN, while FCN_SR is the described FCN with shape refinement modules. I do not think there are conflicts with the descriptions in the paper.

@epoch8260
Copy link
Author

epoch8260 commented May 13, 2022 via email

@ggsDing
Copy link
Owner

ggsDing commented May 13, 2022

let me check whether I still have them on the servers.

@epoch8260
Copy link
Author

epoch8260 commented May 13, 2022 via email

@ggsDing
Copy link
Owner

ggsDing commented May 13, 2022 •
edited
Loading

I just uploaded a checkpoint of the FCN+SR model (see link below). This is not the specific saved file associated with the results in the paper, but the accuracy should be close.
I will also check if the results can be reproduced with the released codes. Unfortunately, I am already graduated and do not have enough devices, so this could take time.
checkpoint link

@ggsDing
Copy link
Owner

ggsDing commented May 13, 2022

Note that the evaluation codes in this repository are not very rigorous, as the prediction is performed on cropped images. It is suggested to first stitch the cropped masks, and then calculate the final accuracy.

@epoch8260
Copy link
Author

epoch8260 commented May 23, 2022 via email

@jerrywyn
Copy link

I just uploaded a checkpoint of the FCN+SR model (see link below). This is not the specific saved file associated with the results in the paper, but the accuracy should be close. I will also check if the results can be reproduced with the released codes. Unfortunately, I am already graduated and do not have enough devices, so this could take time. checkpoint link

hi, are you sure you have uploaded the right checkpoint file? It's not correspondent to the code you provided.
The error message is:
Missing key(s) in state_dict: "SR.0.weight".............
Unexpected key(s) in state_dict: "DC.0.weight"................

And, which dataset is used to train the checkpoint file?

@Royal-kev
Copy link

谢谢大佬，祝大佬毕业顺利工作顺利
…
---- 回复的原邮件 ---- | 发件人 | @.> | | 日期 | 2022年05月14日 00:49 | | 收件人 | @.> | | 抄送至 | @.@.> | | 主题 | Re: [ggsDing/ASLNet] 代码与文中的描述有冲突 (Issue #3) | I just uploaded a checkpoint of the FCN+SR model (see link below). This is not the specific saved file associated with the results in the paper, but the accuracy should be close. I will also check if the results can be reproduced with the released codes. Unfortunately I am currently graduated and do not have enough device, so this could take time. checkpoint — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

大佬，在复现过程中，遇到了一些问题，方便的话，可以交流一下嘛

@ggsDing
Copy link
Owner

ggsDing commented Aug 15, 2022 •
edited
Loading

I just uploaded a checkpoint of the FCN+SR model (see link below). This is not the specific saved file associated with the results in the paper, but the accuracy should be close. I will also check if the results can be reproduced with the released codes. Unfortunately, I am already graduated and do not have enough devices, so this could take time. checkpoint link

hi, are you sure you have uploaded the right checkpoint file? It's not correspondent to the code you provided. The error message is: Missing key(s) in state_dict: "SR.0.weight"............. Unexpected key(s) in state_dict: "DC.0.weight"................

And, which dataset is used to train the checkpoint file?

Please change the name of modules 'SR->DC' in the model file and the checkpoint will work. This was trained on the Inria Dataset.

@jerrywyn
Copy link

I just uploaded a checkpoint of the FCN+SR model (see link below). This is not the specific saved file associated with the results in the paper, but the accuracy should be close. I will also check if the results can be reproduced with the released codes. Unfortunately, I am already graduated and do not have enough devices, so this could take time. checkpoint link

hi, are you sure you have uploaded the right checkpoint file? It's not correspondent to the code you provided. The error message is: Missing key(s) in state_dict: "SR.0.weight"............. Unexpected key(s) in state_dict: "DC.0.weight"................
And, which dataset is used to train the checkpoint file?

Please change the name of modules 'SR->DC' in the model file and the checkpoint will work. This was trained on the DeepGlobe Dataset.

I tried to use your code to train on the Mas dataset and AIRS (WHU Building) dataset and found that discriminatior only degrades the performance, why is that? My configuration is crop_size=512, batch_size=4.

@ggsDing
Copy link
Owner

ggsDing commented Aug 21, 2022

I just uploaded a checkpoint of the FCN+SR model (see link below). This is not the specific saved file associated with the results in the paper, but the accuracy should be close. I will also check if the results can be reproduced with the released codes. Unfortunately, I am already graduated and do not have enough devices, so this could take time. checkpoint link

hi, are you sure you have uploaded the right checkpoint file? It's not correspondent to the code you provided. The error message is: Missing key(s) in state_dict: "SR.0.weight"............. Unexpected key(s) in state_dict: "DC.0.weight"................
And, which dataset is used to train the checkpoint file?

Please change the name of modules 'SR->DC' in the model file and the checkpoint will work. This was trained on the DeepGlobe Dataset.

I tried to use your code to train on the Mas dataset and AIRS (WHU Building) dataset and found that discriminatior only degrades the performance, why is that? My configuration is crop_size=512, batch_size=4.

Hi, I ran the codes again and confirmed that steady improvements are made on the MAS dataset. Please check the uploaded training script for the MAS dataset in the main directory. It is recommended to remove 'conv3' in the discriminator before training, since the resolution of MAS is lower.

@sunrl1
Copy link

sunrl1 commented Oct 24, 2023

对于MAS把Discriminator里面的conv3删掉之后，效果反而更差了，这是为什么

@Meicarl
Copy link

Meicarl commented Nov 21, 2023

I just uploaded a checkpoint of the FCN+SR model (see link below). This is not the specific saved file associated with the results in the paper, but the accuracy should be close. I will also check if the results can be reproduced with the released codes. Unfortunately, I am already graduated and do not have enough devices, so this could take time. checkpoint link

hi, are you sure you have uploaded the right checkpoint file? It's not correspondent to the code you provided. The error message is: Missing key(s) in state_dict: "SR.0.weight"............. Unexpected key(s) in state_dict: "DC.0.weight"................
And, which dataset is used to train the checkpoint file?

Please change the name of modules 'SR->DC' in the model file and the checkpoint will work. This was trained on the DeepGlobe Dataset.

I tried to use your code to train on the Mas dataset and AIRS (WHU Building) dataset and found that discriminatior only degrades the performance, why is that? My configuration is crop_size=512, batch_size=4.

我在尝试复现代码时遇到了和您相同的问题，并且我已经按照我所理解的、你在issue中所描述的解决步骤尝试，但遗憾的是，我并未能成功。我想这可能是因为有些关键信息或者步骤我可能未能完全理解或注意到，我想寻求您的帮助，能否请您分享您解决问题的具体步骤或者别的关键点？如果方便的话，也期待您能给出关于代码或环境设置部分的更多信息。下面是我导入作者上面发的模型时的报错：
File "D:\Anaconda\envs\ai\lib\site-packages\torch\nn\modules\module.py", line 1604, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for FCN_SR:
Missing key(s) in state_dict: "DC.3.conv1.weight", "DC.3.bn1.weight", "DC.3.bn1.bias", "DC.3.bn1.running_mean", "DC.3.bn1.running_var", "DC.3.conv2.weight", "DC.3.bn2.weight", "DC.3.bn2.bias", "DC.3.bn2.running_mean", "DC.3.bn2.running_var", "DC.4.conv.weight", "DC.4.p_conv.weight",
"DC.4.p_conv.bias", "DC.4.m_conv.weight", "DC.4.m_conv.bias", "DC.5.weight", "DC.5.bias", "DC.5.running_mean", "DC.5.running_var".
Unexpected key(s) in state_dict: "DC.3.conv.weight", "DC.3.p_conv.weight", "DC.3.p_conv.bias", "DC.3.m_conv.weight", "DC.3.m_conv.bias", "DC.4.weight", "DC.4.bias", "DC.4.running_mean", "DC.4.running_var", "DC.4.num_batches_tracked".

@sunrl1
Copy link

sunrl1 commented Nov 24, 2023 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
6 participants
@ggsDing @jerrywyn @Meicarl @Royal-kev @epoch8260 @sunrl1