Strange points appear when re-train data about deepfashion_try_on

[LZQhardworker]

The code is committed and pushed. 获取 Outlook for iOS<https://aka.ms/o0ukef>

…

________________________________ 发件人: 涵 杨 ***@***.***> 发送时间: Wednesday, December 22, 2021 3:44:05 AM 收件人: switchablenorms/DeepFashion_Try_On ***@***.***>; switchablenorms/DeepFashion_Try_On ***@***.***> 抄送: Mention ***@***.***> 主题: Re: [switchablenorms/DeepFashion_Try_On] Strange points appear when re-train data (#21) Already up to date 获取 Outlook for iOS<https://aka.ms/o0ukef>

________________________________ 发件人: anwarelahi ***@***.***> 发送时间: Wednesday, December 22, 2021 2:26:26 AM 收件人: switchablenorms/DeepFashion_Try_On ***@***.***> 抄送: LZQhardworker ***@***.***>; Mention ***@***.***> 主题: Re: [switchablenorms/DeepFashion_Try_On] Strange points appear when re-train data (#21) @LZQhardworker<https://github.com/LZQhardworker> Where is the update. Can you please share it with me as I am trying to retrain model. ― Reply to this email directly, view it on GitHub<#21 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AN4WX5WYJH6QLUQMEDEGIGTUSDBFFANCNFSM4OUJMO4A>. Triage notifications on the go with GitHub Mobile for iOS<https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android<https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>. You are receiving this because you were mentioned.Message ID: ***@***.***>

[LZQhardworker]

You can simply separate these modules by commenting the codes

[LZQhardworker]

@anwarelahi Hi, how is your training. Is the light point artifact solved in your training?

[LZQhardworker]

You need to have the parsing to inference on custom data. Try to inference on test set first. 获取 Outlook for iOS<https://aka.ms/o0ukef>

…

________________________________ 发件人: anwarelahi ***@***.***> 发送时间: Monday, January 3, 2022 10:38:56 PM 收件人: switchablenorms/DeepFashion_Try_On ***@***.***> 抄送: LZQhardworker ***@***.***>; Mention ***@***.***> 主题: Re: [switchablenorms/DeepFashion_Try_On] Strange points appear when re-train data (#21) [000001_0 (5)]<https://user-images.githubusercontent.com/53229263/147942867-921ce1dc-7eae-490b-bf57-58a5ed66257e.png> This is the result image from try on folder. As you can see on left arm of person it tried something but warped cloth is not appearing. Warped cloth is, [000001_0 (6)]<https://user-images.githubusercontent.com/53229263/147943208-32e16784-f417-4ffc-a7b5-f0bf6bea073e.png> Seems that I am missing something or need to put right .pth files. ― Reply to this email directly, view it on GitHub<#21 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AN4WX5RF2L3U3BOD3DQA57TUUGYIBANCNFSM4OUJMO4A>. Triage notifications on the go with GitHub Mobile for iOS<https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android<https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>. You are receiving this because you were mentioned.Message ID: ***@***.***>

[roman22275]

Hmm.. Looks weird. Can u give me your weights? I will try to examine it

[LZQhardworker]

It might be some problem with the version of the code, we will check it.

[roman22275]

if u can, please contact me [email protected] I have something to discuss

[thotd21]

Hmm.. Looks weird. Can u give me your weights? I will try to examine it

Hi, this is the model used when running inference with an error:
https://drive.google.com/drive/folders/1Qrvn-oRJ7jGE93fOvm-VbNct2d49-w5X?usp=sharing

[LZQhardworker]

You can try to train G3 longer e.g. 200epochs 获取 Outlook for iOS<https://aka.ms/o0ukef>

…

________________________________ 发件人: thotd21 <[email protected]> 发送时间: Thursday, July 23, 2020 9:53:15 AM 收件人: switchablenorms/DeepFashion_Try_On <[email protected]> 抄送: Yang; Han <[email protected]>; Comment <[email protected]> 主题: Re: [switchablenorms/DeepFashion_Try_On] Strange points appear when re-train data (#21) Hmm.. Looks weird. Can u give me your weights? I will try to examine it Hi, this is the model used when running inference with an error: https://drive.google.com/drive/folders/1Qrvn-oRJ7jGE93fOvm-VbNct2d49-w5X?usp=sharing ― You are receiving this because you commented. Reply to this email directly, view it on GitHub<#21 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AN4WX5QPV3E463RJVQMVJ7TR46JYXANCNFSM4OUJMO4A>.

[thotd21]

@HAN-YANG-HIT 👍 I'm retraining a 1000-image data set to shorten the time to reaching 200 epoch, and will check the results later.
Thanks for the feedback.

[LZQhardworker]

batch size should be 8 发送自我的Sony Xperia智能手机

…

---- thotd21编写 ---- @HAN-YANG-HIT<https://github.com/HAN-YANG-HIT> 👍 I'm retraining a 1000-image data set to shorten the time to reaching 200 epoch, and will check the results later. Thanks for the feedback. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub<#21 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AN4WX5R7JDOTGZGMEU5FB63R46LCPANCNFSM4OUJMO4A>.

[thotd21]

Why does batchsize = 8 affect the quality of generated images?
How many cards do you use when training?
with 2 2080 TI cards I only reached the batch size = 4.

And I want to ask a little more about training details:

model G and G2 should be trained with 200 epoches, while model G1 and U net should be trained with 20 epoches

Does it mean I must train all models to 200 epochs, then use G1 and U net at epoch 20th combined with G and G2 at epoch 200th when running inference? Or train to 20 epochs then use G and G2 models as pretrained models for the remain epochs?
Thanks you.

[thotd21]

@HAN-YANG-HIT
When I use a dataset with only 1000 images for training, will it reduce quality when running tests?
In case of reducing the number of images in training, should I need to increase the number of epochs?

[Learningchen]

Hi, I intend to add a new image to the dataset and train it again, but after 20 epochs, the test image has a strange color in the neck:


I use a Google colab for training with Pytorch 1.15.
Do you know this error?
And can you give more information about the python environment which runs out the same as the result in the article?

could you please tell me how to train my own data? for example ,how to only train G1,G2?

[PLXIV]

I would like to know this as well,

Would you be so kind to give some indications please?

[subinst1999]

Hi
can you help in training the model in colab . Can you share the configuration file

[amandazw]

@HAN-YANG-HIT
When I use a dataset with only 1000 images for training, will it reduce quality when running tests?
In case of reducing the number of images in training, should I need to increase the number of epochs?

Hi,did you solve this problem by re-train more times? I got the same problem

[LZQhardworker]

I proposed a solution to this problem. I posted on the update.

[anwarelahi]

@LZQhardworker Where is the update. Can you please share it with me as I am trying to retrain model.

[LZQhardworker]

Already up to date 获取 Outlook for iOS<https://aka.ms/o0ukef>

…

________________________________ 发件人: anwarelahi ***@***.***> 发送时间: Wednesday, December 22, 2021 2:26:26 AM 收件人: switchablenorms/DeepFashion_Try_On ***@***.***> 抄送: LZQhardworker ***@***.***>; Mention ***@***.***> 主题: Re: [switchablenorms/DeepFashion_Try_On] Strange points appear when re-train data (#21) @LZQhardworker<https://github.com/LZQhardworker> Where is the update. Can you please share it with me as I am trying to retrain model. ― Reply to this email directly, view it on GitHub<#21 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AN4WX5WYJH6QLUQMEDEGIGTUSDBFFANCNFSM4OUJMO4A>. Triage notifications on the go with GitHub Mobile for iOS<https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android<https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>. You are receiving this because you were mentioned.Message ID: ***@***.***>

[anwarelahi]

@LZQhardworker Thanks for the updates. Is it possible to execute each module/step separate? like only execute semantic generation module then clothes warping module.

If possible can you please share script for each module or let me know if it can not be.

[anwarelahi]

@anwarelahi Hi, how is your training. Is the light point artifact solved in your training?

Hi, Yes my person image looks fine on sample result but when I use latest .pth files from checkpoints for test, try on is not working on test.py. Can you please suggest what .pth files should be use for testing try on.

[LZQhardworker]

I think latest is used by default. I will check tomorrow, maybe you did not put it in the right folder 获取 Outlook for iOS<https://aka.ms/o0ukef>

…

________________________________ 发件人: anwarelahi ***@***.***> 发送时间: Monday, January 3, 2022 7:34:14 PM 收件人: switchablenorms/DeepFashion_Try_On ***@***.***> 抄送: LZQhardworker ***@***.***>; Mention ***@***.***> 主题: Re: [switchablenorms/DeepFashion_Try_On] Strange points appear when re-train data (#21) @anwarelahi<https://github.com/anwarelahi> Hi, how is your training. Is the light point artifact solved in your training? Hi, Yes my person image looks fine on sample result but when I use latest .pth files from checkpoints for test, try on is not working on test.py. Can you please suggest what .pth files should be use for testing try on. ― Reply to this email directly, view it on GitHub<#21 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AN4WX5UP7PLVVLH6YBFGWOTUUGCTNANCNFSM4OUJMO4A>. Triage notifications on the go with GitHub Mobile for iOS<https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android<https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>. You are receiving this because you were mentioned.Message ID: ***@***.***>

[anwarelahi]

Yes right tried by default latest and others like 200 and 20 too but no luck. I put all those .pth files on checkpoints\label2city folder of both train and inference projects.

[LZQhardworker]

Can you paste the error? 获取 Outlook for iOS<https://aka.ms/o0ukef>

…

________________________________ 发件人: anwarelahi ***@***.***> 发送时间: Monday, January 3, 2022 10:20:17 PM 收件人: switchablenorms/DeepFashion_Try_On ***@***.***> 抄送: LZQhardworker ***@***.***>; Mention ***@***.***> 主题: Re: [switchablenorms/DeepFashion_Try_On] Strange points appear when re-train data (#21) Yes right tried by default latest and others like 200 and 20 too but no luck. I put all those .pth files on checkpoints\label2city folder of both train and inference projects. ― Reply to this email directly, view it on GitHub<#21 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AN4WX5XDKL4Q5CZW7QDDJ6DUUGWCDANCNFSM4OUJMO4A>. Triage notifications on the go with GitHub Mobile for iOS<https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android<https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>. You are receiving this because you were mentioned.Message ID: ***@***.***>

[anwarelahi]

No, not any type of error, instead try on clothes are not appearing on my model image somehow.

[LZQhardworker]

Can you show the results? 获取 Outlook for iOS<https://aka.ms/o0ukef>

…

________________________________ 发件人: anwarelahi ***@***.***> 发送时间: Monday, January 3, 2022 10:23:42 PM 收件人: switchablenorms/DeepFashion_Try_On ***@***.***> 抄送: LZQhardworker ***@***.***>; Mention ***@***.***> 主题: Re: [switchablenorms/DeepFashion_Try_On] Strange points appear when re-train data (#21) No, not any type of error, instead try on clothes are not appearing on my model image somehow. ― Reply to this email directly, view it on GitHub<#21 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AN4WX5SWITGMIWY7KMSJSRDUUGWO5ANCNFSM4OUJMO4A>. Triage notifications on the go with GitHub Mobile for iOS<https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675> or Android<https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>. You are receiving this because you were mentioned.Message ID: ***@***.***>