-
Notifications
You must be signed in to change notification settings - Fork 3.4k
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.
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
Training time #38
Comments
@cs20162004 Don't forget resize all images to 400x400 manually |
Train with this instead, it has tons of advanced options, auto-cropping, etc: |
@tg-bomze why do I need to resize images to 400x400 manually? |
If you still have training issues, please let me know. |
@xinntao |
GFPGAN network by default uses Real-ESRGAN on regions that don't contain human face (using detection algorithm maybe). But for some images containing face, the generated face image looks unnatural. Like the following: @xinntao do you have any other idea to improve Real_ESRGAN for human face? |
Yes, your understanding is right~ |
These failures are limitations of GFPGAN. We also want to improve Real-ESRGAN's performance on human faces by utilizing more face data. BTW, could you please share with me the original faces that GFPGAN failed in your examples? (Email: xintao.wang@outlook.com) |
Sure. |
@cs20162004 |
@xinntao Thanks a lot for this repository!
It has just been like this for the past 5-6 hours. Will the text on the screen progress further? I am using the "finetune_realesrgan_x4plus.yml" file , making modifications to point to my data directory. I'm running it with 4 GPUs (Tesla P100-SXM2). Please let me know if there's anything I might be doing wrong. |
@Nidish96 Hey I met the same problem, please tell me how it goes if you get any solution |
@Doris1887 I haven't solved it, but I found something. In "train.py" in basicsr, the iterations start in line 154, where the training data (in variable "train_data") is invoked through "prefetcher.next()". This always seems to be "None" and I don't understand why. I've checked the path of the dataset, etc.. |
Hi @xinntao could I ask the license of ESRGAN_SRx4_DF2KOST_official-ff704c30.pth model? |
lower your GPU batch size |
unsubscribe
…---Original---
From: "Cliff ***@***.***>
Date: Thu, Aug 4, 2022 17:55 PM
To: ***@***.***>;
Cc: ***@***.***>;
Subject: Re: [xinntao/Real-ESRGAN] Training time (#38)
lower your GPU batch size
then restart your environment
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>
|
Meaning? |
Hello and thank you for your great work!
You trained ESRNET for 1,000K and ESRGAN for 400K iterations. I was wondering how long did training take in your case with 4 V100 GPU?
I am training with 2 RTX 3090 GPU and training only ESRNET shows 10days 😕 . My training dataset includes FFHQ dataset also (i.e. DIV2K+Flickr2K+FFHQ). Maybe training on FFHQ improves human face result.
Thank you.
The text was updated successfully, but these errors were encountered: