-
Notifications
You must be signed in to change notification settings - Fork 8k
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
Can anybody explain cfg file parameters from region layer and net layer and which of them required to changed for training own custom dataset? #933
Comments
|
By the way be carefull with "random=1" last layer parameter, if you use the net with less then 6 "stride by 2" layers and/or size less then 416x416 or not square. This parameter randomly changes input size of the net in hardcoded manner: +-160pix with 32pix step. Not long ago it also contained an error resulting in conversion of any input format to square. So "you should be aware what are you doing". |
|
thanks a lot @AlexeyAB for quick response and links, actually I have already started training my custom data with this darknet fork and given guidelines. I have trained my data with copy of yolo-voc.2.0.cfg , with1500 images for 2000 iterations, I am getting results but predicted bounding box is not very accurate as marked during training .. I need to improve on accuracy of predicted bounding box . From above link I understood I need to recalculate anchors , which other parameters do I have change to improve the accuracy of bounding box. [net]batch=64 [region]anchors = 1.08,1.19, 3.42,4.41, 6.63,11.38, 9.42,5.11, 16.62,10.52 |
Set |
Which parameter is for total no of iterations. |
@dfsaw |
Is there any min images for which i should train my images. My objects are not getting detected corrected |
https://github.com/AlexeyAB/darknet#how-to-improve-object-detection
|
@dfsaw This is total images for 16 iterations. I.e. |
|
|
@dfsaw Use |
@AlexeyAB what should be the batch, subdivision and steps? Foe batch =64 subdivsion 8, I am getting out of memory error |
https://github.com/AlexeyAB/darknet#how-to-improve-object-detection
|
@AlexeyAB my training dataset includes images with smallest size is 182X 53 and biggest size is 704X576 Thanks |
Whit the error CUDA out of memory?
In your case there is no sense to use 608x608. You can use 416x416 and random=1.
What command did you use for calculating anchors? |
Whit the error CUDA out of memory? What command did you use for calculating anchors? |
|
What params did you use in the Makefile, GPU=1? Do you use Yolo v2 with [region] layer instead of Yolo v3 [yolo]-layer? Do you use the latest code of my repository? |
|
Thanks ok sure I will update my code and start training again. |
I updated my darknet latest code , recompiled and started training fresh but still get same issue, crashes at 40th iteration while resizing.
I have just attached image of debugger .
Sent from Mail<https://go.microsoft.com/fwlink/?LinkId=550986> for Windows 10
…________________________________
From: Alexey <notifications@github.com>
Sent: Saturday, June 23, 2018 6:22:06 PM
To: AlexeyAB/darknet
Cc: AvaniPitre; Mention
Subject: Re: [AlexeyAB/darknet] Can anybody explain cfg file parameters from region layer and net layer and which of them required to changed for training own custom dataset? (#933)
@AvaniPitre<https://github.com/AvaniPitre>
* Try to update your code from this repo and recompile. There are some fixes.
* Did you use Yolo_mark to create your dataset?
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub<#933 (comment)>, or mute the thread<https://github.com/notifications/unsubscribe-auth/Ai_z0UUTiJH9joYK2vBBkBs5ettspEVyks5t_jn2gaJpZM4UTCMD>.
|
No description provided.
The text was updated successfully, but these errors were encountered: