-
Notifications
You must be signed in to change notification settings - Fork 21.3k
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
Weights only save every 100 iterations until 900, then saves every 10,000 #190
Comments
please see function train_detector in examples/detector.c |
Thank you @pluto16 for this helpful comment. Indeed, line 136 in detector.c describes when the weights should be saved:
|
Hi, |
@zaher88abd At the terminal, cd to the darknet folder and run make to re-compile. |
Thanks. |
This should be post in the readme file, so everyone could reach it before training. |
@pluto16 @shm007g For AlexeyAB Darknet where we can change iterations because there is no Example folder containing detector.c file. |
@ahsan3803 I change to if(i%1==0), suppose will save the file in 1st iteration, but it is no success. |
The code has been changed how could we implement again for every 100 cycle ? @AlexeyAB |
What are we gonna edit ? Edit yolo.c file or detector. c ?? Can anyone inform me pleasE? |
@srhtyldz pretty sure you have to modify the detector.c |
I couldn't find the similar line in the new code . Can you help me please about that issue ? |
@srhtyldz It's still there. Look at darknet/examples/detector.c line 138 |
I changed only this line and it worked. |
Oh I thought you were talking about pjreddie's repo |
Sorry that i did not mention about it. |
Do I need to just |
for AlexeyAB Darknet //if (i % 1000 == 0 || (i < 1000 && i % 100 == 0)) {
#ifdef GPU
#ifdef GPU |
What did you change on this line that worked for you? |
Is it possible to make it a parameter in the .cfg file? @it is a bit inconvenient to rebuild every time before running a new network. |
It's now the lines 383-387 in https://github.com/AlexeyAB/darknet/blob/master/src/detector.c#L383 that need be changed to e.g., like the following, to create a checkpoint every 100 iterations
along with a subsequent invocation of |
@sandipan |
@arielkantorovich every 100 |
Hello,
I am training YOLO on the COCO dataset and I have noticed that the weights only save in increments of 100 until iteration 900. After iteration 900, the next set of saved weights is at iteration 10,000, then 20,000 after that.
Is there a way to change how often weights are saved to $DARKNET_ROOT/backup? I would request there be a variable in cfg/yolo.cfg that allows the user to choose how often weights are saved to backup.
The text was updated successfully, but these errors were encountered: