-
Notifications
You must be signed in to change notification settings - Fork 7.9k
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
How to train YOLOv2 544x544 ? #12
Comments
Simply change these lines in your from
to
If out of memory, then set Also you can train for 416x416 but use with 544x544 or more, for example, 832x832.
|
What needs to change in order to use a pretrained weight with 416x416 to detect with 544x544 or higher? Thanks, |
@kaishijeng To use a pretrained weights with 416x416 to detect with 832x832 - we need changes of the same type in your custom from
to
|
What is the purpose of changing subdivisions form 8 to 64?
Thanks,
…On Sun, Jan 22, 2017 at 2:00 AM, Alexey ***@***.***> wrote:
@kaishijeng <https://github.com/kaishijeng> We need the same changes in
your custom .cfg-file or in default yolo.cfg/yolo-voc.cfg:
from
[net]
batch=64
subdivisions=8
height=416
width=416
to
[net]
batch=64
subdivisions=64
height=832
width=832
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#12 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AMGg3mzBiy0njbxhv29j0_CoWS6qQqMBks5rUyjagaJpZM4Lp8eC>
.
|
@kaishijeng Higher resolution requires more GPU-memory. If you get error "out of memory" then you should decrease |
@AlexeyAB Thanks!! Region Avg IOU: 0.287866, Class: 0.028420, Obj: 0.548111, No Obj: 0.513275, Avg Recall: 0.100000, count: 20 Can I ignore this nan ,and continue train ? |
@matakk If only in some of the lines occurs nan, I think this is normal. Try to detect each type of objects (at least each object once) after 2000-4000 iterations, and if all ok, then you can continue train. Also note, that you should use version not earlier than 10 Jan 2017, where was fixed bug: b831db5 About nan. Nan occurs here, if Line 320 in 2fc5f6d
This may be because: |
As a result:
From:
To:
In details:
And sides will automatically increased from 13 to 34. (changes of the subdivision is only necessary to reduce consumption of GPU-RAM) On image below:
|
If you still want to train Yolo at high resolution 1088x1088, then you can try this, but it does not provide many guarantees of success:
From:
To:
You should get |
I have successfully trained YOLO on 544 * 544, the trick is that training images should be bigger than this size. it sacrifices the speed although, as YOLO authors mentioned on the FPS/mAP curve. |
I tried to detect a relatively small object with Could the reason is that because I have not included images that shows the object from far in the training/validation data-set? |
@VanitarNordic You should not change aspect ratio, use for detection network size 608x608. Object in training-dataset should have the same relative size in %, as in detection-dataset. |
No, I trained the model with The input live video resolution is detection-dataset you mean validation images which used in training process or you mean unseen images when we decide to test the model? |
Detection-dataset is images or video on which you want to detect objects. Did you change network size? What is average relative size of object was:
Yes. |
Okay, I got it. Thanks. Yes I changed the network size to Yes, in the training data-set the object sizes are normal and are not from far, that's correct. in detection-dataset sometimes I was putting the object far from camera and it was unable to detect. I think (as you mentioned correctly) if I want to detect the object by its all scales and conditions, I should add training/validation images which cover these conditions. |
thanks alexeyab!
I want more higher mAP, so YOLOv2 544x544 is best choice ,but there is not have train script and cfg file in darknet, Do you have train this resolution?
The text was updated successfully, but these errors were encountered: