-
Notifications
You must be signed in to change notification settings - Fork 3
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
Google colab keeps on crashing while using pyyolo #3
Comments
It might be a google colab issue. Did you try to run it on your local machine because I haven't tested it using Yolov4? Can you ensure you can make it work locally? |
I asked the same to folks at colab. They asked me to ask you guys. I can't
do it on a local machine because my GPU does not support CUDA. It's an
Intel GPU.
…On Fri, Jun 12, 2020 at 12:00 AM Göktuğ Karakaşlı ***@***.***> wrote:
It might be a google colab issue. Did you try to run it on your local
machine because I haven't tested it using Yolov4? Can you ensure you can
make it work locally?
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#3 (comment)>, or
unsubscribe
<https://github.com/notifications/unsubscribe-auth/ALKTD4Z3D2ZUO4CYU4PHIADRWEPDDANCNFSM4N3UYFHQ>
.
|
You actually don't need a GPU to run Darknet. You can compile Darknet without GPU support. For example in Linux, |
Is pyyolo only compatible with yolov3 or works also for yolov4?
…On Fri, 12 Jun, 2020, 1:55 am Göktuğ Karakaşlı, ***@***.***> wrote:
You actually don't need a GPU to run Darknet. You can compile Darknet
without GPU support. For example in Linux,
https://github.com/AlexeyAB/darknet/blob/0a42f8d6144a0a388b1da238fe078af981d07be0/Makefile#L1-L3
if these lines are 1 replace them with 0 and then recompile.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#3 (comment)>, or
unsubscribe
<https://github.com/notifications/unsubscribe-auth/ALKTD4Z7MOGHB5B2RX3T723RWE4UZANCNFSM4N3UYFHQ>
.
|
It just reads weights and configuration, it should work with YOLOv4 too. |
It's just an observation. I tried it with both yolov3 and yolov4 weights
and cfg. The pyyolo works just fine with yolov3 but with yolov4, the
session crashes even before the detection starts. I think it needs to be
tweaked to work with yolov4 weights.
Anyway, it is an amazing tool and keep up.
…On Sun, Jun 14, 2020 at 1:42 PM Göktuğ Karakaşlı ***@***.***> wrote:
It just reads weights and configuration, it should work with YOLOv4 too.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#3 (comment)>, or
unsubscribe
<https://github.com/notifications/unsubscribe-auth/ALKTD44KX26JFAAZV5ZNGG3RWSA5BANCNFSM4N3UYFHQ>
.
|
Can you try with the recent update? Updated it to work with the recent darknet repo, tested with the Yolov4 and it works for me. |
It's working perfectly now with yolov4 weights also.
Thanks for the update.
…On Sat, 20 Jun, 2020, 3:57 pm Göktuğ Karakaşlı, ***@***.***> wrote:
Can you try with the recent update? Updated it to work with the recent
darknet repo, tested with the Yolov4 and it works for me.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#3 (comment)>, or
unsubscribe
<https://github.com/notifications/unsubscribe-auth/ALKTD46JPMO27MD6O3KXZLTRXSFKNANCNFSM4N3UYFHQ>
.
|
The modal keeps on crashing. I am using pyyolo to detect objects in a video. But every time after two detections, the kernel crashes and restarts.
The text was updated successfully, but these errors were encountered: