Skip to content
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

video importing #10

Closed
alireza-rezaeifard opened this issue Mar 1, 2024 · 7 comments
Closed

video importing #10

alireza-rezaeifard opened this issue Mar 1, 2024 · 7 comments

Comments

@alireza-rezaeifard
Copy link

I import a video to the project to check the license plates in the video, the license plates are recognized in the image, but they are not shown and saved in the software.

@mh-ahmadii
Copy link

Hi,
I have a question. I ran the 'best.pt' model using YOLOv5, and in my experience, it was very slow, and the detection quality was very poor. So, I don't know how to run this code. Is it possible for you to share your Python version and also the version of requirements with me (or any other necessary components) to run this code? I can't run this code on my PC (it's doesn't have a GPU), and when I run it on my laptop (with a 4GB GPU), it runs, but none of the buttons or other functions work.

I'm not sure what I should do.

@mh-ahmadii
Copy link

for me it stuck on the 'Adding AutoShape', this is the CMD log:

E:\Development\ML\smart-resident-guard>python home-yolo.py
YOLOv5 2024-3-3 Python-3.9.0 torch-2.2.0+cpu CPU

Fusing layers...
YOLOv5s summary: 157 layers, 7012822 parameters, 0 gradients, 15.8 GFLOPs
Adding AutoShape...
YOLOv5 2024-3-3 Python-3.9.0 torch-2.2.0+cpu CPU

Fusing layers...
Model summary: 224 layers, 7167184 parameters, 0 gradients
Adding AutoShape...

@alireza-rezaeifard
Copy link
Author

for me it stuck on the 'Adding AutoShape', this is the CMD log:

E:\Development\ML\smart-resident-guard>python home-yolo.py
YOLOv5 2024-3-3 Python-3.9.0 torch-2.2.0+cpu CPU

Fusing layers...
YOLOv5s summary: 157 layers, 7012822 parameters, 0 gradients, 15.8 GFLOPs
Adding AutoShape...
YOLOv5 2024-3-3 Python-3.9.0 torch-2.2.0+cpu CPU

Fusing layers...
Model summary: 224 layers, 7167184 parameters, 0 gradients
Adding AutoShape...

for me is the same this error force me to install linux ubounto and i run it on ubounto
but still not working properly

@mtkarimi
Copy link
Owner

mtkarimi commented Mar 4, 2024

i updated to core, please clone and let me know
if the performance is not good enough please consider the hardware requirements

@mh-ahmadii
Copy link

i updated to core, please clone and let me know if the performance is not good enough please consider the hardware requirements

Thank you so much! It's now working correctly for me.

However, I have another question. I ran this on my laptop, which has a Core i5 6th Gen CPU with 16 GB of RAM and 4 GB of graphics memory (Radeon 530 GDDR3). Despite this, I'm only getting 1, maximum 2 frames per second (FPS), and it's running too slowly, even when I change the source to video file. So do you think the issue is with my system configuration, or could it be related to other factors?

@mtkarimi
Copy link
Owner

mtkarimi commented Mar 5, 2024

i updated to core, please clone and let me know if the performance is not good enough please consider the hardware requirements

Thank you so much! It's now working correctly for me.

However, I have another question. I ran this on my laptop, which has a Core i5 6th Gen CPU with 16 GB of RAM and 4 GB of graphics memory (Radeon 530 GDDR3). Despite this, I'm only getting 1, maximum 2 frames per second (FPS), and it's running too slowly, even when I change the source to video file. So do you think the issue is with my system configuration, or could it be related to other factors?

Happy to hear that you can use it :) please consider these two

  1. Hardware
  2. Retraining with smaller models Training Document

@alireza-rezaeifard
Copy link
Author

thank you for reply
my hardware is :
cpu : intel core i5-12400f
gpu : rtx 3060 dual
ram : 2*8gb corssair 3200

i think it's ok to run this app

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants