You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Describe the feature
I suggest that it would be alot better if the installation for this be made a little easier.
I have been working on this algorithm from past one week but the problems dont seem to stop. First the problems were during installation process and had to go through many different process to finally install it. but still the problems were not enough, After that the problems started with it that it has to be specific coco datatset in JSON format but well that is fine and i understand but i would suggest that it make normal JSON format be better. Yet the problems had to still come and now the problem is with Cuda error: Out of memory even with the light version. I am just speechless that even though in the introduction of the algorithm it says that it is indeed better and faster than other but yet the problems are too many and would be alot better if the problems decreased a little.
Thank you Motivation
A clear and concise description of the motivation of the feature.
Ex1. It is inconvenient when installing the SOLOv2 version so i suggest to make it easier to install.
Ex2. I will soon publish my results on this plateform and compare them with YOLO v8 instance segmentation as v8 instance segmentation results are really better for my dataset.
Related resources
If there is an official code release or third-party implementations, please also provide the information here, which would be very helpful.
Additional context
Add any other context or screenshots about the feature request here.
If you would like to implement the feature and create a PR, please leave a comment here and that would be much appreciated.
The text was updated successfully, but these errors were encountered:
Describe the feature
I suggest that it would be alot better if the installation for this be made a little easier.
I have been working on this algorithm from past one week but the problems dont seem to stop. First the problems were during installation process and had to go through many different process to finally install it. but still the problems were not enough, After that the problems started with it that it has to be specific coco datatset in JSON format but well that is fine and i understand but i would suggest that it make normal JSON format be better. Yet the problems had to still come and now the problem is with Cuda error: Out of memory even with the light version. I am just speechless that even though in the introduction of the algorithm it says that it is indeed better and faster than other but yet the problems are too many and would be alot better if the problems decreased a little.
Thank you
Motivation
A clear and concise description of the motivation of the feature.
Ex1. It is inconvenient when installing the SOLOv2 version so i suggest to make it easier to install.
Ex2. I will soon publish my results on this plateform and compare them with YOLO v8 instance segmentation as v8 instance segmentation results are really better for my dataset.
Related resources
If there is an official code release or third-party implementations, please also provide the information here, which would be very helpful.
Additional context
Add any other context or screenshots about the feature request here.
If you would like to implement the feature and create a PR, please leave a comment here and that would be much appreciated.
The text was updated successfully, but these errors were encountered: