-
In the training step, the detectron increases the CPU memory utilized infinitely. I'm running on gpu, and it takes ~5GB on a GeForce RTX 2080 ti. However, the CPU memory keeps increasing on each train…
-
I want to use this model in C++.
My inputs is video and I want to do Panoramic segmentation on it.
My expected output is Segmented image
-
Hi, @jbehley ,
I know that some script for evaluating panoptic segmentation task is released. Could you give some brief introduction or guideline on how to use it?
THX!
-
instance annotation provided?
-
Hi, could you give me some instructions on how to test on my own images?
Thanks a lot!
-
## ❓ How to do something using DETR
Describe what you want to do, including:
1. what inputs you will provide, if any:
2. what outputs you are expecting:
NOTE:
1. Only general answers are …
-
I get the following error when running dasboard.ipynb in jupyter lab
> ---------------------------------------------------------------------------
TypeError Traceba…
-
Firstly, thanks for great work
and is it too small we set the base_lr: 0.00005 ?
Look forward to your reply.
-
Really nice work! I have a small concern on the implementation details of the relative positional embedding.
This is the **overall random initialization** of the positional embedding:
https://gi…
-
In `log.txt`, I see several errors and losses. I would like to know a bit more about some of them.
I would expect the log file to contain:
- a total loss (`train_loss`),
- the three components to…