-
_Hi @xuebinqin_
I recently created a module to quickly embed U2Net into my project. Maybe it will be useful for someone
https://github.com/kos94ok/bgRemoverApp
-
Hi @xuebinqin, how would you make a model smaller than your full one?
So the full u2net is ~170mb, u2netp ~ 4mb. How can I do ~ 80/40/20 mb model (or some kind of t: 0..1 which makes 4..170 mb mod…
-
hello guys
I'm trying to use backgroundnet in a ROS1 environment.
so i modified the code as follows to receive image_msg from ROS image_publisher.
`img_input = input.Capture(format='rgba8')`
…
-
I'm trying to add a remove background step to my workflow, however I can't seem to find anyway to interface with that extension. Theoretically it would look like this:
```py
result = api.extra_singl…
-
u2net_test.py It took more than 1 second to detect a single image of 2080, but you can see that it is 30 frames in the 1080 test, what is the reason for this?
-
I am a student of Tsinghua University. I want to ask whether u2net only supports single category segmentation. For example, for the picture of people riding on bicycles, can people and bicycles be sep…
-
Hello. I followed the instructions for the windows-main branch and installed for my version of CUDA (12.3 on a 12GB 3060). Then I did the following:
1. I ran the gradio bringing it up into Vivaldi
…
-
hi qin, I open this issue to ask why not use ssim and iou loss which used in BASNet?It seems they are effective in BASBet, shown in Ablation Study part. Could you please tell me why you abandon them i…
-
Hi~Mr Qin，I am coming again....
I retrain u2net on my datasets（9000 pics），the loss value oscillate around 0.2，do you think should I keep training？？（I just train for 1.5 day），I am a little worried tha…
-
I'm using Windows OS and python version 3.8.10
FRAME RATE DETECTED: 25/1 (if this looks wrong, override the frame rate)
FRAME RATE: 25 TOTAL FRAMES: 523
WORKER 0 ONLINE
WORKER FRAMERIPPER ONLI…