-
Hey,
Thanks for developing U-2-Net. It works super fast and pretty well. I am currently training it with 50k images ( DUTS- + COCO-dataset).
My train loss is around 0.26 at the moment. Although the …
-
Hello !
Thank you for the paper, really liked it :)
I'm wondering why you decided to monitor validation metrics while training DIS since you didn't do it for U2Net ? Is there a specific reason to …
-
hello, I couldn't find the val part in u2net_train, how to know the quantity of the model without val。
-
u2net-human-seg.pth is 168 MB which is too large. How to slim it?
-
Hello, Thank you for your great work
This U2Net is Excellent and can be extended to some other applications of Computer Vision like Super Resolution and Virtual Try On, If you find these applications…
-
HI,Thanks for your answer. I want to know that whether U2net is suitable for segmentation of small targets. I have trained my datasets which is small objects segmentation,but U2net predicted all 0, No…
-
https://www.paddlepaddle.org.cn/hubdetail?name=U2Net_Portrait
import cv2
import paddlehub as hub
model = hub.Module(name='U2Net_Portrait')
result = model.Portrait_GEN(
images=[cv2.imread('/…
AK391 updated
3 years ago
-
/home/Desktop/my_project/back-end/node_modules/rembg-node/dist/gdown.js:5
function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
…
-
Hi @john-rocky
I made an iOS app called [Lensto](https://apps.apple.com/in/app/lensto-background-changer/id1574844033) that uses U2net, AnimeGanV2, Style Transfer and many other cool filter and ef…
-
First of all, thanks for providing this! The postprocessing of rembg outputs so far seems better than for other rembg plugins I've tried.
I just wanted to note that currently u2net_cloth_seg append…