-
Hi,
Thanks for sharing.
I wonder if the pretrained model u2net_portrait.pth is matched with the model in the u2net_portrait_test.py, in this file , the model is net = U2NET(3,1), becase when I run …
-
Thanks for the nice U2Net sharing ! It helps me a lot.
I just run the new released human segmentation model, and got the error below. please enlighten me.
----------------------------------
(an…
-
Congratulations for your amazing work with u2net at
quick question, I'm trying to apply u2net to do segmentation of people. I tried your pre-trained model, the one available at https://github.com/N…
-
it seems that there is a significant quality difference in the output of EGE-unet and u2netp.,even in your test example. If it is in dark night sky, EGE-unet is completely unusable. If that is what ex…
-
目前paddlehub已经支持u2net模型了 paddlex什么时候支持啊
https://www.paddlepaddle.org.cn/hubdetail?name=U2Net&en_category=ImageSegmentation
-
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, 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?
-
# Can't Access Human Segmentation Model Weights
The readme file has the following line
- To run the human segmentation model, please first downlowd the [u2net_human_seg.pth](https://drive.google.c…
-
Hi Xiong,
Recently I am reading that google paper, and I have a issue want to confirm with you.
![image](https://user-images.githubusercontent.com/74944568/180421690-2d793999-36f0-4a1a-9d3d-cce5d5…