BiSeNet

BiSeNet copied to clipboard

Any suggestions for optimization？

2

any suggestions for optimization? 1. Speed up the reasoning 2. improve the accuracy of segmentation details thx!

laocan

JsutCheng

can you provide inference code of libtorch

4

Thank you.

JJY0710

Have you ever used TRT on Windows

3

Have you ever used TRT on Windows

zhuya1996

Questions about training with customdatasets

17

I made the following changes：  the errror:    I hope someone can help me take a look, how should I modify。Thanks！！！！！！！！！

huangwan-jiayi

why do not set the ignore index 255 to 0??

1

the code pad image through： im = np.pad(im, ((pad_h, pad_h), (pad_w, pad_w), (0, 0))) lb = np.pad(lb, ((pad_h, pad_h), (pad_w, pad_w)), 'constant', constant_values=255) my doubt is, why we not set...

ZuyongWu

Why does the loss function ignore the tag of 255.

5

@CoinCheung Why does the loss function ignore the tag of 255. I look at the data. The label of 255 may be various objects, and each image is almost different....

yeyuxmf

lack F.interpolate in bisenetv1.py

6

in bisenetv1.py class ContextPath lack F.interpolate about avg in line 141, so the result is wrong

qixi666666

Diss Back

4

Hello, I am the author of this paper BiSeNet. First, thanks for your awesome practice. The tricks mentioned in the README file are our common tricks in the implementation of...

yu-changqian

zhuyuanxiang