-
PS F:\Shinde\Colorinsight> python -u "f:\Shinde\Colorinsight\facer\main.py"
Traceback (most recent call last):
File "f:\Shinde\Colorinsight\facer\main.py", line 2, in
import functions as f
…
-
https://github.com/CoinCheung/BiSeNet
をFPGA上のCPUで推論させる．
FPGA上にcloneし，pretrainモデルを用いる．
-
I am reading this paper ;and I try to code ,but I find I can not get the result, and the mIoU only is 0.46.I run your code,and get the same result to me.I want to known if you get the same result in p…
-
-
明明只有18个类别，为啥train.py和test.py都设置成下面这样：
```
n_classes = 19
net = BiSeNet(n_classes=n_classes)
```
另外为啥把HQ数据集的background标签去掉了，加上不是正好19个嘛？？
-
请教下bisenet 如何获取hair的稀疏轮廓，训练数据没有hair类别吧？
-
This repository does not support Resnet18 or Xception39 for BiSeNet to achieve realtime semantic segmentation, could you please support this?
-
In the models/BiSeNet.py the line 91, according to the paper, I think the input should be end_points['pool5'], is that right?
- [ ] [论文笔记-BiSeNet：Bilateral Segmentation Network …
-
Hi!, I am only able to get mean IoU: 70.446% for BiSeNet, when R18 is used as a backbone. I have trained BiSeNet on CityScape leftImg8bit folder (used gtFine folder for GT's) with train input image di…