-
ghost updated
4 years ago
-
我下载了你们的NYUD的数据集,发现里面只有训练集的边缘groundtruth图像,而没有测试集的groundtruth
-
I dont understand that line: fake_labels = self.labels + self.no_classes -self.labels , this simplify to fake_labels=self.no_classes, why writting **fake_labels = self.labels + self.no_classes -self.l…
-
when I train your model,mean iou
-
I see you ignore label '255' in your code, and num_classes of NYUD is 40. So the label '0' means 'wall', and '39' means 'otherprop', right? Unlabeled class is '255'?
-
我有个制作样本的想法,把nyud_cropped做语义分割的样本,通过对训练样本做canny识别,成这样
![image](https://user-images.githubusercontent.com/45627764/52040458-67d4a780-2572-11e9-8f00-9259c3242d13.png)
![image](https://user-images.githu…
-
Do you train your network with this nyud_layers.py?
When I train your network on scannet dataset, the output of your network is 116x156, it is not same as label size(100x100)? They don't match, so I …
-
Before you open an issue, please make sure you have tried the following steps:
1. Make sure your **environment** is the same with (https://mace.readthedocs.io/en/latest/installation/env_requirement…
-
Hi, thanks for your code. I try to reproduce your work by Pytorch on NYUD dataset. But only got MeanIOU: 0.435 using single scale evaluation. It improves the accuracy of RGBonly RefineNet slightly, fa…
-
```
http://0d.kebhana.mx:443/announce
http://104.28.1.30:8080/announce
http://104.28.16.69/announce
http://107.150.14.110:6969/announce
http://109.121.134.121:1337/announce
http://114.55.113.60:…