-
File "C:\Users\Amir\anaconda3\envs\frankmocap\lib\runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "C:\Users\Amir\anaconda3\envs\frankmocap\lib\runpy.py", line 85, in _…
-
作者您好，我在复现您的代码时，发现您的cityscapes_info.json文件中除了trainid=255外，还有一个trainid=-1的分类。然而前面已经有了0-18个trainid，正好为n_classes=19，那么这里trainid=-1的类起到了什么作用呢？
-
There are some errror:
```
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/keras/utils/data_utils.py", line 678, in _data_generator_task
self.queue.put((Tru…
-
```
[W reducer.cpp:347] Warning: Grad strides do not match bucket view strides. This may indicate grad was not created according to the gradient layout contract, or that the param's strides changed s…
-
**Describe the bug**
For "sky" class the Class_Id to train_Id in your description is 17 : 0, However, I did not find the annotation of sky's class id when I actually processed the image
**To Repro…
-
I've noticed some naming inconsistencies across the torchvision datasets when it comes to specifying how to split the dataset (train/val/test). We currently have:
- Team `classes`: [LSUN](https://g…
-
Hi!
First of all, thanks for sharing your very helpful code.
Following the _README.md_, I have downloaded _icnet.npy_ from Google Drive link to the _model/cityscapes_ folder.
However, when I…
-
Traceback (most recent call last):
File "/home/zhoukaiyu/anaconda3/envs/rdrnet/lib/python3.8/site-packages/mmengine/registry/build_functions.py", line 122, in build_from_cfg
obj = obj_cls(**ar…
-
MAC os
Pycharm
源码：
from mmseg.apis import inference_segmentor, init_segmentor
import mmcv
import torch
print(torch.version.cuda)
config_file = r'/Users/wenjun/pythonProject/mmsegmentation-mas…
-
我压根编译的时候没选rt
PS E:\projects\seg\cpp\building\Release> .\test_seg.exe --model_dir=./pp_liteseg_infer_model --img_path=./cityscapes_demo.png --devices=GPU
WARNING: Logging before InitGoogleLogging() i…