Zhengyang Feng

The performance should be reproduceable from my provided shells. Although if you use different PyTorch versions and NVIDIA's apex, it could lead to problems like gradient explosions. Could you give...

@wing212 Firstly, if you are using PyTorch >= 1.6, You best use the master branch. Also a clear environment without the standalone apex package. I suspect the problem is from...

@wing212 Great! Let me know if you still can't reproduce results. FYI, the std for Cityscapes 1/30 experiments is 2.56 in my records.

> > @wing212伟大！如果您仍然无法重现结果，请告诉我。仅供参考，在我的记录中，Cityscapes 1/30实验的标准是2.56。 > > Thank you, I will keep trying. I would like to ask what is 2.56? STD (标准差)

@wing212 Actually, your results look fine. I did get a 57.24 for city-30-1, that is why we need to take averages in these experiments (the STD is quite large). My...

But it looks like you have sid=2 for the voc experiment, do check the dataset and data splits if you can't get similar avg from 3 runs.

@grbcwq123 Hi! Does your dataset has 4 classes? You should first convert the coco pre-trained weights with customized scripts, specifically, change the codes [here](https://github.com/voldemortX/DST-CBC/blob/53853f63033fdb88206828a72d960de2c03efd69/segmentation/convert_coco_resnet101.py#L14) to your number of classes. I've...

@grbcwq123 It seems by the first line warning your apex is not correctly installed. I'd say maybe use a new virtual environment to reinstall the dependencies？The exact cuda and torch...

@TiankaiHang Hi! Thanks for your attention in our work! > * Will your model extended to Parallel (distributed data-parallel) in the future. I'd love to do that, but I have...

You're welcome. I'll pin this issue as a call for help to: - [x] Support multi-GPU training #9 - [ ] Support newer models such as DeepLabV3+