winner-4

我看C-3-Framework中的results_reports中的设置都为3000，我训练自己的模型也需要设置这么大吗？想知道你们都是训练了多少轮次达到了最好的效果，训练一次要好久。

您是从哪借鉴的faster rcnn的结模型结果呢？

Has anyone used the author's pre-trained model to train a downstream task for face parsing? RuntimeError: CUDA error: device-side assert triggered when using multi-GPU training. Has anyone encountered this? Also...

作者你好，我在执行多GPU训练代码是遇到了一些问题，想问下你是否可以看下呢？ 

Hello, I would like to ask if you can provide the inference code of dml_csr? I need to generate pseudo labels for some faces

Hi, could you please provide the codes of semantic_edge for face parsing. Thanks!

你好，我想问下实验中数据预处理都有哪些操作呢？归一化参数是什么？我用这个网络训练loss都是nan，不明白是哪的问题

运行时遇到的环境问题

1

作者你好，我在运行你的代码时遇到了一些环境问题，请问你有遇到过吗？该怎么解决呢？ 

Some questions about the experimental environment

1

Hello author, thank you very much for your outstanding contribution. I would like to ask if it is possible to make an image of the environment you are using and...

When the test code will be open sourced?

2

Hello, thank you for open sourcing this great work. But there seems to be a lack of test code at present. When will the test code be open sourced? I...