zhangqijun

in container,cat this /home/neko/.local/share/xorg/Xorg.99.0.log ``` root@121dc6966020:/home/neko/.local/share/xorg# cat Xorg.99.0.log [2060931.348] _XSERVTransmkdir: Owner of /tmp/.X11-unix should be set to root [2060931.348] X.Org X Server 1.19.2 Release Date: 2017-03-02 [2060931.348] X Protocol Version...

1.running on public network. 2.accessing neko through domain [https://pc.zzz9958123.com:99](https://pc.zzz9958123.com:99) 3.I test some, ``` nc -vuz pc.zzz9958123.com 59000-59100 Connection to pc.zzz9958123.com 59000 port [udp/*] succeeded! Connection to pc.zzz9958123.com 59001 port [udp/*]...

I try this one [https://114.244.66.63:99/](https://114.244.66.63:99/) ,same peer disconnect. also try in local network,use [https://192.168.1.237:99/](https://192.168.1.237:99/),same peer disconnect.

It would be better if training code could be released someday.

ascend 910测试可以运行，但是由于动态尺寸问题，体验不太好

First of all,thank you for your help. After I change > train.py line74 from ` distribution = tf.contrib.distribute.MirroredStrategy()` to ` distribution = tf.contrib.distribute.CollectiveAllReduceStrategy(num_gpus_per_worker=1)`. And add ``` import json os.environ["TF_CONFIG"] =...

Stupid Me,I find I use global system proxy.

> @zhangqijun 您好，想问一下您是如何使用[pbaylies/stylegan-encoder](https://github.com/pbaylies/stylegan-encoder)进行获取的？我只看到代码里面是对齐后生成融合图片，没有看到latent的步骤 encode_images.py 就是获取latent