hot-dog

Here is the whole error information: Traceback (most recent call last): File "/home/xx/anaconda3/envs/py36-1/bin/mmtoir", line 11, in sys.exit(_main()) File "/home/xx/anaconda3/envs/py36-1/lib/python3.6/site-packages/mmdnn/conversion/_script/convertToIR.py", line 192, in _main ret = _convert(args) File "/home/xx/anaconda3/envs/py36-1/lib/python3.6/site-packages/mmdnn/conversion/_script/convertToIR.py", line 92,...

您好，请问如果要用自己的数据训练的话，代码是不是有很多地方需要改动呀，我目前做的改动有配置文件做了相应修改，添加相应的配置项，patchgandiscriminator的输出通道改成了1，还有一些其他的修改没有记录下来。但是目前训练的效果不是太好，请问您当时训练的时候有得到好的结果吗？ @1170300511

请问你们自己训练的时候，训练代码是不是有些地方需要改一下，配置文件有些配置项是缺失的，代码有些地方也是错误的。 @Feynman1999 @Fangzhenxuan

@wjbKimberly @lelechen63 Hi there, i also encountered the same problem. I want to train the ATNet with my own dataset, the landmark data is preprocessed using code extracted from demo.py,...

@haksorus hello, i encountered the same problem, i want to render a top-down orthographic projection view. Did you figure out the issue?

> In the code, they use the perspective projection matrix, which can make the size vary inversely with distance. However, orthographic projection cannot do that. In their cuda code, they...

> @hot-dog Hi, Have you achieved the Orthographic projection with GS? Looking forward to your update. Thank you! sorry, i have not solved the problem mentioned above, i am still...

> > > @hot-dog Hi, Have you achieved the Orthographic projection with GS? Looking forward to your update. Thank you! > > > > > > sorry, i have not...

> > Orthographic > > hi, did your train with Orthographic views or just test rendering with Orthographic views ? @hot-dog Looking forward to your reply, thanks! I am testing...

> > > > Orthographic > > > > > > > > > hi, did your train with Orthographic views or just test rendering with Orthographic views ? @hot-dog...