aniqueakhtar

> It only works when it is initialized, and does not affect the update. But what is the purpose of this? Why are they initialized to the same weight?

Yes. I got it to work. Looking back at my code now, I see I used this in model.py: ``` self.input_y = tf.placeholder(tf.float32, shape=[self.opts.batch_size, int(self.opts.up_ratio*self.opts.num_point),3]) ``` I trained multiple versions...

Just comparing the two files, I can't see any changes. I trained it on my own dataset. Which I generated with a code that looked similar to this: ``` import...

I was unable to fix the problem. I thought there was a problem in my understanding of the code. But now that you have mentioned that comment in the documentation,...

@dandanaus I don't remember exactly, but I believe I assumed there was a mistake in the **scannet_x8_2048_fps.py** and **s3dis_x8_2048_fps.py** files.

I have been able to get these two dockerfiles to work. Maybe it would be better to include these dockerfiles in the documentation so others can follow it: I added...

Since this topic is still open. This is how I was able to install Minkowski on 3090 Ti using Anaconda: ``` conda create -n py3-mink python=3.8 conda activate py3-mink conda...

I had similar issues. Finally figured out that the CUSTOM Region has just not been implemented in v0.5 yet.

This, please! Can you please share the code on how to generate the training data from meshes and from point cloud ply files. So we can train this network on...

> > Hi，have you solved this problem? I trained lots of methods. I don't remember if I specifically trained this one. The results of all the point-net based methods have...