Yizhak Ben-Shabat (Itzik)

Sorry for the delay in response. It corresponds to line 1572 in 'ScanNet/SensReader/c++/src/sensorData.h'. (If you are viewing it using a browser on GitHub, you need to scroll right to see...

Not sure I understand the question. It is designed to work as an independent function. simply `netVLAD.VLAD_pooling()` with the inputs and it should work. Not sure about Keras integration but...

I can not fully understand what is wrong. if it doesn't work, the first thing I would check is an input dimension problem. your input should be of size `BxHxWxC`...

@mathandy well, I am no licensing expert but the method is not mine. I just implemented it as part of my research. I think you need to contact the paper's...

I see you closed this, did you find the problem ? If not, let me know and I will look into it.

It is my experience that it will not be as effective since you will lose the prior knowledge of the spatial connections. Regarding the sum to one. They should be...

I was not able to run this too. Probably a version issue as mentioned above. What I found so far: Pytorch has to be > 1.3 for the torch.promote_types to...

@stevenygd open3d has no attribute geometry. I installed open3d 0.9.0 and it seems to have solved it

You probably solved this already but adding the answer for future users. The first step in the solution would be to convert the rgb image into bytes and then read...

@AAcquier I eventually reimplemented everything in python. I didn't document it properly at the time but I hope this helps: ``` def compute_point_clouds(depth_ins_params, rgb_ins_params, depth_frame, rgb_frame, point_cloud_dir_name): frame_filename, depth_frame_file_extension =...