Open Byeol-Haneul opened 1 year ago
I do not think operating with dense tensors is the focus of this engine, and therefore I believe I can stick with a temporary solution: convert to SparseTensors, but with a very fine sampling rate. This can be done by rescaling the position info.
Hello, I am trying out the Minkowski-PointNet example provided, but with the GlobalAvgPooling(GAP) layer instead of the GlobalMaxPooling layer. However, when implementing, I found out that the GAP of the TensorField object is not natively supported as shown below.
Adding a snippet of code borrowed from the forward function of MinkowskiGlobalMaxPooling in order to process TensorField object, I found out that the following error rises.
Is there a way to bypass this issue? Or is there something that I have missed out? Thank you in advance.