Dear author,
I'm running the code step by step ,but when it run at the upblock0 part, after the " self.up_subm = spconv.SparseInverseConv3d(out_filters, out_filters, kernel_size=3, indice_key=up_key,
bias=False)"
I got an error, maybe caused by the shape size.
alueError: C:/Users/runneradmin/AppData/Local/Temp/build-env-lue3nofd/Lib/site-packages/cumm/include\tensorview/check.h(32)
shape_ten[i] == shape[i] assert faild. error shape [9, 19895] expect [27, -1].
BTW, the code in the upblock ,according to the paper image, the sum operate is not used? Sorry, maybe I misunderstanding,
Dear author, I'm running the code step by step ,but when it run at the upblock0 part, after the " self.up_subm = spconv.SparseInverseConv3d(out_filters, out_filters, kernel_size=3, indice_key=up_key, bias=False)"
I got an error, maybe caused by the shape size. alueError: C:/Users/runneradmin/AppData/Local/Temp/build-env-lue3nofd/Lib/site-packages/cumm/include\tensorview/check.h(32) shape_ten[i] == shape[i] assert faild. error shape [9, 19895] expect [27, -1].
BTW, the code in the upblock ,according to the paper image, the sum operate is not used? Sorry, maybe I misunderstanding,