Error during training

[lty2226262]

Thanks for you great work!

I set the default parameters and encountered the bug:

gen_resolution_global 128 INFO:root:Creating the network INFO:root:InterpNet - Simple - K=64 INFO:root:Network -- backbone -- 12783956 parameters INFO:root:Network -- projection -- 6498 parameters INFO:root:Network -- Number of parameters 12790454 INFO:root:Getting the dataset INFO:root:Adding random noise INFO:root:Dataset - ShapeNet- None INFO:root:Dataset - len 8751 INFO:root:InterpNet - Simple - K=64 INFO:root:Network -- backbone -- 12783956 parameters INFO:root:Network -- projection -- 6498 parameters 0%| | 0/8751 [00:00<?, ?it/s] Traceback (most recent call last): File "generate.py", line 593, in main(config) File "generate.py", line 379, in main for data in tqdm(gen_loader, ncols=100): File "/home/joey/miniconda3/envs/poco/lib/python3.7/site-packages/tqdm/std.py", line 1195, in iter for obj in iterable: File "/home/joey/miniconda3/envs/poco/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 517, in next data = self._next_data() File "/home/joey/miniconda3/envs/poco/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 557, in _next_data data = self._dataset_fetcher.fetch(index) # may raise StopIteration File "/home/joey/miniconda3/envs/poco/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/joey/miniconda3/envs/poco/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/joey/code/POCO/lightconvpoint/datasets/dataset.py", line 54, in getitem return_data = self.net(data, spatial_only=True) File "/home/joey/miniconda3/envs/poco/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/home/joey/code/POCO/networks/network.py", line 29, in forward net_data = self.net(data, spatial_only=spatial_only) File "/home/joey/miniconda3/envs/poco/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/home/joey/code/POCO/networks/backbone/fkaconv_network.py", line 193, in forward x0 = self.activation(self.bn0(self.cv0(x, pos, pos, data["ids00"]))) File "/home/joey/miniconda3/envs/poco/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/home/joey/code/POCO/lightconvpoint/nn/conv_fkaconv.py", line 65, in forward pos = batch_gather(pos, dim=2, index=neighbors_indices).contiguous() File "/home/joey/code/POCO/lightconvpoint/utils/functional.py", line 13, in batch_gather expanse[dim] = -1 IndexError: list assignment index out of range

However, when we use the ResidualPointnet backbone, there's no errors.