RuntimeError: setStorage: sizes [175538], strides [0]

[15197307926]

Hi! Thank you for sharing your work. We encountered the following error while visualizing multiple datasets:

7/22 11:18:27 - mmengine - WARNING - The prefix is not set in metric class IndoorMetric_. Loads checkpoint by local backend from path: work_dirs/unidet3d_1xb8_scannet_s3dis_multiscan_3rscan_scannetpp_arkitscenes_baseline/epoch_1018.p th The model and loaded state dict do not match exactly

missing keys in source state_dict: decoder.query_proj.0.weight, decoder.query_proj.0.bias, decoder.query_proj.2.weight, decoder.query_proj.2.bi as

07/22 11:18:30 - mmengine - INFO - Load checkpoint from work_dirs/unidet3d_1xb8_scannet_s3dis_multiscan_3rscan_scannetpp_arkitscenes_baseline/e poch_1018.pth /mnt/mydisk1/A808radar/anaconda3/envs/unidet3d/lib/python3.9/site-packages/mmdet3d/structures/points/base_points.py:136: UserWarning: point got color value beyond [0, 255] warnings.warn('point got color value beyond [0, 255]') 07/22 11:18:33 - mmengine - INFO - Epoch(test) [ 50/1068] eta: 0:01:11 time: 0.0698 data_time: 0.0220 memory: 775 07/22 11:18:36 - mmengine - INFO - Epoch(test) [ 100/1068] eta: 0:01:01 time: 0.0582 data_time: 0.0184 memory: 1375 07/22 11:18:39 - mmengine - INFO - Epoch(test) [ 150/1068] eta: 0:00:56 time: 0.0553 data_time: 0.0167 memory: 1107 07/22 11:18:42 - mmengine - INFO - Epoch(test) [ 200/1068] eta: 0:00:54 time: 0.0657 data_time: 0.0235 memory: 1090 07/22 11:18:45 - mmengine - INFO - Epoch(test) [ 250/1068] eta: 0:00:50 time: 0.0600 data_time: 0.0200 memory: 1323 07/22 11:18:48 - mmengine - INFO - Epoch(test) [ 300/1068] eta: 0:00:47 time: 0.0616 data_time: 0.0193 memory: 2182 Traceback (most recent call last): File "/mnt/mydisk1/A808radar/CSG/yixing/unidet3d/tools/test.py", line 150, in main() File "/mnt/mydisk1/A808radar/CSG/yixing/unidet3d/tools/test.py", line 146, in main runner.test() File "/mnt/mydisk1/A808radar/anaconda3/envs/unidet3d/lib/python3.9/site-packages/mmengine/runner/runner.py", line 1823, in test metrics = self.test_loop.run() # type: ignore File "/mnt/mydisk1/A808radar/anaconda3/envs/unidet3d/lib/python3.9/site-packages/mmengine/runner/loops.py", line 435, in run self.run_iter(idx, data_batch) File "/mnt/mydisk1/A808radar/anaconda3/envs/unidet3d/lib/python3.9/site-packages/torch/utils/contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "/mnt/mydisk1/A808radar/anaconda3/envs/unidet3d/lib/python3.9/site-packages/mmengine/runner/loops.py", line 454, in run_iter outputs = self.runner.model.test_step(data_batch) File "/mnt/mydisk1/A808radar/anaconda3/envs/unidet3d/lib/python3.9/site-packages/mmengine/model/base_model/base_model.py", line 145, in test step return self._run_forward(data, mode='predict') # type: ignore File "/mnt/mydisk1/A808radar/anaconda3/envs/unidet3d/lib/python3.9/site-packages/mmengine/model/base_model/base_model.py", line 346, in run forward results = self(**data, mode=mode) File "/mnt/mydisk1/A808radar/anaconda3/envs/unidet3d/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1501, in call_impl return forward_call(*args, **kwargs) File "/mnt/mydisk1/A808radar/anaconda3/envs/unidet3d/lib/python3.9/site-packages/mmdet3d/models/detectors/base.py", line 86, in forward return self.predict(inputs, data_samples, **kwargs) File "/mnt/mydisk1/A808radar/CSG/yixing/unidet3d/unidet3d/unidet3d.py", line 464, in predict results_list = self.predict_by_feat(x, sp_pts_masks_src, File "/mnt/mydisk1/A808radar/CSG/yixing/unidet3d/unidet3d/unidet3d.py", line 536, in predict_by_feat return self.trim_bboxes_by_superpoints(sp_pts_mask, point, File "/mnt/mydisk1/A808radar/CSG/yixing/unidet3d/unidet3d/unidet3d.py", line 574, in trim_bboxes_by_superpoints sp_inside = scatter_mean(inside_bbox.float(), File "/mnt/mydisk1/A808radar/anaconda3/envs/unidet3d/lib/python3.9/site-packages/torch_scatter/scatter.py", line 51, in scatter_mean count = scatter_sum(ones, index, index_dim, None, dim_size) File "/mnt/mydisk1/A808radar/anaconda3/envs/unidet3d/lib/python3.9/site-packages/torch_scatter/scatter.py", line 21, in scatter_sum return out.scatter_add(dim, index, src) RuntimeError: setStorage: sizes [175538], strides [0], storage offset 0, and itemsize 4 requiring a storage size of 4 are out of bounds for sto rage of size 0

May I ask if there is a solution available? I look forward to your reply. Thank you!

[filaPro]

Hi. Don't remember such an error. Did you try with out provided checkpoint?

[15197307926]

Hi. Don't remember such an error. Did you try with out provided checkpoint? Yes, we encountered the same issue with the checkpoint you provided, and we haven't found an effective solution yet.

[filaPro]

Looks like some issue of torch_scatter. Are using the same version as in our dockerfile?

[15197307926]

Looks like some issue of torch_scatter. Are using the same version as in our dockerfile?

Yes, our torch_scatter is version 2.1.2. We also found that there were no errors when visualizing the validation of the scannet dataset, but this error occurred when validating multiple datasets.