Henry Zheng

> I have also seldom encountered such cases recently, and maybe we will have a closer look at this issue. At the same time, we welcome more cues/information about this...

### Solution For quick solution just replace the following lines to the code below https://github.com/OpenRobotLab/EmbodiedScan/blob/67110231a8759009ca822ff3f2b3ed577674903b/embodiedscan/datasets/embodiedscan_dataset.py#L59-L64 Make sure to install SharedArray in your environment #### Code: super().__init__(ann_file=ann_file, metainfo=metainfo, data_root=data_root, pipeline=pipeline, test_mode=test_mode,...

Thank you! Cuz I am curious whether there's a difference between our config settings or due to experiment variance.

In the grounder decoder file, change the following lines in predict function in sparse_featfusion_grounder [L532-L533](https://github.com/OpenRobotLab/EmbodiedScan/blob/89aca6fb0e2df01786d0a60a369ad48d585d3f22/embodiedscan/models/detectors/sparse_featfusion_grounder.py#L532-L533) to the following code ``` tokens_positive = [[[[0, 1]]] for _ in range(len(batch_data_samples))] ```

Hi @mxh1999 @Tai-Wang Moreover, I would like to ask if the results in the paper refer to the private split used by the test server, or the publicly available validation...

Same here, the full version indeed takes awhile to run. This is likely to be caused by dataloader initialization where preprocessing procedures are done such as matching the language descriptions...