Error when I use demo.py to visulize result. How can I add images as input?

[ChunZheng2022]

2022-11-04 15:19:40,312 INFO ==> Loading parameters from checkpoint ../output/kitti_models/fspconv80.pth to CPU 2022-11-04 15:19:40,362 INFO ==> Checkpoint trained from version: pcdet+0.6.0+0000000 2022-11-04 15:19:40,411 INFO ==> Done (loaded 653/653) 2022-11-04 15:19:40,586 INFO Visualized sample index: 1 Traceback (most recent call last): File "demo.py", line 112, in main() File "demo.py", line 98, in main preddicts, = model.forward(data_dict) File "/home/lcz/code/platform/openpcdet/pcdet/models/detectors/voxel_rcnn.py", line 11, in forward batch_dict = cur_module(batch_dict) File "/home/lcz/anaconda3/envs/cu113/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl return forward_call(*input, **kwargs) File "/home/lcz/code/platform/openpcdet/pcdet/models/backbones_3d/spconv_backbone_focal.py", line 236, in forward x_image = self.semseg(batch_dict['images'])['layer1_feat2d'] KeyError: 'images'

[yukang2017]

Hi,

The demo function in OpenPCDet currently does no support reading images yet. For this issue you should post it in the official OpenPCDet repo.