高峰
> @VVsssssk @Tartisan @chenxyyy Did you also try to test model conversion to trt with pointpillars trained on nuscenes? It fails at converting the model to ONNX. I get this...
> 用pointpillars可以检测X轴正方向上的目标，但是检测不到X轴负方向的目标，把point_cloud_range从[0, -39.68, -3, 69.12, 39.68, 1]调整成[-69.12, -39.68, -3, 69.12, 39.68, 1]还是不行，使用命令如下： > > ``` > python tools/deploy.py configs/mmdet3d/voxel-detection/voxel-detection_openvino_dynamic_kitti.py /home/workspace/mmdetection3d/configs/pointpillars/hv_pointpillars_secfpn_6x8_160e_kitti-3d-3class.py checkpoints/hv_pointpillars_secfpn_6x8_160e_kitti-3d-3class_20220301_150306-37dc2420.pth /home/workspace/tool_collection/point_clouds/no_label.pcd --work-dir work_dir --show --device cuda:0 > ``` >...
hi,i met this problems too!@knazeri my image and mask_image are below: ```   when i use test function,the error occurs: (pytorch) longmao@longmao-dl:~/workspace/edge-connect$ python test.py --checkpoints ./checkpoint/places2 --input ./examples/ownpictures/images/ --mask...
hi,@knazeri,thanks for your answer! i have resized the input image as you said.now the image and mask_image are all(404,700,3)shape and png format.But another error occurs as below: ``` (pytorch) longmao@longmao-dl:~/workspace/edge-connect$...
The code i used to make mask_image is as below: ```python import cv2 image=cv2.imread('/home/longmao/workspace/edge-connect/examples/ownpictures/images/2.png') image=cv2.cvtColor(image,cv2.COLOR_RGB2GRAY) ret,image=cv2.threshold(image,254,255,cv2.THRESH_BINARY) cv2.imwrite("/home/longmao/workspace/edge-connect/examples/ownpictures/masks/2.png", image) ``` @knazeri
Now the code can run well,but the result with pretrained model is not good.My image is below:  My mask_image is below:  The command line used is below: python...
> Same issue here,when the principal rays are parallel to each others,we will get Nan,want to know how to slove this.Any suggestions?
Same issue here,if we already have poses,how can we use this directly which avoid using colmap again?
> Yeah. So, we already have a few different trackers and segmentation methods implemented (ECO, ATOM, DiMP, LWL, etc). So there are plenty of examples how to integrate a new...