voxelnet
voxelnet copied to clipboard
This is an unofficial inplementation of VoxelNet in TensorFlow.
Excuse me, has anyone encountered such an error code during compilation? ValueError: './utils/box_overlaps.pyx' doesn't match any files. What's causing this problem? Thanks!
Hello, thank you for sharing your efforts. I tried to run the code as mentioned in the readme and I encountred this error which I'm stuck with for some time...
When i specify the GPUs in `confing.py` as following: ![image](https://user-images.githubusercontent.com/35252861/85357982-2963d200-b545-11ea-9ce2-cc13c99e36b1.png) And the memory occupation of gpu 2,3 is shown as following ![image](https://user-images.githubusercontent.com/35252861/85358165-a131fc80-b545-11ea-8a8b-0d78a2473619.png) Why gpu3 is not used ? What should...
After executing python3 test.py crashes with erroe below Traceback (most recent call last): File "/home/administrator/Documents.orig/Kumar_FileSystem/3D_Object_Detection/voxelnet-master/test.py", line 69, in tags, results, front_images, bird_views, heatmaps = model.predict_step(sess, batch, summary=False, vis=True) File "/home/administrator/Documents.orig/Kumar_FileSystem/3D_Object_Detection/voxelnet-master/model/model.py",...
_np_qint32 = np.dtype([("qint32", np.int32, 1)]) C:\Users\hp\anaconda3\envs\voxelnet\lib\site-packages\tensorflow\python\framework\dtypes.py:532: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as...
While running test.py the following error arises. (After running crop.py) **File "/home/blraml/projectWorkSpace/swaraj/lidar/voxelnet/utils/kitti_loader.py", line 60, in iterate_data assert len(data_tag) == len(f_rgb) == len(f_lidar) , "dataset folder is not correct"** len(data_tag) =...
Can you share how the point cloud range set in the paper is determined?
Hi! I am an undergrad and was trying to implement the Voxelnet paper while I came across your repository. I truly appreciate your work and the effort you put in...
Hi, hoping for some discussion about **parametes setting for pedestrian/cyclist training.** I have trying to train for pedestrian&cyclist detection task, and follwed the original paper set the stride to 1...
If I want train a detector that works for pedestrian and car at the same time, what should I do?