RandLA-Net

RandLA-Net copied to clipboard

How to get the iou of road_marking in paper without rgb for toronto3d?

8

Intuitively， without rgb, road_marking is almost impossible to be segmented correctly like other model (kpconv, TGNet), because there are few differences between road and road_marking on xyz. Are there some...

Nireil

Hi, thank you for your work! I am implementing the network with custom data and I am struggling in the dataloading. I tried cutting squares but I ended up with...

lsaeuro

关于环境配置的问题：sh compile_op.sh

18

胡博士你好，我最近也在跑您的神经网络，但是在进行环境配置sh compile_op.sh的时候，出现了下面的问题： running install running build running build_ext cythoning knn.pyx to knn.cpp /home/nvidia/anaconda3/envs/randlanet2/lib/python3.5/site-packages/Cython/Compiler/Main.py:369: FutureWarning: Cython directive 'language_level' not set, using 2 for now (Py2). This will change in a later...

YAOmmeng

ValueError: need at least one array to concatenate

2

Hi.First python utils/data_prepare_semantic3d.py and then I am running main_Semantic.py but I am getting error as below. Could you please help.? main_Semantic3D.py:89: FutureWarning: elementwise comparison failed; returning scalar instead, but in...

makaay2077

Windows Running error

2

File "D:\Anconda\envs\randla\lib\site-packages\tensorflow\python\ops\script_ops.py", line 209, in __call__ ret = func(*args) File "D:\Anconda\envs\randla\lib\site-packages\tensorflow\python\data\ops\dataset_ops.py", line 514, in generator_py_func values = next(generator_state.get_iterator(iterator_id)) File "main_S3DIS.py", line 114, in spatially_regular_gen cloud_idx = int(np.argmin(self.min_possibility[split])) File "", line...

hongzhiqiang67

模型原理理解问题

1

` def evaluate(self, dataset): # Initialise iterator with validation data self.sess.run(dataset.val_init_op) gt_classes = [0 for _ in range(self.config.num_classes)] positive_classes = [0 for _ in range(self.config.num_classes)] true_positive_classes = [0 for _...

OGitHub-Cj

eglxiang

关于Semantic3D测试结果的问题

18

你好，感谢你提供的代码。最近我在跑RandLA在Semantic3D上的结果时提交到Semantic3D服务器的mIoU在75.5%，我想请问一下最新一版的代码是跑出76.0%的代码还是跑出77.4%的代码呢？

azuki-miho

python utils/6_fold_cv.py, ZeroDivisionError: float division by zero, no /test

6

 Hello, everyone! I meet this problem at the 'python utils/6_fold_cv.py'. I hope someone can help me. Thank you! In addition, I don't build /test at the step 'sh...

lifangyan16

Data preparation and data loader for Toronto-3D dataset (with RGB)

2

Will the dataloader and preparation code for the Toronto-3D become available? I'm very interested in the use of RGB info in the training phase! Is the data prepare code very...

fredpeertje