RandLA-Net icon indicating copy to clipboard operation
RandLA-Net copied to clipboard

🔥RandLA-Net in Tensorflow (CVPR 2020, Oral & IEEE TPAMI 2021)

Results 156 RandLA-Net issues
Sort by recently updated
recently updated
newest added

Hi ; I want to test the RandLaNet model with a dataset that doesn't contain .labes files ;The labels are both included in the las and txt Files . What...

胡博士,您好! 我的电脑是64G显卡也是2080ti显存是11G,在训练Semantic3D的时候batch_size为4可以运行best_mIoU只能67左右,batch_size为5的时候出现了显存错误。能给点建议吗? ![F286F535BE542C624FFB68D5A87E7AFF](https://user-images.githubusercontent.com/46115914/116236873-27385880-a792-11eb-8623-291fe6763f0f.jpg) ![6{{}5P8ZHS8_7CB}_VX%8C5](https://user-images.githubusercontent.com/46115914/116237073-5c44ab00-a792-11eb-840f-b7dc26fa3959.png)

I only see the code `self.sess.run(dataset.train_init_op)` but cannot find `sess.run(dataset.flat_inputs)`. So how is the code fetching each batch of cloud point without running `sess.run(dataset.flat_inputs)`. Thanks!

## Semantic3D I submitted Semantic3D results and got the following results: - semantic-8: 0.690 - reduced-8: 0.758 ## S3DIS I got the following results and much lower than the paper...

Hi Sir; I just tested the model with another dataset but I get this error message Can you help me solve this problem ![error](https://user-images.githubusercontent.com/62794017/124368950-64bbd500-dc5e-11eb-86ef-1940758b0ab8.jpg)

main_semantic3d.py and tester_Semantic3d.py are all relative path which relative to python(elf).

Why is the number of predicted point cloud tags not equal to the number of point clouds? -------------- ./data/semantic_kitti/dataset/sequences_0.06/25/velodyne/1623230394502471.npy 1623230394502471.label (14316, 3) (26692,) -------------- ./data/semantic_kitti/dataset/sequences_0.06/25/velodyne/1623230394702421.npy 1623230394702421.label (14339, 3) (26729,)

I created docker-image and installed required packages. Pre-trained models downloaded from [here](https://drive.google.com/drive/folders/1iU8yviO3TP87-IexBXsu13g6NklwEkXB) ``` python main_Semantic3D.py --mode test --gpu 0 --model_path=/data/models/Semantic3D/checkpoint Load_pc_0: bildstein_station1_xyz_intensity_rgb Load_pc_1: bildstein_station5_xyz_intensity_rgb Load_pc_2: domfountain_station1_xyz_intensity_rgb Load_pc_3: domfountain_station2_xyz_intensity_rgb Load_pc_4: domfountain_station3_xyz_intensity_rgb...

I have custom dataset without classes to which I want to test on the model which is trained on S3DIS dataset but while I am running main_s3dis.py script in test...

I have run the all network,but the ply file is binary system,I have try a lot of methods to visiualize it,but I failed.Can you give me some advice.Thanks a lot...

help wanted