-
Hi all, thank you very much for the incredible work you have doing.
I'm running inference on the validation split of SemanticKITTI by using the following function I added in the SemanticSegmentation …
-
Hello! In **generate_loop_GT_KITTI.py**, why there is **pose = np.linalg.inv(T_cam_velo) @ (pose @ T_cam_velo)**?
I know that _T_cam_velo_ means the transformation matrix from velodyne to camera0,…
-
Thanks for your work. I am really excited to demo it but I'm unable to run the demo.
I am using Ubuntu 18.04 + Cuda 10.1 + CuDNN 7.5.1 + TensorRT 5.1.5 (as per your README and compatibility of ver…
-
Hi, I just ran an evaluation using the pre-trained model of SemanticKitti, the results …
-
I would suggest this schedule,
1. Set previous previous_training_path as empty, config.pre_train as True, config.learning_rate = 1e-2, and train a model for about 200 epochs, but check the segment…
-
Thank you for publishing your code of such an interesting work. I am new to ZSL/G-ZSL, so I am little bit confused about the source of word representations(Word2Vec/GloVe) of the SemanticKITTI dataset…
-
how to solve this error? Thanks!
－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－－
Traceback (most recent call last):
File "downstream_train.py", line 87, in
trainer.fit(model_sem_kitti)
…
-
when i am tring to print each point's label, some points' label are very big such as 65791 , 14286858 , etc. Each scan has about 4000 to 6000 ,some even 8000. Does anybody else come across the same ph…
-
Hi:
Is it feasible to apply this method to the Semantic3D dataset?
Best!
-
when i use this code: python3 train_SemanticKITTI.py --checkpoint_path pretrain_model/checkpoint.tar,
This error will happen: confusion_matrix() takes 2 positional arguments but 3 were given.
coul…