xiaoquan wang

Why the number of training datasets is less than the number of official nuScene dataset?

2

Hi, I found the number of training datasets is 20096, but the number of offical nuScene datasets is 28119. I am confused why the training number is less than the...

I can't reproduce the result.

2

Hi, The backbone is DLA34. The GPU number is 2 and per-GPU bachsize is 2.The result is below. ````[12/30 19:06:04 tridet.visualizers.d2_visualizer]: Found 2D detection predictions (bbox2d and/or mask2d) for 3769...

ModuleNotFoundError: No module named 'lib.helpers.decorator_helper_level'

3

When I run `python ../../tools/train_val.py --config config_val.yaml`, I get the error as follow. > Traceback (most recent call last): File "../../tools/train_val.py", line 19, in from lib.helpers.trainer_helper import Trainer File "/newnfs/zzwu/08_3d_code/progressive-coordinate-transforms/lib/helpers/trainer_helper.py",...

How to generate each learner's label?

1

How to construct the location loss function? 

TypeError: __init__() got an unexpected keyword argument 'im2col_step'

1

Hi, Thanks for sharing your code. When I run the code, I met the error bellow? Can you help me? My environment is that: cuda==11.2 pytorch=1.9.0 ``` File "/home/CN/zizhang.wu/anaconda3/envs/bevdepth_wxq/lib/python3.7/site-packages/mmcv/cnn/bricks/conv.py", line...

How to decode the depth map from the predicted depth map?

1

Hi, I have a question regarding depth map decoding. The number of predicted depth map's channels is 112, how can I transform it to continuous depth?

allow_unreachable=True) # allow_unreachable flag RuntimeError: derivative for to_sparse is not implemented

1

When I add sparse conv to other code, the error is below. ` Traceback (most recent call last): File "train.py", line 215, in main() File "train.py", line 185, in main...

Why there are many holes and inconsistent regions when exporting the point clouds.

5

Hi, The training set has 207 images while the eval set has 23 images. This is the exporting point clouds. The script is below. ```` ns-export pointcloud --load-config outputs/data_pk2_230_1gpu_ex/nerfacto/2023-02-07_095509/config.yml \...

Hi, I wanted to generate the mask of the Nuscene dataset, but I don't know how to do it. How can I use the [process_nuscenes_masks.py](https://github.com/nerfstudio-project/nerfstudio/blob/main/scripts/datasets/process_nuscenes_masks.py) to generate the mask of...

"gpu_partition - [CreateCommunicator] warn:failed get env VCUDA_PORT "

1

Hi, When I run the comman of "ns-install-cli", I met the error below. ```` [17:33:55] ❌ Completion script generation failed: ['ns-train', '--tyro-print-completion', 'bash'] install.py:107 **gpu_partition - [CreateCommunicator] warn:failed get env...