MilkClouds

### Solution I'm trying So, to resolve this problem I tried this things (since I am currently dealing with this problem, this sections will be updated continuously) I think fundamental...

I copied `predict_original_samples` function from `torch-points3d/torch_points3d/datasets/segmentation/forward/shapenet.py` to `torch-points3d/torch_points3d/datasets/segmentation/shapenet.py` error above is solved. but error below occur ``` Traceback (most recent call last): File "forward_scripts/forward.py", line 113, in main run(model, dataset,...

Is this issue completed? Is there anything remaining to implement? Will it be merged?

Warning: 6 star filter in `modules/core/src/main/kotlin/com/waicool20/wai2k/script/modules/ScriptModule.kt` is hardcoded temporarily.

I've solved lcuda not found issue, on WSL2 by executing `ln -s /usr/lib/wsl/lib/libcuda.so ~/anaconda3/envs/(your env)/lib/libcuda.so` may be helpful to someone.

In my opinion, simply not using base64 would not resolve https://github.com/gradio-app/gradio/issues/2635, since it is not because of base64; it is because of image encoding logic of pillow. If gradio use...

I experience same phenomena(deadlock over 30 minute) on `dyhead/atss_swin-l-p4-w12_fpn_dyhead_mstrain_2x_coco.py`, only on distributed learning(and more than 1 gpu) setting. 1 gpu training is okay.

## (New) Error report and analysis Hi, I had different type of error but seems to occur because of same reason. I ran `bash tools/dist_train.sh configs/mask_rcnn/mask_rcnn_r50_fpn_1x_wandb_coco.py 2` and met error...

What dataset did you use for your thermal data? Did you use LLVIP in the paper?

No stack information on torch 2.2.0, but `experimental_config` works.