ShenZheng2000

How long for training

2

Hello, authors! I have a doubt about how long it takes to converge your model. Your manuscript mentions that "The proposed MBLLEN can be quickly converged after being trained for...

Code for L2 Chamfer distance

1

Hello, authors! I would like to know how you obtained the L2 Chamfer distance in Table 2 of your paper. After executing your code on the c3d dataset, I obtained...

Save teacher weight

1

The current code only saves the student' weight. How to save the teacher weight during training?

synthia dataset get unexpected json

1

I preprocess the synthia dataset using your code below. ``` python tools/convert_datasets/synthia.py data/synthia/ --nproc 8 ``` However, the `sample_with_class.json` is empty, as shown below.  Therefore, when I train the...

For cityscapes, there is a function called [cityscapes_classes](https://github.com/lhoyer/DAFormer/blob/77e33108a13d333a4ffc74db1aaaf1bd7f6e88b6/mmseg/core/evaluation/class_names.py#L6) and a function called [cityscapes_palette](cityscapes_palette). Is there such classes or palettes for dark zurich also?

What does the `rank0` suffix in files like `val_epoch0_rank0.json` indicate after training?

Multi-GPU Training Issue

3

Hi, authors! I encounter an issue when training with 8 GPUs. The dataset has been created, and the model has been initialized. However, there is a TypeError shown as below....

Thanks for your nice work. I wonder if you can upload the checkpoints and the script for inference on single images.

Hi, authors! In the paper, you have compared your method with many baselines (e.g., FoldingNet, AtlasNet, PCN, MSN, GRNet, PoinTr, SnowflakeNet, and SoftPoolNet). Could you please provide pretrained weights for...

Hello, authors! I would like to know how long it takes to train your model. Are you using a single GPU, or multiple GPUs?