tdzdog

Can the code for splitting the data be provided? I am aiming to split our custom dataset. But there is still some confusion after reading the paper. To be specific,...

There is no 'val5_full.txt' required by 's3dis_pointweb.yaml' in the provided data and what are the 'train5.txt' and 'val6.txt' used for? Besides, how can I test the 6-folds cross validation?

How to get the results of different heading angles?

1

In the paper, Table 7 provides a result breakdown w.r.t heading angles. However, the waymo open dataset tool does not provide such a breakdown. Hence, how to get such results?

I tried to apply grounded dino on my custom data. However, I am confused about how to input the text or class names? I notice that you take 'dog.stick.' as...

Reproduced results of ViG for different graph types is confusing.

1

I have investigated the influence of graph types for ViG. However, my experiment results are confusing and different from the data in paper. As shown in Table 6, EdgeConv has...

higher performance of ViG

9

I try to train ViG-S on ImageNet and get 80.54% top1 accuracy, which is higher than that in paper, 80.4%. I wonder if 80.4 is the average of multiple trainings?...

I noticed that batchsize=1 is applied for each gpu while the syncbatchnorm is not applied. Wouldn't this lead to inaccurate parameter updates for the BN layer? I have tried to...