develop

Hi, I can not download the TU-berlin and sketchy dataset from the link you provided. Can you help me to download this two datasets?

> puter, just in case. Thank you! I just download the TU-Berlin and sketchy datasets by another means.

> hello could you please give a sample class_labels.txt for me, thanks Hi, do you get the labels.txt？Would you mind providing me with a txt file?

> I got 0.363 map, but I use the semantic_label released by the author. Hi. Have you made any changes to the code?I just got 0.3294 map.I have not made...

> When I use multiple GPUs to train basicvsr, this warning is reported and it keeps getting stuck. How to solve it? command to run： ./tools/dist_train.sh ./configs/restorers/basicvsr/basicvsr_reds4.py 2 UserWarning: Setting...

> 什么意思？你要写？ 想用你的这个repo里的模型水一篇本科毕业论文，但是想认真读一读关于这个模型相关的参考文献。所以想问一下大佬做这个模型的时候参考的有关的文献。谢谢！

> Hello, You should add the following parameter when initialising the vit_large: `model = vit_large(patch_size=14, img_size=518)` This is because we published weights of models trained on images of size 518x518...

> I have also encountered the same problem. Have you found the reason? hi, you can calculate it in the following ways: $$ N_{patch} = size_{img} * size_{img} / (size_{patch}...

>  大佬，我用你给的densenet权重训练出现了这个问题，这是为什么呢 请问是修改_classes.txt里面只保留car这一个类吗？ 我的毕设也是检测车，如果可行的话我就重新训练一次 或者有没有办法在预测和评估的时候只保留一个类

I think: Firstly, the hidden variable is obtained through VAE encoding, and after a forward process, noise is added to 100 time step (z_t can be obtained at any time...