Winne2GO
Winne2GO
@uminaty the celeA-HQ I use is with 30k images and the model trained over 50k iters produces images without noise, the existing colour shift may be due to the random...
does the noise added to the real input before each layer or only the first layer？thx
Hi @AlexsaseXie @markuspaschi , do you know why the colors of the model in rendered images are different in ubuntu and windows though I have set the color_model to RGBA...
@vardeep-sandhu Did you find out the reason? Thanks
pip install SharedArray
@yufeng9819 Hi, do you know which metrics correspond to those in Tabel 1? '1-NN-CD-acc' and '1-NN-EMD-acc'? 
> 我想请问一下，你们的pkl文件中代表的内容是什么?video_id，tokens_ids，target_ids是什么意思？ If you want to do the inference with your own data, you should preprocess your *.json files with the provided script https://github.com/YehLi/xmodaler/blob/master/tools/msvd_preprocess.py to generate the *.pkl files according...
The new commint https://github.com/KaihuaTang/Scene-Graph-Benchmark.pytorch/commit/81714a337ada463f428b2d0a1521730c5c597571 does not resolve the problem for me? It seems that somewhere before the line 'data_loaders_val = make_data_loader(cfg, mode="test", is_distributed=distributed)' in tools/relation_test_net.py another dataloader of 'custom_eval False...
I want to generate pano images from skybox but I don't know how. Can someone help?
@caiyongqi have you resolved this ?