Seyed Rohollah Hosseyni
Seyed Rohollah Hosseyni
Hi, thank you for your great repository. I think there is an issue in Line 27-28 in src/blocks/PositionalEncoding.py. ``` # Sin/Cos transformation for even, odd indices embeddings[::2] = embeddings[::2].sin() embeddings[1::2]...
Hi, thanks for the great work 1- Are the results in table 1 of paper based on the ground truth lengthes of motions? I did not find length_estimator in eval_t2m_trans_res.py....
Hi, thanks for the great work. I developed an autoregressive model that is somewhat similar to T2M-GPT. However, during sampling, I get better results when `if_categorical=False` compared to `if_categorical=True`, both...
Great work! I really liked it. Could you provide the FID score of your multi-scale VQVAE on ImageNet? I think it was not mentioned in the paper. Thanks.
Great work. Congratulations. Are the cifar10 stats computed here https://drive.google.com/drive/folders/1RvjSE2AZSa7VrB3jh9ACO-ylVs8Q91cs (using pytorch-fid) statistics from cifar10 train set or test set? I downloaded cifar10 and computed both train and test statistics,...
Hi, Can you please provide the reconstruction FID of RVQ on KIT-ML dataset? Thanks
Hi, is progressive training supported?
Congrats for the great work. Could you please provide scripts for video tuning?
Greate work. Congrats. In Fig. 7 of BAMM paper, the blue meshes are corresponding to the blue texts, and the red meshes to the red texts. In Table 5 of...
Hi Ekkasit, Can you please share the code to calculate the FID score without ground truth lengthes? I think the current code in GPT_eval_multi.py calculated the FID score with ground...