WAT
WAT copied to clipboard
wonder for environment
Hi,Thanks for your nice work! I‘am running this project.I have some questions about the code.
====> Epoch: 181 Time: 168.94 TOTAL: 35.0043 MSE: 0.4555 DCT_smooth: 0.0667 Lastframe_smooth: 0.0574 KLD: 10.9880 lr: 0.00080 total samp: 156 ====> Epoch: 182 Time: 162.82 TOTAL: 51.4539 MSE: 0.7225 DCT_smooth: 0.0797 Lastframe_smooth: 0.1789 KLD: 12.7424 lr: 0.00079 total samp: 62
I don't know if this is due to the disappearance of gradient or other reasons, could you tell me the specific configuration of your environment? It's very helpful for me.
And i still want to ask that why can not i training the ntu_rnn dataset?It said that sampling_generator() got an unexpected keyword argument 'is_transi in exp_vae_act.py file.I don't know how to slove these problems and i also cannot find any data about ADE in my csv file,can U upload the complete code ?I am waiting for Ur answer.