ggsonic
ggsonic
this is my tensorboard graph. i use your provided dataset and your default hyperparams. batch 32,lr 0.001,200 epochs,trained for 8 hours using one single gpu card to get the above...
committed! actually it is a simple idea and simple change.
according to @barronalex 's code, the frames should be reshaped to output multiple non-overlapping frames at each time step. then in eval.py, reshape these frames back to the normal overlapping...
@candlewill not exactly. A simple tf.reshape handling above example data will get `[[ 1 1 1 1 1 1 1 2 2 2 2 2 2 2 3 3 3...
@reiinakano In my experiments, the new reduce_frames method can make the training process stable, while the former method always had somewhat "mode collapse". But the new method might need more...
Hi @1adrianb , will the 2dfan-2.pth.tar be available? i want to have a test. or will you please send me a 2-stacked 2dfan model to my gmail [email protected]. Thanks!
报名活动 姓名：郭成凯 BOT5会员：是 介绍：边缘计算爱好者
I, Chengkai Guo, is the Vice Chair of BOT5 seminar Session 2020 Episode 9. I confirm that the Chair had followed(or not followed) the following steps in this seminar: -...
报名本次活动： 郭成凯，bot5会员 文本与音乐生成爱好者 本次分享一个小主题：jukebox openai的音乐生成模型 根据歌词和音乐类型生成乐曲和vocal
报名本周活动 郭成凯，bot5会员 transformer-xl,gpt2爱好者