search

mpc001 / auto_avsr

Auto-AVSR: Lip-Reading Sentences Project
Apache License 2.0
158 stars 40 forks source link

Number of gpus / total batch size to reproduce the results in the paper #15

Closed tomato18463 closed 10 months ago

tomato18463 commented 10 months ago

Hi,

Thanks for sharing your code. If my understanding of the code is correct, the size of batch is actually related to the number of gpus for training. If I want to get a good result (i.e. reproduce the result in the paper), how many gpus I need? How many gpus are used to get the result in the paper?

Thank you!

mpc001 commented 10 months ago

Hi @tomato18463, I used 32 GPUs (A100-40GB) for 23-h/438-h experiments and 64 GPUs for 3448-hour experiments. (#9)