Timothy Mak

Results 12 issues of Timothy Mak

Is it possible to reduce GPU memory usage during inference?

It appears it is taking >30GB of memory for inference. What are the parameters I can set which can reduce the demand? Thanks!

Prediction of decoded message as mean of multiple segments?

In the paper, it is claimed that the model encodes watermark at a rate of 32 bit per second. This implies that we can encode a *different* message every second....