Shunyuan Mao comments

Results 9 comments of


                                            Shunyuan Mao

Performance of computing partial derivative

Hi @shuheng-liu , Do you have any update would like to share about the questions, I am not familiar to automatic diff so I would like to know whether the...

Add a pre-built binary for Mac M1.

Hi, I am an M1 Mac user, and I am looking forward to having a pre-built package. Any updates?

Add a pre-built binary for Mac M1.

Hi @markcmiller86, This sounds really promising! Seems that you are pretty close (or succeed) to install visit from `build_visit`. If the official pre-build package won't be available in days, I...

Add a pre-built binary for Mac M1.

@markcmiller86 I see, thank you! I will post here if I get something looks interesting.

How to avoid w less than 0?

+1, I am facing the same problem.

Adaptive weight

Hi @oneikunikun , It's one year since I implemented this example, and I have not been following deepxde's updates for long, so I might be unable to help you with...

Adaptive weight

> @smao-astro , > Thank you for your timely reply, which is very helpful to me. > So the processing method of the original wave_1d case is not completely applied...

Botorch model_bridge changes after calling evaluate_acquisition function

Hi, I faced a similar issue when I using Service API with `GenerationStrategy`. The plots generated with `plot_slice` are different before and after the following line is executed ``` acq_values...

Problem training model with jax.jvp in forward pass

Hi all, I am migrating from dm-haiku to flax.nnx, I definitely want nnx.vjp and nnx.jvp, thank you in advance!