Currently, we have a benchmark of network size in the FAQ. I think we should choose some typical datasets to test more parameters and benchmark their accuracy and speed (for both CPUs and GPUs).
Detailed Description
I have several ideas here:
[ ] type_one_side: #2265
[ ] precision: In some (or most) systems, FP64 does not improve accuracy compared to FP32.
[ ] activation_function
[ ] the type of the descriptor: se_e2_a, se_e2_r, se_e3, local_frame
[ ] axis_neuron
[ ] training steps
[ ] loss function, i.e., the weight of energy/forces
Summary
Currently, we have a benchmark of network size in the FAQ. I think we should choose some typical datasets to test more parameters and benchmark their accuracy and speed (for both CPUs and GPUs).
Detailed Description
I have several ideas here:
type_one_side
: #2265precision
: In some (or most) systems, FP64 does not improve accuracy compared to FP32.activation_function
se_e2_a
,se_e2_r
,se_e3
,local_frame
axis_neuron
Further Information, Files, and Links
No response