savetaskmodel
function defined in module
FastAI
savetaskmodel(path, task, model[; force = false])
Save a trained
model along with a
task to
path for later inference. Use
loadtaskmodel for loading both back into a session. If
path already exists, only write to it if
force = true.
If
model weights are on a GPU, they will be moved to the CPU before saving so they can be loaded in a non-GPU environment.
JLD2.jl is used for serialization.
There is
1
method for FastAI.savetaskmodel:
The following pages link back here:
Keypoint regression, Quickstart, Saving and loading models for inference, TimeSeries Classification, tsregression