You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I got error error: too few arguments to function call expected at least 2, have 1 Result<Method> method = program->load_method(method_name);
I've created model with variable shape input and seems for that I don't need to allocate memory in advance. The tutorial above could be a good candidate, but I got errors.
Could anyone help or direct to where can I find good explanation about running executorch models in C++ with variable shaped inputs.
The text was updated successfully, but these errors were encountered:
I've created model with variable shape input and seems for that I don't need to allocate memory in advance.
Hmm we provide the option out of the box to have users opt out of memory planning their inputs, but you still need to provide arenas for any internal activations that occur in your model. So I would expect you to still need to provide the allocator.
Running the tutorial
https://pytorch.org/executorch/stable/running-a-model-cpp-tutorial.html
I got error
error: too few arguments to function call expected at least 2, have 1 Result<Method> method = program->load_method(method_name);
I've created model with variable shape input and seems for that I don't need to allocate memory in advance. The tutorial above could be a good candidate, but I got errors.
Could anyone help or direct to where can I find good explanation about running executorch models in C++ with variable shaped inputs.
The text was updated successfully, but these errors were encountered: