minimal Namespace Reference

Functions
	main (nnpackage_path, backends="cpu")

Variables
	argv = sys.argv[1:]

Function Documentation

main()

minimal.main	(		nnpackage_path,
			backends = "cpu"
	)

Definition at line 8 of file minimal.py.

def main(nnpackage_path, backends="cpu"):
    # Create session and load nnpackage
    # The default value of backends is "cpu".
    session = infer.session(nnpackage_path, backends)
 
    # Prepare input. Here we just allocate dummy input arrays.
    input_infos = session.get_inputs_tensorinfo()
    dummy_inputs = []
    for info in input_infos:
        # Retrieve the dimensions list from tensorinfo property.
        dims = list(info.dims)
        # Build the shape tuple from tensorinfo dimensions.
        shape = tuple(dims[:info.rank])
        # Create a dummy numpy array filled with zeros.
        dummy_inputs.append(np.zeros(shape, dtype=info.dtype))
 
    outputs = session.infer(dummy_inputs)
 
    print(f"nnpackage {nnpackage_path.split('/')[-1]} runs successfully.")
    return
 
 

Variable Documentation

argv

minimal.argv = sys.argv[1:]

Definition at line 31 of file minimal.py.