NXP Backend: Use absolute import for experimental CifarNet model in aot_neutron_compile.py.

As of the CifarNet model is installed as part of the ExecuTorch, by previous commit, use absolute import instead of relative.

Author: robert-kalmar

examples/nxp/aot_neutron_compile.py

@@ -22,6 +22,11 @@
 from executorch.examples.models import MODEL_NAME_TO_MODEL
 from executorch.examples.models.model_factory import EagerModelFactory
 
+from executorch.examples.nxp.experimental.cifar_net.cifar_net import (
+    CifarNet,
+    test_cifarnet_model,
+)
+
 from executorch.exir import (
     EdgeCompileConfig,
     ExecutorchBackendConfig,
@@ -32,8 +37,6 @@
 from torch.export import export
 from torchao.quantization.pt2e.quantize_pt2e import convert_pt2e, prepare_pt2e
 
-from .experimental.cifar_net.cifar_net import CifarNet, test_cifarnet_model
-
 FORMAT = "[%(levelname)s %(asctime)s %(filename)s:%(lineno)s] %(message)s"
 logging.basicConfig(level=logging.INFO, format=FORMAT)