/jKfddlmZddlmZddlZddlmZddlmZddl m Z Gdd e Z dS) ) annotations)PathN)LOGGER)check_executorch_requirements) BaseBackendc"eZdZdZd dZd d Zd S)ExecuTorchBackendzMeta ExecuTorch inference backend for on-device deployment. Loads and runs inference with Meta ExecuTorch models (.pte files) using the ExecuTorch runtime. Supports both standalone .pte files and directory-based model packages with metadata. weight str | PathreturnNonec0tjd|dtddlm}t |}|r(t|d}|dz }n |}|j dz }| t|}| d|_|r0ddlm}|||d Sd S) zLoad an ExecuTorch model from a .pte file or directory. Args: weight (str | Path): Path to the .pte model file or directory containing the model. zLoading z for ExecuTorch inference...r)Runtimez*.ptez metadata.yamlforward)YAMLN)rinforexecutorch.runtimerris_dirnextrglobparentget load_programstr load_methodmodelexistsultralytics.utilsrapply_metadataload)selfr rw model_file metadata_fileprogramrs g/home/longshao/multi-rider-rag/.venv/lib/python3.11/site-packages/ultralytics/nn/backends/executorch.py load_modelzExecuTorchBackend.load_models  CvCCCDDD%'''...... LL 88:: 7aggg..//J/MMJH6M++--,,S__==((33     ! ! : . . . . . .    - 8 8 9 9 9 9 9 : :im torch.Tensorlistc8|j|gS)zRun inference using the ExecuTorch runtime. Args: im (torch.Tensor): Input image tensor in BCHW format, normalized to [0, 1]. Returns: (list): Model predictions as a list of ExecuTorch output values. )rexecute)r"r*s r'rzExecuTorchBackend.forward2sz!!2$'''r)N)r r r r)r*r+r r,)__name__ __module__ __qualname____doc__r(rr)r'r r sF ::::8 ( ( ( ( ( (r)r ) __future__rpathlibrtorchrrultralytics.utils.checksrbaserr r3r)r'r9s#""""" $$$$$$BBBBBB,(,(,(,(,( ,(,(,(,(,(r)