FizddlmZddlmZddlmZddlZddlmZ d ddZ y) ) annotations)Path)AnyN)LOGGERc ddl} tjd|d| jdt |t t fr|D cgc]} | jc} n |j} | j||rdn| |} |r-ddl } | j| || jj|} |7t|}|jdd |d z }| j| || | Scc} w) aQExport a PyTorch model to OpenVINO format with optional INT8 quantization. Args: model (torch.nn.Module): The model to export (may be NMS-wrapped). im (torch.Tensor | list[torch.Tensor] | tuple[torch.Tensor, ...]): Example input tensor(s) for tracing. output_dir (Path | str | None): Directory to save the exported OpenVINO model. dynamic (bool): Whether to use dynamic input shapes. half (bool): Whether to compress to FP16. int8 (bool): Whether to apply INT8 quantization. calibration_dataset (nncf.Dataset | None): Dataset for INT8 calibration (required when ``int8=True``). ignored_scope (dict | None): Kwargs passed to ``nncf.IgnoredScope`` for head patterns. prefix (str): Prefix for log messages. Returns: (ov.Model): The converted OpenVINO model. rN z starting export with openvino z...)input example_input)modelcalibration_datasetpreset ignored_scopeT)parentsexist_okz model.xml)compress_to_fp16)openvinorinfo __version__ isinstancelisttupleshape convert_modelnncfquantizeQuantizationPresetMIXEDrmkdir save_model)r im output_dirdynamichalfint8r rprefixovi input_shapeov_modelr output_files c/var/www/pod-logistic/pod-ai/venv/lib/python3.12/site-packages/ultralytics/utils/export/openvino.pytorch2openvinor, s6 KK"VH;BNN;K3OP+5b4-+HB'q177'bhhKWT+]_`H == 3**00' ! *% 5 ;.  h d C O#(sC))NFFFNN)r ztorch.nn.Moduler zr8s# $ %)&*!%0 0D0"0 0  0  0$00 0 0r7