o hQ@sddlZddlmZddlmZmZddlmZddlm Z m Z m Z m Z ddl mZmZddlmZmZddlmZdd lmZmZmZed Zgd ZGd d d eZdededefddZdefddZddZdedede e ee ee effddZ d>dededede edef dd Z!ded!e"d"ed#e#fd$d%Z$ded!e"d"efd&d'Z%  ( )d?deded"ed!e"de ed#e#defd*d+Z&d,edefd-d.Z'd,edefd/d0Z(d1efd2d3Z)e*d4krseZ+e+,Z-ee-j./e-_.zce0d5e&e-j1e-j2e-j.e-j3e-j4e-j5e-je-j(r(eee-j1d6kre0d7e0d8e'e-j.e-_6e(e-j6e-_7e-j8rNe0d9e)e-j.e9e-d:r@e)e-j6e9e-d;rQe)e-j7WdSWdSWdSe:yrZ;ze0d= than 2Gbz --quantizez/Quantize the neural network to be run with int8output)super__init__ add_argumentstrSUPPORTED_PIPELINESint)self __class__X/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/convert_graph_to_onnx.pyr$3sJ z$OnnxConverterArgumentParser.__init__)__name__ __module__ __qualname____doc__r$ __classcell__r,r,r*r-r.srfilename identifierreturncCs|j|j||jS)aE Append a string-identifier at the end (before the extension, if any) to the provided filepath Args: filename: pathlib.Path The actual path object we would like to add an identifier suffix identifier: The suffix to add Returns: String with concatenated identifier at the end of the filename )parentjoinpathstem with_suffixsuffix)r3r4r,r,r-generate_identified_filename\s r;minimum_versioncCsPzddl}t|j}|tkrtd|jd|dWdSty'tdw)z Check onnxruntime is installed and if the installed version match is recent enough Raises: ImportError: If onnxruntime is not installed or too old version is found rNz*We found an older version of onnxruntime (z&) but we require onnxruntime to be >= zp to enable all the conversions options. Please update onnxruntime by running `pip install --upgrade onnxruntime`zonnxruntime doesn't seem to be currently installed. Please install the onnxruntime by running `pip install onnxruntime` and relaunch the conversion.) onnxruntimer __version__ORT_QUANTIZE_MINIMUM_VERSION ImportError)r<r= ort_versionr,r,r-check_onnxruntime_requirementsis   rBcCsxtd|jjj}gg}}|ddD]}||vr'|||||qt|dtd||t|fS)a Ensure inputs are presented in the correct order, without any Non Args: model: The model used to forward the input data tokens: BatchEncoding holding the input data input_names: The name of the inputs Returns: Tuple z$Ensuring inputs are in correct orderNz, is not present in the generated input list.zGenerated inputs order: )printforward__code__ co_varnamesappendtuple)modeltokens input_namesmodel_args_name model_argsordered_input_namesarg_namer,r,r-ensure_valid_inputs    rQnlp frameworkc sdtdtdtffdd |jd|d}|jjd|d kr&|jdi|n||}t|tr4| }t|t t fs>|f}t | }fd d | D}g}|D]}t|t t frc||qT||qTd d tt|D}fdd t||D} t|fi| } ||| |fS)a? Attempt to infer the static vs dynamic axes for each input and output tensors for a specific model Args: nlp: The pipeline object holding the model to be exported framework: The framework identifier to dispatch to the correct inference scheme (pt/tf) Returns: - List of the inferred input variable names - List of the inferred output variable names - Dictionary with input/output variables names as key and shape tensor as value - a BatchEncoding reference which was used to infer all the above information nameis_inputseq_lencst|ttfrfdd|DSddt|jDddi}r:t|jdkr/d|d<n!td t|jd fd dt|jD}|d d |DtdrVdnddd||S)Ncsg|] }|qSr,r,).0t)build_shape_dictrUrTrVr,r- sz:infer_shapes..build_shape_dict..cSsg|] \}}|dkr|qS)rCr,)rWaxisnumelr,r,r-rZrbatchsequencerCzUnable to infer tensor axes ()csg|] \}}|kr|qSr,r,)rWdimshape)rVr,r-rZr]cSsi|]}|dqS)r`r,)rWrbr,r,r- sz:infer_shapes..build_shape_dict..zFound inputr" z with shape: ) isinstancerIlist enumeraterclen ValueErrorupdaterD)rTtensorrUrVaxesseq_axes)rY)rUrTrVr-rYs "z&infer_shapes..build_shape_dictzThis is a sample output)return_tensorsrc i|] \}}|||dqS)Tr,rWkvrYrVr,r-rd z infer_shapes..cSsg|]}d|qS)output_r,)rWir,r,r-rZsz infer_shapes..crr)Fr,rsrvr,r-rdrwNr,)r&boolr( tokenizer input_idsrcrJrgrto_tuplerhrIkeysitemsextendrHrangerjzipdict) rRrSrKoutputs input_varsinput_dynamic_axes outputs_flatr" output_namesoutput_dynamic_axes dynamic_axesr,rvr- infer_shapess& "     r pipeline_namerJr{cKs`|dur|}|dkrtstd|dkrtstdtd|d|dt|||||d S) a Convert the set of arguments provided through the CLI to an actual pipeline reference (tokenizer + model Args: pipeline_name: The kind of pipeline to use (ner, question-answering, etc.) framework: The actual model to convert the pipeline from ("pt" or "tf") model: The model name which will be loaded by the pipeline tokenizer: The tokenizer name which will be loaded by the pipeline, default to the model's value Returns: Pipeline object NrLCannot convert because PyTorch is not installed. Please install torch first.rLCannot convert because TF is not installed. Please install tensorflow first.zLoading pipeline (model: z , tokenizer: ra)rJr{rS model_kwargs)r ExceptionrrDr )rrSrJr{ models_kwargsr,r,r-load_graph_from_argssropsetr"use_external_formatc Cststdddl}ddlm}ddlm}td|j| Ft |d\}}} } t |j | |\} } |rJ||j | | | || d|d|d n||j | | | || d|d WddSWddS1slwYdS) a Export a PyTorch backed pipeline to ONNX Intermediate Representation (IR Args: nlp: The pipeline to be exported opset: The actual version of the ONNX operator set to use output: Path where will be stored the generated ONNX model use_external_format: Split the model definition from its parameters to allow model bigger than 2GB Returns: rrN)export)is_torch_less_than_1_11zUsing framework PyTorch: rT)frLrrdo_constant_foldinguse_external_data_formatenable_onnx_checker opset_version)rrLrrrr)rrtorch torch.onnxrtransformers.pytorch_utilsrrDr>no_gradrrQrJas_posix) rRrr"rrrrrLrrrKrOrNr,r,r-convert_pytorchsF     "rc ststdtdzGddlddl}ddlm}tdjjd|t|d\}}}}|j |j fd d | D} |j j|j | ||d \} } WdStym} ztd | jd | jd| d} ~ ww)av Export a TensorFlow backed pipeline to ONNX Intermediate Representation (IR) Args: nlp: The pipeline to be exported opset: The actual version of the ONNX operator set to use output: Path where will be stored the generated ONNX model Notes: TensorFlow cannot export model bigger than 2GB due to internal constraint from TensorFlow rzD/!\ Please note TensorFlow doesn't support exporting model > 2Gb /!\rN)r>zUsing framework TensorFlow: z , tf2onnx: rcs g|] \}}jj||dqS))rT) TensorSpec from_tensor)rWkeyrmrr,r-rZUrwz&convert_tensorflow..)r output_pathzCannot import z6 required to convert TF model to ONNX. Please install z first. )rrrD tensorflowtf2onnxr>versionVERSIONrrJpredictdatarconvert from_kerasrr@rT) rRrr"rt2ovrLrrrKinput_signature model_proto_er,rr-convert_tensorflow8s(  rFrc Kstdttd|t||||fi|}|js-td|jt|jnt t |jdkrCt d|jd|dkrPt ||||dSt |||dS) a Convert the pipeline object to the ONNX Intermediate Representation (IR) format Args: framework: The framework the pipeline is backed by ("pt" or "tf") model: The name of the model to load for the pipeline output: The path where the ONNX graph will be stored opset: The actual version of the ONNX operator set to use tokenizer: The name of the model to load for the pipeline, default to the model's name if not provided use_external_format: Split the model definition from its parameters to allow model bigger than 2GB (PyTorch only) pipeline_name: The kind of pipeline to instantiate (ner, question-answering, etc.) model_kwargs: Keyword arguments to be forwarded to the model constructor Returns: zoThe `transformers.convert_graph_to_onnx` package is deprecated and will be removed in version 5 of TransformerszONNX opset version set to: zCreating folder rzFolder z" is not empty, aborting conversionrN)warningswarn FutureWarningrDrr6existsrrrjrrrr) rSrJr"rr{rrrrRr,r,r-r`s ronnx_model_pathcCsTddlm}m}t|d}|}||_|||}td|dtd|S)a> Load the model at the specified path and let onnxruntime look at transformations on the graph to enable all the optimizations possible Args: onnx_model_path: filepath where the model binary description is stored Returns: Path where the optimized model binary description has been saved rInferenceSessionSessionOptionsz -optimizedz$Optimized model has been written at : ✔zY/!\ Optimized model contains hardware specific operators which might not be portable. /!\)r=rrr;roptimized_model_filepathrD)rrropt_model_path sess_optionrr,r,r-optimizes  rc Csddl}ddl}ddlm}ddlm}ddlm}ddlm }| | }t |j t dkr4td|}||t |j t d krX||d d |jd d d dddt|d } n||d d |jd d d dddt|d } | t|d} td| d|| jj| | S)z Quantize the weights of the model from float32 to in8 to allow very efficient inference on modern CPU Args: onnx_model_path: Path to location the exported ONNX model is stored Returns: The Path generated for the quantized rN) ModelProto)QuantizationMode) ONNXQuantizer)IntegerOpsRegistryz1.5.0zpModels larger than 2GB will fail to quantize due to protobuf constraint. Please upgrade to onnxruntime >= 1.5.0.z1.13.1FT) rJ per_channel reduce_rangemodestatic weight_qType input_qType tensors_rangenodes_to_quantizenodes_to_excludeop_types_to_quantize) rJrrrrractivation_qTyperrrrz -quantizedz$Quantized model has been written at r)onnxr= onnx.onnx_pbronnxruntime.quantizationr'onnxruntime.quantization.onnx_quantizerr!onnxruntime.quantization.registryrloadrr r>rDCopyFrom IntegerOpsrhquantize_modelr; save_modelrJ) rrr=rrrr onnx_model copy_model quantizerquantized_model_pathr,r,r-quantizesZ       rpathc Csddlm}m}ddlm}td|dz|}|||dgd}td|d WdS|yI}ztd |d WYd}~dSd}~ww) Nrr)RuntimeExceptionz"Checking ONNX model loading from: z ...CPUExecutionProvider) providerszModel u correctly loaded: ✔zError while loading the model u: ✘)r=rr+onnxruntime.capi.onnxruntime_pybind11_staterrDr)rrrr onnx_optionsrrer,r,r-verifys r__main__z' ====== Converting model to ONNX ======raV Using TensorFlow might not provide the same optimization level compared to PyTorch. For TensorFlow users you can try optimizing the model directly through onnxruntime_tools. For more information, please refer to the onnxruntime documentation: https://github.com/microsoft/onnxruntime/tree/master/onnxruntime/python/tools/transformers z$ ====== Optimizing ONNX model ======z+ ====== Check exported ONNX model(s) ======optimized_outputquantized_outputz"Error while converting the model: rC)N)NFr)=rargparserosrrpathlibrtypingrrrr packaging.versionr r transformers.pipelinesr r transformers.tokenization_utilsrtransformers.utilsrrrr?r'rr&r;rBrQrrr(rzrrrrrrr.parser parse_argsargsr"absoluterDrSrJrr{rrr check_loadinghasattrrrexitr,r,r,r-s    . *A 7- 2K