模型中存在不支持量化的层量化模型失败【免费下载链接】geGEGraph Engine是面向昇腾的图编译器和执行器提供了计算图优化、多流并行、内存复用和模型下沉等技术手段加速模型执行效率减少模型内存占用。 GE 提供对 PyTorch、TensorFlow 前端的友好接入能力并同时支持 onnx、pb 等主流模型格式的解析与编译。项目地址: https://gitcode.com/cann/ge问题现象描述执行ATC模型转换命令时通过--compression_optimize_conf参数配置模型量化将模型中的权重由浮点数float32量化到低比特整数int8相关的选项结果报错提示如下ATC start working now, please wait for a moment. [ERROR][ProcessScale][52] Not support scale greater than 1 / FLT_EPSILON. [ERROR][WtsArqCalibrationCpuKernel][188] ArqQuantCPU scale is illegal. [ERROR][ArqQuant][301] WtsArqCalibrationCpuKernel of format CO_CI_KH_KW failed. [ERROR] AMCT(14815,atc.bin):2023-04-14-12:23:19[weight_algorithm.cpp:137]Default/network-DeepLabV3/resnet-Resnet/layer4-SequentialCell/0-Bottleneck/downsample-SequentialCell/0-Conv2d/Conv2D-op311 arq weight fake quant failed! [ERROR] AMCT(14815,atc.bin):2023-04-14-12:23:19[weight_calibration_pass.cpp:90]Fail to execute WeightFakeQuant without trans! [ERROR] AMCT(14815,atc.bin):2023-04-14-12:23:19[weight_calibration_pass.cpp:185]layer Default/network-DeepLabV3/resnet-Resnet/layer4-SequentialCell/0-Bottleneck/downsample-SequentialCell/0-Conv2d/Conv2D-op311 run WeightFakeQuantArq failed [ERROR] AMCT(14815,atc.bin):2023-04-14-12:23:19[graph_optimizer.cpp:43]pass run failed [ERROR] AMCT(14815,atc.bin):2023-04-14-12:23:19[quantize_api.cpp:227]Do GenerateCalibrationGraph optimizer pass failed. [ERROR] AMCT(14815,atc.bin):2023-04-14-12:23:19[quantize_api.cpp:363]Generate calibration Graph failed. [ERROR] AMCT(14815,atc.bin):2023-04-14-12:23:22[inner_graph_calibration.cpp:78]Failed to execute InnerQuantizeGraph failed.原因分析通过报错提示layerxxxxxxrun WeightFakeQuantArq failed可知当前模型中有权重相关的层不支持量化需要跳过这些不支持量化的层。解决措施跳过不支持量化的层配置方法如下增加配置跳过不支持量化的层。新增一个配置文件文件名后缀为.cfg例如_simple_config.cfg_文件内容如下加粗部分为报错提示中不支持量化的层skip_layers: Default/network-DeepLabV3/resnet-Resnet/layer4-SequentialCell/0-Bottleneck/downsample-SequentialCell/0-Conv2d/Conv2D-op311同时在--compression_optimize_conf参数指定的量化配置文件中增加config_file参数calibration: { input_data_dir: xxxxxx config_file: simple_config.cfg input_shape: xxxxxx infer_soc: xxxxxx }重新执行模型转换。重新执行推理。如果跳过不支持量化的层影响模型推理的结果数据则需要用户自行调整模型再重新量化模型。【免费下载链接】geGEGraph Engine是面向昇腾的图编译器和执行器提供了计算图优化、多流并行、内存复用和模型下沉等技术手段加速模型执行效率减少模型内存占用。 GE 提供对 PyTorch、TensorFlow 前端的友好接入能力并同时支持 onnx、pb 等主流模型格式的解析与编译。项目地址: https://gitcode.com/cann/ge创作声明：本文部分内容由AI辅助生成（AIGC），仅供参考