drakitLiu

发现即使没有scale文件，但也可以将量化后的静态图合并成onnx模型文件，使用的命令是： [paddle2onnx --model_dir ./ --model_filename model.pdmodel --params_filename model.pdiparams --save_file quant_model.onnx --opset_version 13 --enable_dev_ver](https://github.com/PaddlePaddle/Paddle2ONNX/blob/develop/docs/zh/quantize.md#/)sion True --deploy_backend onnxruntime --enable_onnx_checker True 但是失真度太大了！ 于是我尝试改用这个量化方法： ``` quant_recon_static( executor=exe, model_dir=args__.model_path, quantize_model_path=args__.save_path + 'quant_recon_static/', data_loader=data_loader, model_filename=args__.model_filename, params_filename=args__.params_filename,...

看着像是genface效果

> > I have encountered the same problem, which is also not falling at 0.69. May I ask if you have solved it？ > > I am working on it....

> > I have encountered the same problem, which is also not falling at 0.69. May I ask if you have solved it？ > > I am working on it....

Hi , Me too ! May I ask if you have solved it？