Preprocess for classification model

[zgplvyou]

Hi, I try to infer the classification models on onnxruntime engin. however, I can`t get the consistent accuracy in the page except resnet mobilenet and shufflenet. I think the preprocess of these models is different and i use the preprocess in imagenet_preprocess.py. mobilenet and shufflenet converted from pytorch got normal accuracy while inceptionv1 and efficientnet-lite4 converted from caffe got low accuracy. I guess the preprocess of the models from caffe is different.

[gcunhase]

I got low accuracies on bvlcalexnet-12, caffenet-12, googlenet-12, inception-v1-12, inception-v2-9, rcnn-ilsvrc13-9, and zfnet512-12. Does anyone know how the pre-processing steps differ for those models? Thanks.