About input image normalization

megvii-research / video_analyst

A series of basic algorithms that are useful for video understanding, including Single Object Tracking (SOT), Video Object Segmentation (VOS) and so on.

MIT License

832 stars 176 forks source link

About input image normalization #227

Open INTOUCHABLE-VS opened 2 years ago

INTOUCHABLE-VS commented 2 years ago

You normalized the input image in goolenet and shufflenetv2, but not in other backbone networks. Will this operation have any impact on the results?