Do we need to normalize before feeding to TF_EfficientNet?

[vythaihn]

Hi,

I saw this:

'tf_efficientnetv2_s': _cfg( url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-effv2-weights/tf_efficientnetv2_s-eb54923e.pth', mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), input_size=(3, 300, 300), test_input_size=(3, 384, 384), pool_size=(10, 10), crop_pct=1.0),

So, I'm wondering should I normalize the inputs before feeding into this model or not?

Same question with 'pytorch_efficientnet' since I don't see mean and std in the _cfg.

Thank you!