def get_image_normalizer(mean,std):
"""
mean,std is the mean,std of 3 channels individually like [100, 81.1, 92],[12.1, 13.2, 21.5]
"""
def transformer(x):
## your code here should normalize the images coming in x-tensor
## x is of shape [batch_size,Height,Width,Channels]
return transformer
Intended Usage
Like how mappers are used here and here
Limitations
Online References/Documentation was referred while making this API
Branch Name (The github branch in which you are working on this).
Note: Before raising a PR make sure that you have made an issue like this with tag: enhancement, ensure your code is tested and documented.
Proposed Features
dataset.map
How the API looks like?
Intended Usage Like how mappers are used here and here
Limitations
Online References/Documentation was referred while making this API
Branch Name (The github branch in which you are working on this).
Note: Before raising a PR make sure that you have made an issue like this with tag: enhancement, ensure your code is tested and documented.