I find that in the training and testing phase, the dataset is standardized as a whole batch, including computing the mean and variance in a per channel style.
However, when the model is deployed, the image is feed individually, how should we preprocess the image?
What mean and variance should we use?
I find that in the training and testing phase, the dataset is standardized as a whole batch, including computing the mean and variance in a per channel style. However, when the model is deployed, the image is feed individually, how should we preprocess the image? What mean and variance should we use?