I have was reading that ToTensor() turns the data into a 32-bit floating point per channel,scaling the values form 0.0 to 1.0
so what is the purpose of transfomers.Normalize(std,mean)!
Normalize subtracts the passed mean from the input and divides by the std to create a zero-mean and unit-variance output. This normalization is also known as standardizing, z-scoring, or whitening in signal processing and was shown to help ML training.