Sequential batch processing vs paralle batch processing?

In deep learning based model training, in general batch of inputs are passed. For example for training a deep learning model with [512] dimensional input feature vector, say for batch size= 4, we mainly pass [4,512] dimenional input. I am curious what are the logical significance of passing the same input after flattening the input across the batch and channel dimenions [2048]. Logically the locality structure will be destroyed but will it significanlty speed up my implementation? And can it affect the performance?

no, elementwise ops work on internally flattened data already, and you can’t flatten conv/matmul/etc inputs.

1 Like