pytorch has a history of constraining API to be computationally efficient (in eager), in a "dont let user shoot themselves in the foot" kinda way. this is one of those constraints.
PyTorch API design constraints for computational efficiency
By
–
By
–
pytorch has a history of constraining API to be computationally efficient (in eager), in a "dont let user shoot themselves in the foot" kinda way. this is one of those constraints.