train.py index error

[arthurzhang817]

In train.py, the output starts from "Iter [2/1000]...". I went into the code, and I found out that i starts from 0 (assuming no "resume training" scheme).

In the first iteration, i is increased to 1 immediately, but in later printing lines, they all use (i+1), which means there will never be a "Iter [1/1000]...".

The solution is to set start_iter as -1.