Dataset format

[shimmer-ghq]

Hi, I ran train_nasnet_mobile.py directly with my own data set, but all the predicted scores of the trained model were 1.0. I suspect that the format of my dataset is not correct. Could you please tell me the format of your dataset (TXT file containing picture ID and score)?

[shimmer-ghq]

My TXT dataset format: "Picture name" "score" (a floating point number)