Open Zhen-ao opened 3 years ago
Good question, as of now I haven't done proper ablation so I can't tell you exactly how much worse it would be - I expect maybe 2 points if you use the Imagenet pre-trained model and worse if you do random initialization also training converges slower. May I ask what is the problem with the pre-trained weights.
hi~Thanks for your work, but I have a question: Is it possible to not load the pre-trained model? Will it be very different from the current result?