Open nyg2017 opened 6 years ago
I get the same problem with you when I training this model start from scratch. The training epoch is not at the end(129/159 epoch), but the gap is so large. I also want to know the performances in ./img/learning_curve.jpg is the result corresponding for what. Thank you for give me some ideas if you could. And at the same, I will continue learning it. :)
I wonder to know if the performances in ./img/learning_curve.jpg is the final result by fine-tone with the pre-trained model. I've done a lot of work to achieve the same result(such as freezing the front layer parameters, adjusting hyper parameter .etc), but there's still a big gap. And I'd appreciate it if you could give me any hints. THX!!!