Same problem with fine tuning.
JinnyZhao opened this issue · 1 comments
Your issue is that I'm trying to adopt this approach for multiclass classification. And the first step when we're training the top model from bottlenecks works fine and I have 76% accuracy for 102 classes. But when I proceed to fine-tune step, the model with each next epoch decreases in accuracy. So if at the end of 1st epoch of fine-tune I have about 45% of accuracy, on the 2nd epoch I'm getting 40%, etc.
Same problem with fine tuning. Im trying now and model decreased in accuracy from 70% to 40%.
I'm trying to find the issue for a few weeks but no results. Whether you have resolved it,thanks!
I've simplified the fine-tuning process and not it should work. There's also no such steps like getting bottlenecks and top-model training.