How minibatch accuracy can go beyond 100% while training convolutional neural network?

4 ビュー (過去 30 日間)

Ankita Jain 2021 年 12 月 23 日

0
リンク

この質問への直接リンク

https://jp.mathworks.com/matlabcentral/answers/1616370-how-minibatch-accuracy-can-go-beyond-100-while-training-convolutional-neural-network

コメント済み: Ankita Jain 2022 年 4 月 29 日

I am training CNN on expression data and I am getting sharp spikes in accuracy that goes beyond 100%, and loss goes less than 0. But when curve smoothed both accuracy and loss are in the limits (i.e. accuracy less than 100% and loss is greater than 0). How it is possible?

Total number of samples: 20500

Epoch: 5

Minibatch size: 25.

What am I doing wrong?