How to interpret a drastic accuracy loss while training a neuronal net (CNN)?

datascience.stackexchange https://datascience.stackexchange.com/questions/37938

  •  31-10-2019
  •  | 
  •  

Pergunta

How can one interpret a drastic accuracy loss after ~38 epochs? Maybe more dropout should be added to the CNN network?

Training vs Test Accuracy

(x-axis shows the number of epochs)

Nenhuma solução correta

Licenciado em: CC-BY-SA com atribuição
scroll top