search

Skyy93 / Sample4Geo

76 stars 10 forks source link

Training result error #31

Closed sugy0114 closed 3 weeks ago

sugy0114 commented 3 weeks ago

Thank you for your reply. Does this mean that the epoch should be set to 1 during training? Will it not cause underfitting?

Skyy93 commented 3 weeks ago

Yes, you should not set the epochs higher than 1, expect you introduce more regularization to the approach.

The data in this case are easier to recognize which is why there is no underfitting.