hantek/deeplearn_hsi

for network parameters

yang123jx opened this issue · 2 comments

Hello, as for experiment on Salinas Valley data, the network parameter [310 100] performs bad, how to tune the depth and number of neurons in each layer ?

How large is your dataset? What kind of architecture are you using? What is the training/test cost and error rate correspondingly?

Closing since there is no more response.