Same image - Different output
groot-1313 opened this issue · comments
groot-1313 commented
After training the model, I tested it from the latest checkpoint.
The model predicts different outputs for the same input image!!!
groot-1313 commented
I switched off the dropout to avoid it.
julien2512 commented
dropout garanties non specialization of each neuron in a NxN matrix (you do not need to apply it on convolutional networks). That mean your network would be more flexible to change.
I do not know your usecase exactly, but you should keep it while learning.
Eventhough, may be it is possible to keep it for the test.
mattchiang-gsp commented
@groot-1313 How exactly did you switch off dropout?