search

NVIDIA / gpu-rest-engine

A REST API for Caffe using Docker and Go
BSD 3-Clause "New" or "Revised" License
421 stars 94 forks source link

Serving models with number of outputs less than 5 #34

Open sergey-serebryakov opened 6 years ago

sergey-serebryakov commented 6 years ago

Hi! I think, in current implementation the engine cannot server models if they have less than five outputs. The classify method accepts as one of the input parameters N which is the number of top classifications to return. The Argmax function fails in this case.

flx42 commented 6 years ago

You have to edit the code in this case, to modify the Classify call.