Adriano Dennanni

icon company Infosimples icon location São Paulo icon location I'm a Machine Learning Engineer

Results 2 comments of Adriano Dennanni

Problems with multi-task learning with DataframeIterator / flow_from_dataframe

If I had a a single dense output, I would have only one loss/acc metric. It is very useful to have multiple metrics, one for each branch of the model....

Feature request: exchangeable internal HTTP clients (from Net::HTTP to Curb, for example)

Hello @flavorjones . Sorry for the long time for the reply. I will validate this today and will return soon.