DavidBPw

icon company Leibniz-Forschungsinstitut für Molekulare Pharmakologie icon location Berlin

Results 2 comments of DavidBPw

can supCon loss used in multi-label classification?

Would it be sufficient to just modify the mask iand my input labels in such a way that the mask correctly identifies data points who share at least one class...

Saving the model

You can save a model in tensorflow at the location checkpoint_path with: model.save_weights(checkpoint_path) And to load it you can use: model.load_weights(checkpoint_path)