Bayesian-Neural-Networks
Bayesian-Neural-Networks copied to clipboard
2 questions: batch & layer
Here are two questions, and would you please help me with them:
- In the COLAB notebook, this code didn't train in batches, right?
- In the COLAB notebook, the MC_Dropout_Model can run without the MC_Dropout_Layer?
Hi @EvannaB
- I believe that all models should train in minibatches by default.
- You can remove the MC dropout layer, but you will remove the uncertainty estimation capabilities of the model if you do this.