# can i get weights per iteration of MLP?

im building an mlp with scikit learn. Is there a way I can access weights and biases of the output layer per iteration? There is an option mlp.coefs_ But it outputs the train weights when the model is compiled

• clf.coefs_ contains the weight matrices that constitute the model parameters: – Sachin Yadav Oct 31 '19 at 16:35
• @SachinYadav but it accessible only when the model is compiled. I want to access the weights which are updated in every iteration – imtiaz ul Hassan Oct 31 '19 at 17:09