Model.fit() model.compile()

#1

Please explain the parameters in model.fit and model.compile in more detail

#2

hey @Ankit003 ,

  1. model.compile
    a. loss -> it specifies the loss function that you need to implement in order to update weights in your network.
    b. optimizer -> The algorithm that you need to use which will update the values of weights and biases.
    c. metrics - > a list of some metrics that you want to calculate at each epoch while training your model.

  2. Model.fil
    a. X,Y - > these are the training inputs and outputs , upon which your model is going to be trained on.
    b. epochs -> Number of iterations to perform training.
    c. batch_size -> While performing mini-batch gradient descent , what size of this batch to be.
    d. validation_data -> validation data to be used to check performance of our model on unseen data at each iteration.
    e. validation_split -> if you don’t have validation data ,then it will automaitcally split the training data into validation data

These are most common parameters used. If you wanted to understand some else too , kindly let me know here itself.
I hope these helped you.

#3

I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.

On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.