Regarding first assignment of the week 1/ house prediction model

I already find out everything with the assignment besides the part I shared below. Could anybody give me a hint on that?

def house_model():

I dont really understand why we should define a house model besides running a model.

Please take some time to read the markdown in the notebook. The level of explanation is good enough to complete the assignment. Feel free to ask specific questions about problems you encounter.


I have problem with keras too.

Please click my name and message your notebook as an attachment.

There are 2 mistakes in your notebook:

  1. keras is used directly instead of tf.keras since only tensorflow is imported as tf.
  2. Loss function is misspelled.
1 Like

Thanks!! It worked out

@Brady_Sark

You’ve missed this hint:
Hint: Your network might work better if you scale the house price down. You don’t have to give the answer 400…it might be better to create something that predicts the number 4, and then your answer is in the ‘hundreds of thousands’ etc.

The grader expects the model to predict a number close to 4 when the number of rooms is 7.

Thank you for taking the time to review my code. I did answer the question with both a value near 4 and the anticipated house value of around 400000.
My interpretation of the question asked for both answers. Should I just get rid of the secondary calculation?

For clarity, the commented code near the bottom asked for finding the anticipated house value. Should I have ignored that?

You’re welcome. Hope this helps.

Thank you again for all the help, and for putting up with my bone headedness