C2W2 assignment cannot reach 80%

Course Q&A TensorFlow Developer Professional Convolutional Neural Networks in TensorFlow
1

Hi,

I cannot reach 80%… I have set batch size for train/validation to 90/10. I use Adam as the optimizer.

image
image2300×84 9.17 KB

2

Hello @chien_4 ,

Send me your notebook via dm such that I can check where it went wrong. By clicking on the profile picture, you will see an option to message. There you can attach your notebook. Then we can discuss the issues here, under the topic you created.

With regards,
Nilosree Sengupta

3

Hello @chien_4 ,

I have gone through your code.

  1. You cannot import anything apart from what’s given. So Remove the code : from tensorflow.keras.optimizers import RMSprop.
    You need to code between this block only:
### START CODE HERE
....
### END CODE HERE
  1. You need to think of some better units, dimensions and functions for the parameters of the graded functions:
  • def train_val_generators
  • def create_model()
    As a mentor I should not say you the specific dimensions, inputs and functions for the parameters. Read the hints, explore the applicability of various loss functions. Revise the lessons and experiment with values to get it.
  1. Under def train_val_generators, I see you have commented out important parameters like :
#  height_shift_range= None,
 #  zoom_range=None,

Don’t comment out these. Put appropriate values here replacing “None”.

With regards,
Nilosree Sengupta