Tier 2 - Deep Learning, Tensorflow error

[willsmithorg]

In Surface_Observation_Prediction_in_Tensorflow.ipynb:

Section 'Creating the Model'

When I execute this cell:
model = fullyconnected_sequential( time_of_day_train_norm.shape[1], depth=3, width=32, activation="tanh", learning_rate=10**(-3) )

I get the error
`
ValueError Traceback (most recent call last)
in <cell line: 0>()
----> 1 model = fullyconnected_sequential(
2 time_of_day_train_norm.shape[1], depth=3, width=32, activation="tanh", learning_rate=10**(-3)
3 )
3 frames
/usr/local/lib/python3.11/dist-packages/keras/src/backend/common/variables.py in standardize_shape(shape)
560 raise ValueError("Undefined shapes are not supported.")
561 if not hasattr(shape, "iter"):
--> 562 raise ValueError(f"Cannot convert '{shape}' to a shape.")
563 if config.backend() == "tensorflow":
564 if isinstance(shape, tf.TensorShape):

ValueError: Cannot convert '1' to a shape.`

[willsmithorg]

tf.version is 2.18.0 in my google colab.

My guess is that there was breaking change in tensorflow since this code was written.

I have a fix for this, I just wanted to raise this as an issue so it's clear what I'm fixing.