Week 1 Course 1 - Define output layers of the model

Course Q&A TensorFlow: Advanced Techniques Specialization Custom Models, Layers and Loss Functions with TF
1

Hi, im getting this error

AttributeError Traceback (most recent call last)
in
----> 1 utils.test_final_model(final_model)

~/work/release/W1_Assignment/utils.py in test_final_model(final_model)
273 {
274 “name”: “layer_3_activation_check”,
→ 275 “result”: test_output.layers[4].activation,
276 “expected”: tf.keras.activations.sigmoid,
277 “error_message”: ‘wine_quality layer has an incorrect activation. Please check implementation.’

AttributeError: ‘NoneType’ object has no attribute 'layers

from what the error message says, the error would be that the activation function of wine_quality is not correct, but that line of code, according to the statement, does not require defining the activation. I hope you can help me, thank you!

2

I think you filed this message in the incorrect category. You filed it against DLS Course 1. I am not familiar with any assignments in any of the DLS courses that deal with “wine quality”.

3

Yes, sorry i was trying to post it in the Tensor Flow specialization.

4

You can use the little “Edit Pencil” icon next to the title to move it, rather than recreating it from scratch.

Oh, sorry, I see you already did that. Great!

5

Hi there,

There must activations used for the layers and the output of the model. This is a normal structure of neural network.