Issues with C3_W4_Lab_3_Saliency on Google Colab

[Andreas0815]

Hello,
I’m having issues with C3_W4_Lab_3_Saliency on colab.

The downgrade to tf 2.15 seemed to work as well as the import of the packages.
When building the model, the following line of code crashes:

model = tf.keras.Sequential([
    hub.KerasLayer('https://tfhub.dev/google/tf2-preview/inception_v3/classification/4'),
    tf.keras.layers.Activation('softmax')
])

And it gives the following error:

ValueError: Only instances of keras.Layer can be added to a Sequential model. Received: <tensorflow_hub.keras_layer.KerasLayer object at 0x7aa063838450> (of type <class 'tensorflow_hub.keras_layer.KerasLayer'>)

Could someone have a look on this?

Thanks

Google Colab

[gent.spah]

Hello, I am not getting any of these errors.

When you run the cells, when you run the first one:

Install packages for compatibility

Make a session restart and then run the other ones. Run->Restart Session

[Deepti_Prasad]

hi @Andreas0815

Are you following these steps, check the pinned comment

TF Advanced Technique C3_W4_Lab_3 error

Yes @Mun_Chung_Wong There is version issue with C3 assignment and you did the right way to resolve your issue. Another way would be Learners can reload the colab from the classroom or just add these lines at the top of their existing notebook (then run everything again to generate a new model file): !pip install tf-keras==2.15 --quiet !pip install tensorflow==2.15 --quiet !pip install keras==2.15 --quiet This would be required with course 3 as well as course 4 assignment but not all assignm…

Regards
DP

[Andreas0815]

Hello,

thanks for your support. It was my mistake. I think I restarted the whole colab instead of the whole session or something similar happened. It works now.

Andreas