C4 W2: Transfer learning with MobileNetv2 `weights="imagenet"` without the top layers?

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

In Exercise 2 - alpaca_model, I manage to download the entire weights with weights="imagenet" but how do I specify weights="imagenet" without the top layers? I know the exercise comes with a local copy but how / where was the weights downloaded in the first place? I want to know that. https://www.tensorflow.org/api_docs/python/tf/keras/applications/MobileNetV2 doesn’t provide the information needed. Thanks.

2

I believe include_top=False, does the job.

3

Glad to know that you solved it on your own.

1 Like