Project - Introduction to Transfer Learning (Cat vs Non-cats Project)

18 / 26

Previous Index Next

Cats vs Non-cats using Transfer Learning - Compile the VGG16 model

In addition to adding the custom dense layers to train, we should also mention some other factors like:

the optimization algorithm
learning rate
loss function
metrics of evaluation and others.

We shall now see how to do this.

INSTRUCTIONS

Instantiate SGD optimizer with learning rate lr=0.025.
```
sgd = SGD(lr=0.025)
```
Now let us compile the vgg_model and mention the loss as 'binary_crossentropy' since this is a binary classification, optimizer as sgd which we mentioned above, and metrics as accuracy.
```
<<  your code comes here >>.compile(loss=<< your code comes here >>, optimizer=sgd,    metrics=['accuracy'])
```

Get Hint See Answer

Note - Having trouble with the assessment engine? Follow the steps listed here

Previous Index Next

Loading comments...