Convolution_model_Application (happymodel)

Course Q&A Deep Learning Specialization Sequence Models
1

Hello
I have problem with this part of my code

model = tf.keras.Sequential([
## ZeroPadding2D with padding 3, input shape of 64 x 64 x 3

        ## Conv2D with 32 7x7 filters and stride of 1
        
        ## BatchNormalization for axis 3
        
        ## ReLU
        
        ## Max Pooling 2D with default parameters
        
        ## Flatten layer
        
        ## Dense layer with 1 unit for output & 'sigmoid' activation
        
        # YOUR CODE STARTS HERE

        # YOUR CODE ENDS HERE
    ])

I would appreciate it if someone tell me how to write these lines.

2

Hi @Mojtaba_Hassanzadeh ,

First of all, it is important to understand the ‘Sequential’ of keras:

The Sequential is like a ‘container’. In this ‘container’ you will add, in order, the different layers of your model. Something like this:

model = tf.keras.Sequential([
layer1,
layer2,
layer3,
…
layer’n’
])

Based on this, the exercise is asking to add layers in this container, and the instructions are telling you the type of each layer, and the order in which these need to be added.

For instance, the first layer to add, according to the instruction is ZeroPadding2D with some parameters: padding=3, shape=(64,64,3).

I would not do you good telling you exactly the code of this and the rest of layers, so I would like to recommend: for each named layer, do a Google search, and do your best to complete the layers. Since the names are clearly stated, your Google search will return very precise entries of documentation.

Try that and let us know how it goes.

Thanks,

Juan