# GRADED FUNCTION: Siamese

def Siamese$($text$\_$vectorizer, vocab$\_$size$=36224,$ d$\_$feature$=128)$:

$"""$Returns a Siamese model.

Args:

text$\_$vectorizer $($TextVectorization$)$: TextVectorization instance, already adapted to your training data.

vocab$\_$size $($int$,$ optional$)$: Length of the vocabulary. Defaults to $56400.$

d$\_$model $($int$,$ optional$)$: Depth of the model. Defaults to $128.$

Returns:

tf$.$model.Model: A Siamese model.

$"""$

### START CODE HERE ###

branch $=$ tf$.$keras.models.Sequential$($name$=$'sequential'$)$

# Add the text$\_$vectorizer layer. This is the text$\_$vectorizer you instantiated and trained before

branch.add$($text$\_$vectorizer$)$

# Add the Embedding layer. Remember to call it 'embedding' using the parameter $`$name$`$

branch.add$($tf$.$keras.layers.Embedding$($

input$\_$dim$=$vocab$\_$size,

output$\_$dim$=$d$\_$feature,

embeddings$\_$initializer$=$'uniform',

embeddings$\_$regularizer$=$None,

activity$\_$regularizer$=$None,

embeddings$\_$constraint$=$None,

mask$\_$zero$=$False,

input$\_$length$=$None,

sparse$=$False,

name$=$'embedding'

$)$

$)$

# Add the LSTM layer, recall from W$2$ that you want to the LSTM layer to return sequences, ot just one value.

# Remember to call it $\text{'}$LSTM$\text{'}$ using the parameter $`$name$`$

branch.add$($tf$.$keras.layers.LSTM$($

units$=$d$\_$feature,

activation$=$'tanh',

recurrent$\_$activation$=$'sigmoid',

use$\_$bias$=$True,

kernel$\_$initializer$=$'glorot$\_$uniform',

recurrent$\_$initializer$=$'orthogonal',

bias$\_$initializer$=$'zeros',

unit$\_$forget$\_$bias$=$True,

kernel$\_$regularizer$=$None,

recurrent$\_$regularizer$=$None,

bias$\_$regularizer$=$None,

activity$\_$regularizer$=$None,

kernel$\_$constraint$=$None,

recurrent$\_$constraint$=$None,

bias$\_$constraint$=$None,

dropout$=0\mathrm{.}0,$

recurrent$\_$dropout$=0\mathrm{.}0,$

return$\_$sequences$=$True,

return$\_$state$=$False,

go$\_$backwards$=$False,

stateful$=$False,

time$\_$major$=$False,

unroll$=$False,

name$=\text{'}$LSTM$\text{'}$

$)$

$)$

# Add the GlobalAveragePooling$1$D layer. Remember to call it 'mean' using the parameter $`$name$`$

branch.add$($tf$.$keras.layers.GlobalAveragePooling$1$D$($

data$\_$format$=$'channels$\_$last',

name$=$'mean'

$)$

$)$

# Add the normalizing layer using the Lambda function. Remember to call it 'out' using the parameter $`$name$`$

branch.add$($tf$.$keras.layers.Lambda$($

lambda x: tf$.$math.l$2\_$normalize$($x$),$

name$=$'out'

$)$

$)$

# Define both inputs. Remember to call then 'input$\_1\text{'}$ and 'input$\_2\text{'}$ using the $`$name$`$ parameter.

# Be mindful of the data type and size

input$1=$ tf$.$keras.layers.Input$($None$,$ dtype$=$None, name$=$'input$\_1\text{'})$

input$2=$ tf$.$keras.layers.Input$($None$,$ dtype$=$None, name$=$'input$\_2\text{'})$

# Define the output of each branch of your Siamese network. Remember that both branches have the same coefficients,

# but they each receive different inputs.

branch$1=$ None

branch$2=$ None

# Define the Concatenate layer. You should concatenate columns, you can fix this using the $`$axis$`$parameter$.$

# This layer is applied over the outputs of each branch of the Siamese network

conc $=$ tf$.$keras.layers.Concatenate$($axis$=$None, name$=$'conc$\_1\_2\text{'})([$None$,$ None$])$

### END CODE HERE ###

return tf$.$keras.models.Model$($inputs$=[$input$1,$ input$2],$ outputs$=$conc, name$=$"SiameseModel"$)$