Previous Index Next

Building the Model

Now that we have preprocessed and created the dataset, we can create the model:
- The first layer is an Embedding layer, which will convert word IDs into embeddings. The embedding matrix needs to have one row per word ID (vocab_size + num_oov_buckets) and one column per embedding dimension (this example uses 128 dimensions, but this is a hyperparameter you could tune).
- Whereas the inputs of the model will be 2D tensors of shape [batch size, time steps], the output of the Embedding layer will be a 3D tensor of shape [batch size, time steps, embedding size].

Note:

keras.layers.Embedding : Turns positive integers (indexes) into dense vectors of fixed size. More here.
keras.layers.GRU : The GRU(Gated Recurrent Unit) Layer.

INSTRUCTIONS

Set embed_size to 128, which is the embedding size of each word.
```
embed_size = 128
```

Create the model model with

Embedding layer
GRU layer with 4 units
GRU layer with 2 units

Dense layer with 1 unit and sigmoid activation

model = keras.models.Sequential([
    keras.layers.Embedding(vocab_size + num_oov_buckets, embed_size,
               mask_zero=True,
               input_shape=[None]),
    keras.layers.GRU(4, return_sequences=True),
    keras.layers.GRU(2),
    keras.layers.Dense(1, activation="sigmoid")
])

Compile the model with "binary_crossentropy" loss(as this is a binary classification problem), "adam" optimizer and "accuracy" metric.
```
model.compile(loss="binary_crossentropy", optimizer="adam", metrics=["accuracy"])
```

Get Hint See Answer

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

Project - How to Build a Sentiment Classifier using Python and IMDB Reviews

Building the Model

XP

Loading comments...