The Sequential model (original) (raw)

Skip to main content

The Sequential model

Stay organized with collections Save and categorize content based on your preferences.

Author: fchollet

Setup

import tensorflow as tf
import keras
from keras import layers

When to use a Sequential model

A Sequential model is appropriate for a plain stack of layerswhere each layer has exactly one input tensor and one output tensor.

Schematically, the following Sequential model:

# Define Sequential model with 3 layers
model = keras.Sequential(
    [
        layers.Dense(2, activation="relu", name="layer1"),
        layers.Dense(3, activation="relu", name="layer2"),
        layers.Dense(4, name="layer3"),
    ]
)
# Call model on a test input
x = tf.ones((3, 3))
y = model(x)

is equivalent to this function:

# Create 3 layers
layer1 = layers.Dense(2, activation="relu", name="layer1")
layer2 = layers.Dense(3, activation="relu", name="layer2")
layer3 = layers.Dense(4, name="layer3")

# Call layers on a test input
x = tf.ones((3, 3))
y = layer3(layer2(layer1(x)))

A Sequential model is not appropriate when:

Creating a Sequential model

You can create a Sequential model by passing a list of layers to the Sequential constructor:

model = keras.Sequential(
    [
        layers.Dense(2, activation="relu"),
        layers.Dense(3, activation="relu"),
        layers.Dense(4),
    ]
)

Its layers are accessible via the layers attribute:

model.layers

[<keras.src.layers.core.dense.Dense at 0x7fa3c8de0100>, <keras.src.layers.core.dense.Dense at 0x7fa3c8de09a0>, <keras.src.layers.core.dense.Dense at 0x7fa5181b5c10>]

You can also create a Sequential model incrementally via the add() method:

model = keras.Sequential()
model.add(layers.Dense(2, activation="relu"))
model.add(layers.Dense(3, activation="relu"))
model.add(layers.Dense(4))

Note that there's also a corresponding pop() method to remove layers: a Sequential model behaves very much like a list of layers.

model.pop()
print(len(model.layers))  # 2

2

Also note that the Sequential constructor accepts a name argument, just like any layer or model in Keras. This is useful to annotate TensorBoard graphs with semantically meaningful names.

model = keras.Sequential(name="my_sequential")
model.add(layers.Dense(2, activation="relu", name="layer1"))
model.add(layers.Dense(3, activation="relu", name="layer2"))
model.add(layers.Dense(4, name="layer3"))

Specifying the input shape in advance

Generally, all layers in Keras need to know the shape of their inputs in order to be able to create their weights. So when you create a layer like this, initially, it has no weights:

layer = layers.Dense(3)
layer.weights  # Empty

[]

It creates its weights the first time it is called on an input, since the shape of the weights depends on the shape of the inputs:

# Call layer on a test input
x = tf.ones((1, 4))
y = layer(x)
layer.weights  # Now it has weights, of shape (4, 3) and (3,)

[<tf.Variable 'dense_6/kernel:0' shape=(4, 3) dtype=float32, numpy= array([[ 0.1752373 , 0.47623062, 0.24374962], [-0.0298934 , 0.50255656, 0.78478384], [-0.58323103, -0.56861055, -0.7190975 ], [-0.3191281 , -0.23635858, -0.8841506 ]], dtype=float32)>, <tf.Variable 'dense_6/bias:0' shape=(3,) dtype=float32, numpy=array([0., 0., 0.], dtype=float32)>]

Naturally, this also applies to Sequential models. When you instantiate a Sequential model without an input shape, it isn't "built": it has no weights (and callingmodel.weights results in an error stating just this). The weights are created when the model first sees some input data:

model = keras.Sequential(
    [
        layers.Dense(2, activation="relu"),
        layers.Dense(3, activation="relu"),
        layers.Dense(4),
    ]
)  # No weights at this stage!

# At this point, you can't do this:
# model.weights

# You also can't do this:
# model.summary()

# Call the model on a test input
x = tf.ones((1, 4))
y = model(x)
print("Number of weights after calling the model:", len(model.weights))  # 6

Number of weights after calling the model: 6

Once a model is "built", you can call its summary() method to display its contents:

model.summary()

Model: "sequential_3" _________________________________________________________________ Layer (type) Output Shape Param #

dense_7 (Dense) (1, 2) 10

dense_8 (Dense) (1, 3) 9

dense_9 (Dense) (1, 4) 16

Total params: 35 (140.00 Byte) Trainable params: 35 (140.00 Byte) Non-trainable params: 0 (0.00 Byte)

However, it can be very useful when building a Sequential model incrementally to be able to display the summary of the model so far, including the current output shape. In this case, you should start your model by passing an Inputobject to your model, so that it knows its input shape from the start:

model = keras.Sequential()
model.add(keras.Input(shape=(4,)))
model.add(layers.Dense(2, activation="relu"))

model.summary()

Model: "sequential_4" _________________________________________________________________ Layer (type) Output Shape Param #

dense_10 (Dense) (None, 2) 10

Total params: 10 (40.00 Byte) Trainable params: 10 (40.00 Byte) Non-trainable params: 0 (0.00 Byte)

Note that the Input object is not displayed as part of model.layers, since it isn't a layer:

model.layers

[<keras.src.layers.core.dense.Dense at 0x7fa3bc0ba820>]

A simple alternative is to just pass an input_shape argument to your first layer:

model = keras.Sequential()
model.add(layers.Dense(2, activation="relu", input_shape=(4,)))

model.summary()

Model: "sequential_5" _________________________________________________________________ Layer (type) Output Shape Param #

dense_11 (Dense) (None, 2) 10

Total params: 10 (40.00 Byte) Trainable params: 10 (40.00 Byte) Non-trainable params: 0 (0.00 Byte)

Models built with a predefined input shape like this always have weights (even before seeing any data) and always have a defined output shape.

In general, it's a recommended best practice to always specify the input shape of a Sequential model in advance if you know what it is.

A common debugging workflow: add() + summary()

When building a new Sequential architecture, it's useful to incrementally stack layers with add() and frequently print model summaries. For instance, this enables you to monitor how a stack of Conv2D and MaxPooling2D layers is downsampling image feature maps:

model = keras.Sequential()
model.add(keras.Input(shape=(250, 250, 3)))  # 250x250 RGB images
model.add(layers.Conv2D(32, 5, strides=2, activation="relu"))
model.add(layers.Conv2D(32, 3, activation="relu"))
model.add(layers.MaxPooling2D(3))

# Can you guess what the current output shape is at this point? Probably not.
# Let's just print it:
model.summary()

# The answer was: (40, 40, 32), so we can keep downsampling...

model.add(layers.Conv2D(32, 3, activation="relu"))
model.add(layers.Conv2D(32, 3, activation="relu"))
model.add(layers.MaxPooling2D(3))
model.add(layers.Conv2D(32, 3, activation="relu"))
model.add(layers.Conv2D(32, 3, activation="relu"))
model.add(layers.MaxPooling2D(2))

# And now?
model.summary()

# Now that we have 4x4 feature maps, time to apply global max pooling.
model.add(layers.GlobalMaxPooling2D())

# Finally, we add a classification layer.
model.add(layers.Dense(10))

Model: "sequential_6" _________________________________________________________________ Layer (type) Output Shape Param #

conv2d (Conv2D) (None, 123, 123, 32) 2432

conv2d_1 (Conv2D) (None, 121, 121, 32) 9248

max_pooling2d (MaxPooling2 (None, 40, 40, 32) 0
D)

Total params: 11680 (45.62 KB) Trainable params: 11680 (45.62 KB) Non-trainable params: 0 (0.00 Byte) _________________________________________________________________ Model: "sequential_6" _________________________________________________________________ Layer (type) Output Shape Param #

conv2d (Conv2D) (None, 123, 123, 32) 2432

conv2d_1 (Conv2D) (None, 121, 121, 32) 9248

max_pooling2d (MaxPooling2 (None, 40, 40, 32) 0
D)

conv2d_2 (Conv2D) (None, 38, 38, 32) 9248

conv2d_3 (Conv2D) (None, 36, 36, 32) 9248

max_pooling2d_1 (MaxPoolin (None, 12, 12, 32) 0
g2D)

conv2d_4 (Conv2D) (None, 10, 10, 32) 9248

conv2d_5 (Conv2D) (None, 8, 8, 32) 9248

max_pooling2d_2 (MaxPoolin (None, 4, 4, 32) 0
g2D)

Total params: 48672 (190.12 KB) Trainable params: 48672 (190.12 KB) Non-trainable params: 0 (0.00 Byte)

Very practical, right?

What to do once you have a model

Once your model architecture is ready, you will want to:

Once a Sequential model has been built, it behaves like a Functional API model. This means that every layer has an inputand output attribute. These attributes can be used to do neat things, like quickly creating a model that extracts the outputs of all intermediate layers in a Sequential model:

initial_model = keras.Sequential(
    [
        keras.Input(shape=(250, 250, 3)),
        layers.Conv2D(32, 5, strides=2, activation="relu"),
        layers.Conv2D(32, 3, activation="relu"),
        layers.Conv2D(32, 3, activation="relu"),
    ]
)
feature_extractor = keras.Model(
    inputs=initial_model.inputs,
    outputs=[layer.output for layer in initial_model.layers],
)

# Call feature extractor on test input.
x = tf.ones((1, 250, 250, 3))
features = feature_extractor(x)

Here's a similar example that only extract features from one layer:

initial_model = keras.Sequential(
    [
        keras.Input(shape=(250, 250, 3)),
        layers.Conv2D(32, 5, strides=2, activation="relu"),
        layers.Conv2D(32, 3, activation="relu", name="my_intermediate_layer"),
        layers.Conv2D(32, 3, activation="relu"),
    ]
)
feature_extractor = keras.Model(
    inputs=initial_model.inputs,
    outputs=initial_model.get_layer(name="my_intermediate_layer").output,
)
# Call feature extractor on test input.
x = tf.ones((1, 250, 250, 3))
features = feature_extractor(x)

Transfer learning with a Sequential model

Transfer learning consists of freezing the bottom layers in a model and only training the top layers. If you aren't familiar with it, make sure to read our guide to transfer learning.

Here are two common transfer learning blueprint involving Sequential models.

First, let's say that you have a Sequential model, and you want to freeze all layers except the last one. In this case, you would simply iterate overmodel.layers and set layer.trainable = False on each layer, except the last one. Like this:

model = keras.Sequential([
    keras.Input(shape=(784)),
    layers.Dense(32, activation='relu'),
    layers.Dense(32, activation='relu'),
    layers.Dense(32, activation='relu'),
    layers.Dense(10),
])

# Presumably you would want to first load pre-trained weights.
model.load_weights(...)

# Freeze all layers except the last one.
for layer in model.layers[:-1]:
  layer.trainable = False

# Recompile and train (this will only update the weights of the last layer).
model.compile(...)
model.fit(...)

Another common blueprint is to use a Sequential model to stack a pre-trained model and some freshly initialized classification layers. Like this:

# Load a convolutional base with pre-trained weights
base_model = keras.applications.Xception(
    weights='imagenet',
    include_top=False,
    pooling='avg')

# Freeze the base model
base_model.trainable = False

# Use a Sequential model to add a trainable classifier on top
model = keras.Sequential([
    base_model,
    layers.Dense(1000),
])

# Compile & train
model.compile(...)
model.fit(...)

If you do transfer learning, you will probably find yourself frequently using these two patterns.

That's about all you need to know about Sequential models!

To find out more about building models in Keras, see:

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-01-13 UTC.