Learn Keras - 10 Code Examples & CST Typing Practice Test

Keras is an open-source, high-level deep learning API written in Python. It provides a user-friendly interface for building and training neural networks, running on top of TensorFlow, Theano, or CNTK backends.

View all 10 Keras code examples →

Keras Simple Linear Regression Keras Simple Neural Network Keras MNIST Classifier Keras Convolutional Neural Network Keras LSTM Example Keras Autoencoder Example Keras Regression with Multiple Inputs Keras Transfer Learning Example Keras Custom Callback Example Keras GAN Example

Learn KERAS with Real Code Examples

Updated Nov 24, 2025

Introduction & Fundamentals Setup & Configuration Architecture & Deep Internals Performance & Security Development Workflow Learning & Career Growth Business & Strategy Examples

Code Sample Descriptions

Keras Simple Linear Regression

import numpy as np
from tensorflow import keras
from tensorflow.keras import layers

# Sample data
x_train = np.array([1, 2, 3, 4], dtype=float)
y_train = np.array([2, 4, 6, 8], dtype=float)

# Define model
model = keras.Sequential([layers.Dense(units=1, input_shape=[1])])
model.compile(optimizer='sgd', loss='mean_squared_error')

# Train the model
model.fit(x_train, y_train, epochs=500)

# Predict
y_pred = model.predict([10.0])
print("Prediction for 10:", y_pred)

A minimal Keras example for linear regression using a single dense layer.

Let’s Try →

Keras Simple Neural Network

import numpy as np
from tensorflow import keras
from tensorflow.keras import layers

# Sample data
x_train = np.random.rand(100,3)
y_train = np.random.randint(0,2,100)

# Define model
model = keras.Sequential([
    layers.Dense(8, activation='relu', input_shape=[3]),
    layers.Dense(1, activation='sigmoid')
])

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=50)

Basic feedforward neural network for binary classification.

Let’s Try →

Keras MNIST Classifier

from tensorflow import keras
from tensorflow.keras import layers

(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
x_train, x_test = x_train/255.0, x_test/255.0

model = keras.Sequential([
    layers.Flatten(input_shape=(28,28)),
    layers.Dense(128, activation='relu'),
    layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=5)
model.evaluate(x_test, y_test)

Train a simple fully-connected network on MNIST digits.

Let’s Try →

Keras Convolutional Neural Network

from tensorflow import keras
from tensorflow.keras import layers

model = keras.Sequential([
    layers.Conv2D(32, (3,3), activation='relu', input_shape=(28,28,1)),
    layers.MaxPooling2D((2,2)),
    layers.Flatten(),
    layers.Dense(64, activation='relu'),
    layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

A simple CNN for image classification.

Let’s Try →

Keras LSTM Example

import numpy as np
from tensorflow import keras
from tensorflow.keras import layers

x_train = np.random.rand(100,10,1)
y_train = np.random.rand(100,1)

model = keras.Sequential([
    layers.LSTM(50, input_shape=(10,1)),
    layers.Dense(1)
])

model.compile(optimizer='adam', loss='mse')
model.fit(x_train, y_train, epochs=20)

A simple LSTM network for sequence prediction.

Let’s Try →

Keras Autoencoder Example

from tensorflow import keras
from tensorflow.keras import layers

input_dim = 20
model = keras.Sequential([
    layers.Dense(10, activation='relu', input_shape=(input_dim,)),
    layers.Dense(5, activation='relu'),
    layers.Dense(10, activation='relu'),
    layers.Dense(input_dim, activation='sigmoid')
])
model.compile(optimizer='adam', loss='mse')

A simple autoencoder for dimensionality reduction.

Let’s Try →

Keras Regression with Multiple Inputs

import numpy as np
from tensorflow import keras
from tensorflow.keras import layers

x_train = np.random.rand(100,3)
y_train = np.dot(x_train, [1.5,-2.0,1.0])+0.5

model = keras.Sequential([layers.Dense(1, input_shape=[3])])
model.compile(optimizer='sgd', loss='mse')
model.fit(x_train, y_train, epochs=100)

Linear regression with multiple features.

Let’s Try →

Keras Transfer Learning Example

from tensorflow import keras
base_model = keras.applications.MobileNetV2(input_shape=(128,128,3), include_top=False, weights='imagenet')
base_model.trainable = False
model = keras.Sequential([
    base_model,
    layers.GlobalAveragePooling2D(),
    layers.Dense(10, activation='softmax')
])
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

Use a pre-trained MobileNetV2 for image classification.

Let’s Try →

Keras Custom Callback Example

from tensorflow import keras

class PrintLossCallback(keras.callbacks.Callback):
    def on_epoch_end(self, epoch, logs=None):
        print(f"Epoch {epoch+1}: loss = {logs['loss']}")

model = keras.Sequential([keras.layers.Dense(1, input_shape=[1])])
model.compile(optimizer='sgd', loss='mse')
model.fit([1,2,3],[2,4,6], epochs=5, callbacks=[PrintLossCallback()])

Custom callback to print loss at each epoch.

Let’s Try →

Keras GAN Example

from tensorflow import keras
from tensorflow.keras import layers

# Generator
generator = keras.Sequential([
    layers.Dense(128, activation='relu', input_shape=(100,)),
    layers.Dense(784, activation='sigmoid')
])

# Discriminator
discriminator = keras.Sequential([
    layers.Dense(128, activation='relu', input_shape=(784,)),
    layers.Dense(1, activation='sigmoid')
])
discriminator.compile(optimizer='adam', loss='binary_crossentropy')

Minimal GAN architecture structure in Keras.

Let’s Try →

Frequently Asked Questions about Keras

What is Keras?

What are the primary use cases for Keras?

Image classification and object detection. Natural language processing (NLP). Reinforcement learning prototypes. Time series forecasting. Educational purposes and research experiments

What are the strengths of Keras?

Easy to learn and use. Rapid prototyping of deep learning models. Highly modular and extensible. Strong community and documentation. Backend-agnostic (primarily TensorFlow)

What are the limitations of Keras?

Less control for low-level custom operations compared to raw TensorFlow. Primarily Python-based. Not ideal for highly optimized production pipelines without TensorFlow knowledge. Limited support for non-TensorFlow backends in recent versions. Scaling very large models requires careful backend management

How can I practice Keras typing speed?

CodeSpeedTest offers 10+ real Keras code examples for typing practice. You can measure your WPM, track accuracy, and improve your coding speed with guided exercises.

Learn Other Programming Languages

C React Python C++Rust TypeScript Kotlin PHP Java C#Ruby Mql Cql N1ql Cypher Gremlin Partiql Haskell Elixir Fsharp View all languages →

Code Sample Descriptions

Keras Simple Linear Regression

import numpy as np
from tensorflow import keras
from tensorflow.keras import layers

# Sample data
x_train = np.array([1, 2, 3, 4], dtype=float)
y_train = np.array([2, 4, 6, 8], dtype=float)

# Define model
model = keras.Sequential([layers.Dense(units=1, input_shape=[1])])
model.compile(optimizer='sgd', loss='mean_squared_error')

# Train the model
model.fit(x_train, y_train, epochs=500)

# Predict
y_pred = model.predict([10.0])
print("Prediction for 10:", y_pred)

A minimal Keras example for linear regression using a single dense layer.

Let’s Try →

Keras Simple Neural Network

import numpy as np
from tensorflow import keras
from tensorflow.keras import layers

# Sample data
x_train = np.random.rand(100,3)
y_train = np.random.randint(0,2,100)

# Define model
model = keras.Sequential([
    layers.Dense(8, activation='relu', input_shape=[3]),
    layers.Dense(1, activation='sigmoid')
])

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=50)

Basic feedforward neural network for binary classification.

Let’s Try →

Keras MNIST Classifier

from tensorflow import keras
from tensorflow.keras import layers

(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
x_train, x_test = x_train/255.0, x_test/255.0

model = keras.Sequential([
    layers.Flatten(input_shape=(28,28)),
    layers.Dense(128, activation='relu'),
    layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=5)
model.evaluate(x_test, y_test)

Train a simple fully-connected network on MNIST digits.

Let’s Try →

Keras Convolutional Neural Network

from tensorflow import keras
from tensorflow.keras import layers

model = keras.Sequential([
    layers.Conv2D(32, (3,3), activation='relu', input_shape=(28,28,1)),
    layers.MaxPooling2D((2,2)),
    layers.Flatten(),
    layers.Dense(64, activation='relu'),
    layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

A simple CNN for image classification.

Let’s Try →

Keras LSTM Example

import numpy as np
from tensorflow import keras
from tensorflow.keras import layers

x_train = np.random.rand(100,10,1)
y_train = np.random.rand(100,1)

model = keras.Sequential([
    layers.LSTM(50, input_shape=(10,1)),
    layers.Dense(1)
])

model.compile(optimizer='adam', loss='mse')
model.fit(x_train, y_train, epochs=20)

A simple LSTM network for sequence prediction.

Let’s Try →

Keras Autoencoder Example

from tensorflow import keras
from tensorflow.keras import layers

input_dim = 20
model = keras.Sequential([
    layers.Dense(10, activation='relu', input_shape=(input_dim,)),
    layers.Dense(5, activation='relu'),
    layers.Dense(10, activation='relu'),
    layers.Dense(input_dim, activation='sigmoid')
])
model.compile(optimizer='adam', loss='mse')

A simple autoencoder for dimensionality reduction.

Let’s Try →

Keras Regression with Multiple Inputs

import numpy as np
from tensorflow import keras
from tensorflow.keras import layers

x_train = np.random.rand(100,3)
y_train = np.dot(x_train, [1.5,-2.0,1.0])+0.5

model = keras.Sequential([layers.Dense(1, input_shape=[3])])
model.compile(optimizer='sgd', loss='mse')
model.fit(x_train, y_train, epochs=100)

Linear regression with multiple features.

Let’s Try →

Keras Transfer Learning Example

from tensorflow import keras
base_model = keras.applications.MobileNetV2(input_shape=(128,128,3), include_top=False, weights='imagenet')
base_model.trainable = False
model = keras.Sequential([
    base_model,
    layers.GlobalAveragePooling2D(),
    layers.Dense(10, activation='softmax')
])
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

Use a pre-trained MobileNetV2 for image classification.

Let’s Try →

Keras Custom Callback Example

from tensorflow import keras

class PrintLossCallback(keras.callbacks.Callback):
    def on_epoch_end(self, epoch, logs=None):
        print(f"Epoch {epoch+1}: loss = {logs['loss']}")

model = keras.Sequential([keras.layers.Dense(1, input_shape=[1])])
model.compile(optimizer='sgd', loss='mse')
model.fit([1,2,3],[2,4,6], epochs=5, callbacks=[PrintLossCallback()])

Custom callback to print loss at each epoch.

Let’s Try →

Keras GAN Example

from tensorflow import keras
from tensorflow.keras import layers

# Generator
generator = keras.Sequential([
    layers.Dense(128, activation='relu', input_shape=(100,)),
    layers.Dense(784, activation='sigmoid')
])

# Discriminator
discriminator = keras.Sequential([
    layers.Dense(128, activation='relu', input_shape=(784,)),
    layers.Dense(1, activation='sigmoid')
])
discriminator.compile(optimizer='adam', loss='binary_crossentropy')

Minimal GAN architecture structure in Keras.

Let’s Try →

Frequently Asked Questions about Keras

What is Keras?

What are the primary use cases for Keras?

Image classification and object detection. Natural language processing (NLP). Reinforcement learning prototypes. Time series forecasting. Educational purposes and research experiments

What are the strengths of Keras?

Easy to learn and use. Rapid prototyping of deep learning models. Highly modular and extensible. Strong community and documentation. Backend-agnostic (primarily TensorFlow)

What are the limitations of Keras?

How can I practice Keras typing speed?

CodeSpeedTest offers 10+ real Keras code examples for typing practice. You can measure your WPM, track accuracy, and improve your coding speed with guided exercises.