Learn Tensorflow - 10 Code Examples & CST Typing Practice Test

TensorFlow is an open-source, end-to-end platform for machine learning developed by Google. It provides comprehensive tools, libraries, and community resources for building and deploying ML models across different environments.

View all 10 Tensorflow code examples →

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

Learn TENSORFLOW 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

TensorFlow Simple Linear Regression

import tensorflow as tf
import numpy as np

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

# Define a simple linear model
model = tf.keras.Sequential([tf.keras.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 TensorFlow example showing linear regression training on sample data.

Let’s Try →

TensorFlow Simple Neural Network

import tensorflow as tf
import numpy as np

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

# Define model
model = tf.keras.Sequential([
    tf.keras.layers.Dense(8, activation='relu', input_shape=[3]),
    tf.keras.layers.Dense(1, activation='sigmoid')
])
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

# Train
model.fit(x_train, y_train, epochs=50)

A basic feedforward neural network for classification.

Let’s Try →

TensorFlow MNIST Example

import tensorflow as tf
mnist = tf.keras.datasets.mnist

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

model = tf.keras.Sequential([
    tf.keras.layers.Flatten(input_shape=(28,28)),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.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 MNIST digit classifier using TensorFlow.

Let’s Try →

TensorFlow Convolutional Neural Network

import tensorflow as tf
from tensorflow.keras import layers, models

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

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

A simple CNN for image classification.

Let’s Try →

TensorFlow LSTM Example

import tensorflow as tf
import numpy as np

# Sample sequence data
x_train = np.random.rand(100, 10, 1)
y_train = np.random.rand(100, 1)

model = tf.keras.Sequential([
    tf.keras.layers.LSTM(50, input_shape=(10,1)),
    tf.keras.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 →

TensorFlow Autoencoder Example

import tensorflow as tf
from tensorflow.keras import layers, models

input_dim = 20
model = models.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 data compression.

Let’s Try →

TensorFlow Regression with Multiple Inputs

import tensorflow as tf
import numpy as np

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

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

Linear regression with multiple input features.

Let’s Try →

TensorFlow Transfer Learning Example

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

Use a pre-trained MobileNet model for image classification.

Let’s Try →

TensorFlow Custom Callback Example

import tensorflow as tf

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

model = tf.keras.Sequential([tf.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()])

Define a custom callback to print loss after each epoch.

Let’s Try →

TensorFlow GAN Example

import tensorflow as tf
from tensorflow.keras import layers

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

# Discriminator
discriminator = tf.keras.Sequential([
    layers.Dense(128, activation='relu', input_shape=(784,)),
    layers.Dense(1, activation='sigmoid')
])

# Compile discriminator
discriminator.compile(optimizer='adam', loss='binary_crossentropy')

A minimal GAN example structure.

Let’s Try →

Frequently Asked Questions about Tensorflow

What is Tensorflow?

What are the primary use cases for Tensorflow?

Deep learning for image, video, and speech recognition. Natural language processing and translation. Reinforcement learning for AI agents. Time series forecasting and predictive analytics. Deployment of AI models on cloud, mobile, and embedded devices

What are the strengths of Tensorflow?

Highly scalable for large datasets and models. Cross-platform support: desktop, mobile, cloud. Extensive ecosystem with tools and libraries. Strong community support and documentation. Production-ready pipelines and deployment options

What are the limitations of Tensorflow?

Steep learning curve for beginners. Verbose for low-level model definitions. Debugging can be complex for graph-based models. Python-centric (other languages supported but limited). Can be overkill for small or simple ML tasks

How can I practice Tensorflow typing speed?

CodeSpeedTest offers 10+ real Tensorflow 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

TensorFlow Simple Linear Regression

import tensorflow as tf
import numpy as np

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

# Define a simple linear model
model = tf.keras.Sequential([tf.keras.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 TensorFlow example showing linear regression training on sample data.

Let’s Try →

TensorFlow Simple Neural Network

import tensorflow as tf
import numpy as np

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

# Define model
model = tf.keras.Sequential([
    tf.keras.layers.Dense(8, activation='relu', input_shape=[3]),
    tf.keras.layers.Dense(1, activation='sigmoid')
])
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

# Train
model.fit(x_train, y_train, epochs=50)

A basic feedforward neural network for classification.

Let’s Try →

TensorFlow MNIST Example

import tensorflow as tf
mnist = tf.keras.datasets.mnist

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

model = tf.keras.Sequential([
    tf.keras.layers.Flatten(input_shape=(28,28)),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.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 MNIST digit classifier using TensorFlow.

Let’s Try →

TensorFlow Convolutional Neural Network

import tensorflow as tf
from tensorflow.keras import layers, models

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

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

A simple CNN for image classification.

Let’s Try →

TensorFlow LSTM Example

import tensorflow as tf
import numpy as np

# Sample sequence data
x_train = np.random.rand(100, 10, 1)
y_train = np.random.rand(100, 1)

model = tf.keras.Sequential([
    tf.keras.layers.LSTM(50, input_shape=(10,1)),
    tf.keras.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 →

TensorFlow Autoencoder Example

import tensorflow as tf
from tensorflow.keras import layers, models

input_dim = 20
model = models.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 data compression.

Let’s Try →

TensorFlow Regression with Multiple Inputs

import tensorflow as tf
import numpy as np

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

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

Linear regression with multiple input features.

Let’s Try →

TensorFlow Transfer Learning Example

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

Use a pre-trained MobileNet model for image classification.

Let’s Try →

TensorFlow Custom Callback Example

import tensorflow as tf

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

model = tf.keras.Sequential([tf.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()])

Define a custom callback to print loss after each epoch.

Let’s Try →

TensorFlow GAN Example

import tensorflow as tf
from tensorflow.keras import layers

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

# Discriminator
discriminator = tf.keras.Sequential([
    layers.Dense(128, activation='relu', input_shape=(784,)),
    layers.Dense(1, activation='sigmoid')
])

# Compile discriminator
discriminator.compile(optimizer='adam', loss='binary_crossentropy')

A minimal GAN example structure.

Let’s Try →

Frequently Asked Questions about Tensorflow

What is Tensorflow?

What are the primary use cases for Tensorflow?

What are the strengths of Tensorflow?

What are the limitations of Tensorflow?

How can I practice Tensorflow typing speed?

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