Python tensorflow example

Python tensorflow example

Here's a simple example of using TensorFlow to create a basic neural network and train it on the MNIST dataset:

# Import necessary modules
import numpy as np
from sklearn.metrics import accuracy_score
from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout
Load MNIST dataset
(x_train, y_train), (x_test, y_test) = mnist.load_data()
Normalize pixel values to be between 0 and 1
x_train, x_test = x_train / 255.0, x_test / 255.0
One-hot encode the output labels
y_train = np.eye(10)[y_train]
Create a Sequential model with two hidden layers
model = Sequential()
model.add(Dense(128, activation='relu', input_shape=(28*28,)))
model.add(Dropout(0.2))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.3))
model.add(Dense(10))
Compile the model with loss function and optimizer
model.compile(loss='categorical_crossentropy', optimizer='adam')
Train the model on the training set
model.fit(x_train, y_train, epochs=5, batch_size=128)
Evaluate the model on the test set
y_pred = model.predict(x_test)
y_pred_class = np.argmax(y_pred, axis=1)
print("Test accuracy:", accuracy_score(np.argmax(y_test, axis=1), y_pred_class))

This code creates a basic neural network with two hidden layers and trains it on the MNIST dataset. The goal is to classify hand-written digits (0-9). The model uses ReLU activation functions for the hidden layers and categorical cross-entropy loss function.

The accuracy of the model can be evaluated by comparing its predictions with the true labels of the test set. The result should be around 97%, which is a reasonable accuracy for this simple neural network architecture on the MNIST dataset.

Here's how you could improve the code:

Note: This example uses Keras API to create and train the neural network.

How do I run TensorFlow in Python?

To run TensorFlow in Python, you'll need to install the necessary packages and set up a basic environment. Here's a step-by-step guide:

pip install tensorflow

This will download and install the latest version of TensorFlow.

import tensorflow as tf
print(tf.version)

This should print the current version of TensorFlow installed on your system.

Here's an example script:

import tensorflow as tf
Set up some constants
LEARNING_RATE = 0.01
TRAINING_STEPS = 1000
Create a simple neural network model
model = tf.keras.models.Sequential([
tf.keras.layers.Dense(64, activation='relu', input_shape=(784,)),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(10, activation='softmax')
])
Compile the model
model.compile(optimizer=tf.keras.optimizers.Adam(LEARNING_RATE),
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
Train the model on a simple dataset (e.g., MNIST)
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
model.fit(x_train, y_train, epochs=TRAINING_STEPS, verbose=2)
Evaluate the model
test_loss, test_acc = model.evaluate(x_test, y_test, verbose=2)
print(f"Test accuracy: {test_acc:.3f}")

In this example, we're creating a simple neural network with three layers. We're then training it on the MNIST dataset and evaluating its performance.

python tf_example.py

This will execute your script and output the results. You should see some output indicating that the model has been trained and evaluated successfully.

Remember to keep an eye on the TensorFlow documentation and tutorials for more advanced topics and best practices. Happy coding!