Home > Article > Backend Development > How to use the keras module for deep learning in Python 3.x
How to use the Keras module for deep learning in Python 3.x
Keras is a high-level neural network library for building and training deep learning models. It is based on Python and supports backends such as TensorFlow, Theano, and MxNet. Keras provides a simple and easy-to-use API, allowing us to quickly build various types of deep learning models, such as Multilayer Perceptron, Convolutional Neural Network and Recurrent Neural Network )wait.
This article will introduce how to use the Keras module for deep learning in the Python 3.x environment. We will first install Keras and its dependent libraries, and then learn how to build and train a simple neural network model through a simple example code.
1. Install Keras
Before we begin, we need to install Keras into our Python environment. Keras can be installed using pip through the following command:
pip install keras
2. Build a simple neural network model
Next, we will use Keras to build a simple neural network model to realize handwritten digit recognition Task. First, we need to import the necessary libraries:
import numpy as np from keras.models import Sequential from keras.layers import Dense from keras.utils import np_utils
Then, we need to load the MNIST data set, which contains 60,000 training samples and 10,000 test samples. Each sample is a 28x28 grayscale image, corresponding to a A number between [0, 9]. The following code can be used to load the dataset:
from keras.datasets import mnist (X_train, Y_train), (X_test, Y_test) = mnist.load_data()
Next, we need to preprocess the data. Since the original image data is a 28x28 grayscale image, we need to flatten it into a 784-dimensional vector and normalize the input data to scale the pixel value from the range of [0, 255] to [0, 1 ] Within the range:
X_train = X_train.reshape(X_train.shape[0], 784).astype('float32') / 255 X_test = X_test.reshape(X_test.shape[0], 784).astype('float32') / 255
In order to be able to train the model, we also need to one-hot encode the label. Keras provides the np_utils.to_categorical() function to help us achieve this step:
Y_train = np_utils.to_categorical(Y_train, 10) Y_test = np_utils.to_categorical(Y_test, 10)
Now, we can build a simple multilayer perceptron (Multilayer Perceptron) model. This model contains an input layer, two hidden layers and an output layer. You can use the Sequential() function to create a sequence model and the Dense() function to add layers:
model = Sequential() model.add(Dense(units=512, input_dim=784, activation='relu')) model.add(Dense(units=512, activation='relu')) model.add(Dense(units=10, activation='softmax'))
After the model is built, we need to compile the model. You can use the compile() function to configure the model training process. Here, we can specify the loss function, optimizer and evaluation index:
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
3. Training model and prediction
After the model is compiled, we can use the fit() function to train the model. You can specify the training data, the number of training rounds, and the number of samples in each batch:
model.fit(X_train, Y_train, epochs=10, batch_size=128)
After the model training is completed, we can use the evaluate() function to evaluate the performance of the model on the test set:
loss, accuracy = model.evaluate(X_test, Y_test) print('Test loss:', loss) print('Test accuracy:', accuracy)
Finally, we can use the predict_classes() function to predict the category of new samples:
predictions = model.predict_classes(X_test)
In this way, we have completed the construction and training process of a simple neural network model.
Summary:
This article introduces how to use the Keras module for deep learning in Python 3.x. We first installed Keras and its dependent libraries, and then learned how to build and train a simple neural network model through sample code. This is just an introduction to deep learning. Keras also provides more functions and models to meet different needs. I hope that readers can have a preliminary understanding of Keras and deep learning through the introduction of this article, and be able to use it in practical applications.
The above is the detailed content of How to use the keras module for deep learning in Python 3.x. For more information, please follow other related articles on the PHP Chinese website!