python-kerasHow can I use a GPU with Python and Keras to run an example?
Using a GPU with Python and Keras to run an example is quite simple.
- First, you must install the necessary packages:
pip install tensorflow-gpu
pip install keras
- Then, you must set the backend to use the GPU:
import os
os.environ["CUDA_VISIBLE_DEVICES"]="0"
- Finally, you can run your example code:
import tensorflow as tf
from keras.models import Sequential
model = Sequential()
model.add(tf.keras.layers.Dense(units=1, input_shape=[1]))
model.compile(optimizer='sgd', loss='mean_squared_error')
xs = np.array([-1.0, 0.0, 1.0, 2.0, 3.0, 4.0], dtype=float)
ys = np.array([-3.0, -1.0, 1.0, 3.0, 5.0, 7.0], dtype=float)
model.fit(xs, ys, epochs=500)
print(model.predict([10.0]))
Output example
[[18.979214]]
The code above will use the GPU to run an example of training a simple linear model using Keras and TensorFlow.
The first two lines install the necessary packages. The third line sets the backend to use the GPU. The fourth line imports the necessary libraries. The fifth line creates a model and adds a single layer. The sixth line compiles the model. The seventh and eighth lines create the data. The ninth line trains the model. The tenth line prints the prediction for the given input.
Helpful links
More of Python Keras
- How do I use Python Keras to zip a file?
- How can I improve the validation accuracy of my Keras model using Python?
- How do I use Python Keras to create a Zoom application?
- How can I use XGBoost, Python and Keras together to build a machine learning model?
- How can I use Python and Keras to create a Variational Autoencoder (VAE)?
- How can I use YOLO with Python and Keras?
- How do I use validation_data when creating a Keras model in Python?
- How can I use word2vec and Keras to develop a machine learning model in Python?
- How do I save weights in a Python Keras model?
- How do I use a webcam with Python and Keras?
See more codes...