TensorFlow is an end-to-end open source platform for machine learning
TensorFlow makes it easy for beginners and experts to create machine learning models. See the sections below to get started.
For beginners
The best place to start is with the user-friendly Sequential API. You can create models by plugging together building blocks. Run the “Hello World” example below, then visit the tutorials to learn more.
To learn ML, check out our education page. Begin with curated curriculums to improve your skills in foundational ML areas.
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.models.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28)),
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dropout(0.2),
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)
For experts
The Subclassing API provides a define-by-run interface for advanced research. Create a class for your model, then write the forward pass imperatively. Easily author custom layers, activations, and training loops. Run the “Hello World” example below, then visit the tutorials to learn more.
class MyModel(tf.keras.Model):
def __init__(self):
super(MyModel, self).__init__()
self.conv1 = Conv2D(32, 3, activation='relu')
self.flatten = Flatten()
self.d1 = Dense(128, activation='relu')
self.d2 = Dense(10, activation='softmax')
def call(self, x):
x = self.conv1(x)
x = self.flatten(x)
x = self.d1(x)
return self.d2(x)
model = MyModel()
with tf.GradientTape() as tape:
logits = model(images)
loss_value = loss(logits, labels)
grads = tape.gradient(loss_value, model.trainable_variables)
optimizer.apply_gradients(zip(grads, model.trainable_variables))
Solutions to common problems
Explore step-by-step tutorials to help you with your projects.
Train a neural network to classify images of clothing, like sneakers and shirts, in this fast-paced overview of a complete TensorFlow program.
Train a generative adversarial network to generate images of handwritten digits, using the Keras Subclassing API.
Train a sequence-to-sequence model for Spanish to English translation using the Keras Subclassing API.
See how well you synchronize to the lyrics of the popular hit "Dance Monkey." This in-browser experience uses the Facemesh model for estimating key points around the lips to score lip-syncing accuracy.
Our codebase offers tight Keras integration, access to distribution strategies, easy debugging with eager execution - all the goodies that one might expect from a TensorFlow 2 codebase.
TensorFlow 2.3 showcases new features in ‘tf.data’ to solve input pipeline bottlenecks and save resources, Keras experimental Preprocessing Layers for data preprocessing, and new TF Profiler tools.
This new tutorial shows an off-the-shelf implementation of text transfer learning using BERT, designed to let you modify or retrain it from scratch.