TensorFlow es una plataforma de código abierto de extremo a extremo para el aprendizaje automático

TensorFlow facilita la creación de modelos de aprendizaje automático, sin importar si eres principiante o experto. Consulta las secciones que se encuentran a continuación para comenzar.

Ver los instructivos

Los instructivos te enseñan a usar TensorFlow con ejemplos completos de extremo a extremo.

Ver la guía

Las guías explican los conceptos y los componentes de TensorFlow.

Para principiantes

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.Dense(10, activation='softmax')


model.fit(x_train, y_train, epochs=5)
model.evaluate(x_test, y_test)

Para expertos

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))

Soluciones para problemas comunes

Explora instructivos paso a paso para obtener ayuda con tus proyectos.

ML basics with Keras
Tu primera red neuronal

Entrena una red neuronal para que clasifique imágenes de indumentaria, como zapatillas y camisas, en esta reseña rápida de un programa completo de TensorFlow.

Image generation

Generate images based on a text prompt using the KerasCV implementation of stability.ai's Stable Diffusion model.

Simple audio recognition

Preprocess WAV files and train a basic automatic speech recognition model.

Noticias y anuncios

Check out our blog for additional updates, and subscribe to our TensorFlow newsletter to get the latest announcements sent directly to your inbox.