TensorFlow 是一个端到端开源机器学习平台
借助 TensorFlow，初学者和专家可以轻松地创建机器学习模型。请参阅以下几部分，了解如何开始使用。
针对新手
您最好从用户友好的 Sequential API 入手。通过将构建块组合在一起来创建模块。请运行下面的“Hello World”示例，然后访问教程以了解详情。
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)
针对专家
Subclassing API 提供了由运行定义的高级研究接口。为您的模型创建一个类，然后以命令方式编写前向传播。您可以轻松编写自定义层、激活函数和训练循环。请运行下面的“Hello World”示例，然后访问教程以了解详情。
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))
常见问题的解决方案
浏览分步教程以帮助您完成项目。
News & announcements
See updates to help you with your work, and subscribe to our monthly TensorFlow newsletter to get the latest announcements sent directly to your inbox.
TensorFlow 2 will include many API changes, such as reordering arguments, renaming symbols, and changing default values for parameters. To streamline the changes, the TensorFlow engineering team has created a tf_upgrade_v2 utility that will help transition legacy code...
通过代码示例了解面向初学者和专家新推出的用户友好型 API，并了解如何在您的项目中应用 Keras Sequential API、Functional API 和 Subclassing API。
TF.Text is a TensorFlow 2 library that handles preprocessing regularly found in text-based models, and other features useful for language modeling not provided by core TensorFlow.