Keras 3.0 发布

机器学习开发者的超能力

Keras 是一个为人类而非机器设计的深度学习 API。Keras 专注于调试速度、代码优雅与简洁、可维护性和可部署性。选择 Keras，您的代码库将更小、更易读、更易于迭代。

inputs = keras.Input(shape=(32, 32, 3))
x = layers.Conv2D(32, 3, activation="relu")(inputs)
x = layers.Conv2D(64, 3, activation="relu")(x)
residual = x = layers.MaxPooling2D(3)(x)

x = layers.Conv2D(64, 3, padding="same")(x)
x = layers.Activation("relu")(x)
x = layers.Conv2D(64, 3, padding="same")(x)
x = layers.Activation("relu")(x)
x = x + residual

x = layers.Conv2D(64, 3, activation="relu")(x)
x = layers.GlobalAveragePooling2D()(x)
outputs = layers.Dense(10, activation="softmax")(x)

model = keras.Model(inputs, outputs, name="mini_resnet")
keras.utils.plot_model(model, "mini_resnet.png")
model.fit(dataset, epochs=10)

运行快速入门

causal_lm = keras_hub.models.CausalLM.from_preset(
  "gemma2_instruct_2b_en",
  dtype="float16",
)
prompt = """<start_of_turn>user
Write python code to print the first 100 primes.
<end_of_turn>
<start_of_turn>model
"""
text_output = causal_lm.generate(prompt, max_length=512)

text_to_image = keras_hub.models.TextToImage.from_preset(
    "stable_diffusion_3_medium",
    dtype="float16",
)
prompt = "Astronaut in a jungle, detailed"
image_output = text_to_image.generate(prompt)

运行快速入门

欢迎来到多框架机器学习

Keras 采用多后端方法，让您能够自由使用 JAX、TensorFlow 和 PyTorch。构建可在这些框架之间无缝迁移的模型，并利用每个生态系统的优势。

入门指南

inputs = keras.Input(shape=(28, 28, 1))
x = inputs
x = layers.Conv2D(16, 3, activation="relu")(x)
x = layers.Conv2D(32, 3, activation="relu")(x)
x = layers.MaxPooling2D(3)(x)
x = layers.Conv2D(32, 3, activation="relu")(x)
x = layers.Conv2D(16, 3, activation="relu")(x)
x = layers.GlobalMaxPooling2D()(x)
x = layers.Dropout(0.5)
outputs = layers.Dense(10)

model = keras.Model(inputs, outputs)
model.summary()

函数式 API

从零开始，学习如何使用函数式构建模式来构建模型。

查看指南

model.compile(
    optimizer="rmsprop",
    loss="categorical_crossentropy",
    metrics=["accuracy"],
)

history = model.fit(
    x_train,
    y_train,
    batch_size=64,
    epochs=2,
    validation_data=(x_val, y_val),
)

使用内置方法进行训练和评估

使用 model.fit(...) 训练和评估您的模型。

查看指南

class MLPBlock(keras.layers.Layer):
    def __init__(self):
        super().__init__()
        self.dense_1 = layers.Dense(32)
        self.dense_2 = layers.Dense(32)
        self.dense_3 = layers.Dense(1)

    def call(self, inputs):
        x = self.dense_1(inputs)
        x = keras.activations.relu(x)
        x = self.dense_2(x)
        x = keras.activations.relu(x)
        return self.dense_3(x)