Keras 3.0 釋出

機器學習開發者的超能力

Keras 是一個為人類而非機器設計的深度學習 API。Keras 專注於除錯速度、程式碼優雅與簡潔、可維護性和可部署性。選擇 Keras，您的程式碼庫將更小、更易讀、更易於迭代。

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)

執行快速入門

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)

執行快速入門

歡迎來到多框架機器學習

Keras 採用多後端方法，讓您能夠自由使用 JAX、TensorFlow 和 PyTorch。構建可在這些框架之間無縫遷移的模型，並利用每個生態系統的優勢。

入門指南

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()

函式式 API

從零開始，學習如何使用函式式構建模式來構建模型。

檢視指南

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),
)

使用內建方法進行訓練和評估

使用 model.fit(...) 訓練和評估您的模型。

檢視指南

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)