model = keras.Sequential([
    keras.Input(shape=(3, 1)),
    layers.Dense(2, activation="relu", name="layer1"),
    layers.Dense(3, activation="relu", name="layer2"),
    layers.Dense(4, name="layer3"),
])

# تمرير قائمة من الطبقات للباني (Constructor)
model = keras.Sequential([
    layers.Dense(2, activation="relu"),
    layers.Dense(3, activation="relu"),
    layers.Dense(4),
])

# أو البناء تدريجيا
model = keras.Sequential()
model.add(layers.Dense(2, activation="relu"))
model.add(layers.Dense(3, activation="relu"))
model.add(layers.Dense(4))
model.pop()   # يحذف الطبقة الأخيرة - يتصرف كقائمة من الطبقات

layer = layers.Dense(3)
layer.weights          # [] - فارغة

x = ops.ones((1, 4))
y = layer(x)
layer.weights           # الآن لديها أوزان: بشكل (4, 3) و(3,)

model = keras.Sequential()
model.add(keras.Input(shape=(4,)))
model.add(layers.Dense(2, activation="relu"))

model.summary()   # تعمل فورا - النموذج مبني بالفعل ("built")

model.summary()

Model: "sequential"
 Layer (type)      Output Shape       Param #
 dense (Dense)      (1, 2)              10
 dense_1 (Dense)     (1, 3)               9
 dense_2 (Dense)     (1, 4)              16
 Total params: 35

model = keras.Sequential()
model.add(keras.Input(shape=(784,)))
model.add(layers.Dense(64, activation="relu"))
model.add(layers.Dense(64, activation="relu"))
model.add(layers.Dense(10, activation="softmax"))

(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
x_train = x_train.reshape(60000, 784).astype("float32") / 255
x_test = x_test.reshape(10000, 784).astype("float32") / 255

# حجز 10,000 عينة للتحقق (Validation)
x_val, y_val = x_train[-10000:], y_train[-10000:]
x_train, y_train = x_train[:-10000], y_train[:-10000]

model.compile(
    optimizer=keras.optimizers.RMSprop(learning_rate=1e-3),
    loss=keras.losses.SparseCategoricalCrossentropy(),
    metrics=[keras.metrics.SparseCategoricalAccuracy()],
)

# اختصار بمعرفات نصية للإعدادات الافتراضية
model.compile(optimizer="rmsprop",
              loss="sparse_categorical_crossentropy",
              metrics=["sparse_categorical_accuracy"])

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

results = model.evaluate(x_test, y_test, batch_size=128)
print("test loss, test acc:", results)

predictions = model.predict(x_test[:3])   # احتمالات من الطبقة الأخيرة
print("predictions shape:", predictions.shape)

inputs = keras.Input(shape=(784,))
x = layers.Dense(64, activation="relu")(inputs)
x = layers.Dense(64, activation="relu")(x)
outputs = layers.Dense(10)(x)

model = keras.Model(inputs=inputs, outputs=outputs, name="mnist_model")