Keras基础自学十一（ 加载权重）

one-hot encoding
Y_labels = to_categorical(Y, num_classes=3)

# 设定随机种子
seed = 7
np.random.seed(seed)
# 构建模型函数
def load_model(optimizer='rmsprop', init='glorot_uniform'):
    # 构建模型
    model = Sequential()
    model.add(Dense(units=4, activation='relu', input_dim=4, kernel_initializer=init))
    model.add(Dense(units=6, activation='relu', kernel_initializer=init))
    model.add(Dense(units=3, activation='softmax', kernel_initializer=init))

    filepath = 'weights.best.h5'    # 加载权重
    model.load_weights(filepath=filepath)    

    # 编译模型
    model.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['accuracy'])

    return model

# 构建模型
model = load_model()

# 评估模型
scores = model.evaluate(x, Y_labels, verbose=0)
print('%s: %.2f%%' % (model.metrics_names[1], scores[1] * 100))