FtrlOptimizer
- class
paddle.fluid.optimizer.
FtrlOptimizer
(learning_rate, l1=0.0, l2=0.0, lr_power=-0.5, parameter_list=None, regularization=None, name=None)[源代码]
该接口实现FTRL (Follow The Regularized Leader) Optimizer.
FTRL 原始论文: ( https://www.eecs.tufts.edu/~dsculley/papers/ad-click-prediction.pdf)
- 参数:
- learning_rate (float|Variable)- 全局学习率。
- parameter_list (list, 可选) - 指定优化器需要优化的参数。在动态图模式下必须提供该参数;在静态图模式下默认值为None,这时所有的参数都将被优化。
- l1 (float,可选) - L1 regularization strength,默认值0.0。
- l2 (float,可选) - L2 regularization strength,默认值0.0。
- lr_power (float,可选) - 学习率降低指数,默认值-0.5。
- regularization - 正则化器,例如
fluid.regularizer.L2DecayRegularizer
。 - name (str, 可选) - 可选的名称前缀,一般无需设置,默认值为None。
- 抛出异常:
ValueError
- 如果learning_rate
,rho
,epsilon
,momentum
为 None.
代码示例
- import paddle
- import paddle.fluid as fluid
- import numpy as np
- place = fluid.CPUPlace()
- main = fluid.Program()
- with fluid.program_guard(main):
- x = fluid.layers.data(name='x', shape=[13], dtype='float32')
- y = fluid.layers.data(name='y', shape=[1], dtype='float32')
- y_predict = fluid.layers.fc(input=x, size=1, act=None)
- cost = fluid.layers.square_error_cost(input=y_predict, label=y)
- avg_cost = fluid.layers.mean(cost)
- ftrl_optimizer = fluid.optimizer.Ftrl(learning_rate=0.1)
- ftrl_optimizer.minimize(avg_cost)
- fetch_list = [avg_cost]
- train_reader = paddle.batch(
- paddle.dataset.uci_housing.train(), batch_size=1)
- feeder = fluid.DataFeeder(place=place, feed_list=[x, y])
- exe = fluid.Executor(place)
- exe.run(fluid.default_startup_program())
- for data in train_reader():
- exe.run(main, feed=feeder.feed(data), fetch_list=fetch_list)
注意:目前, FtrlOptimizer 不支持 sparse parameter optimization。
minimize
(loss, startup_program=None, parameter_list=None, no_grad_set=None, grad_clip=None)
通过更新parameter_list来添加操作,进而使损失最小化。
该算子相当于backward()和apply_gradients()功能的合体。
- 参数:
- loss (Variable) – 需要最小化的损失值变量
- startup_program (Program, 可选) – 用于初始化parameter_list中参数的 Program , 默认值为None,此时将使用 default_startup_program
- parameter_list (list, 可选) – 待更新的Parameter或者Parameter.name组成的列表, 默认值为None,此时将更新所有的Parameter
- no_grad_set (set, 可选) – 不需要更新的Parameter或者Parameter.name组成的集合,默认值为None
- grad_clip (GradClipBase, 可选) – 梯度裁剪的策略,静态图模式不需要使用本参数,当前本参数只支持在dygraph模式下的梯度裁剪,未来本参数可能会调整,默认值为None
返回: (optimize_ops, params_grads),数据类型为(list, list),其中optimize_ops是minimize接口为网络添加的OP列表,params_grads是一个由(param, grad)变量对组成的列表,param是Parameter,grad是该Parameter对应的梯度值
返回类型: tuple
clear_gradients
()
注意:
1. 该API只在 Dygraph 模式下生效
清除需要优化的参数的梯度。
代码示例
- import paddle.fluid as fluid
- import numpy as np
- with fluid.dygraph.guard():
- value = np.arange(26).reshape(2, 13).astype("float32")
- a = fluid.dygraph.to_variable(value)
- linear = fluid.Linear(13, 5, dtype="float32")
- optimizer = fluid.optimizer.FtrlOptimizer(learning_rate=0.02,
- parameter_list=linear.parameters())
- out = linear(a)
- out.backward()
- optimizer.minimize(out)
- optimizer.clear_gradients()
current_step_lr
()
注意:
1. 该API只在 Dygraph 模式下生效
获取当前步骤的学习率。当不使用LearningRateDecay时,每次调用的返回值都相同,否则返回当前步骤的学习率。
返回:当前步骤的学习率。
返回类型:float
代码示例
- import paddle.fluid as fluid
- import numpy as np
- # example1: LearningRateDecay is not used, return value is all the same
- with fluid.dygraph.guard():
- emb = fluid.dygraph.Embedding([10, 10])
- adam = fluid.optimizer.Adam(0.001, parameter_list = emb.parameters())
- lr = adam.current_step_lr()
- print(lr) # 0.001
- # example2: PiecewiseDecay is used, return the step learning rate
- with fluid.dygraph.guard():
- inp = np.random.uniform(-0.1, 0.1, [10, 10]).astype("float32")
- linear = fluid.dygraph.nn.Linear(10, 10)
- inp = fluid.dygraph.to_variable(inp)
- out = linear(inp)
- loss = fluid.layers.reduce_mean(out)
- bd = [2, 4, 6, 8]
- value = [0.2, 0.4, 0.6, 0.8, 1.0]
- adam = fluid.optimizer.Adam(fluid.dygraph.PiecewiseDecay(bd, value, 0),
- parameter_list=linear.parameters())
- # first step: learning rate is 0.2
- np.allclose(adam.current_step_lr(), 0.2, rtol=1e-06, atol=0.0) # True
- # learning rate for different steps
- ret = [0.2, 0.2, 0.4, 0.4, 0.6, 0.6, 0.8, 0.8, 1.0, 1.0, 1.0, 1.0]
- for i in range(12):
- adam.minimize(loss)
- lr = adam.current_step_lr()
- np.allclose(lr, ret[i], rtol=1e-06, atol=0.0) # True