NAdam¶
- class paddle.optimizer. NAdam ( learning_rate=0.002, beta1=0.9, beta2=0.999, epsilon=1.0e-8, momentum_decay=0.004, parameters=None, weight_decay=None, grad_clip=None, name=None ) [源代码] ¶
在论文 Incorporating Nesterov Momentum into Adam 中, NAdam 优化器的实现是基于 Adam 优化算法实现的。主要的改进是结合了 Nesterov 动量和 Adam 自适应学习率的优点。
其参数更新的计算公式如下:
参数¶
learning_rate (float|LRScheduler,可选) - 学习率,用于参数更新的计算。可以是一个浮点型值或者一个 LRScheduler 类。默认值为 0.002。
parameters (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。
beta1 (float,可选) - 一阶矩估计的指数衰减率,默认值为 0.9。
beta2 (float,可选) - 二阶矩估计的指数衰减率,默认值为 0.999。
epsilon (float,可选) - 保持数值稳定性的短浮点类型值,默认值为 1e-08。
weight_decay (float|Tensor,可选) - 正则化方法。可以是 float 类型或者 Tensor。默认值为 None,表示没有正则化。
momentum_decay (float,可选): 动量衰减率。默认值为 0.004.
grad_clip (GradientClipBase,可选) – 梯度裁剪的策略,支持三种裁剪策略:paddle.nn.ClipGradByGlobalNorm 、 paddle.nn.ClipGradByNorm 、 paddle.nn.ClipGradByValue 。默认值为 None,此时将不进行梯度裁剪。
name (str,可选) - 具体用法请参见 Name,一般无需设置,默认值为 None。
注解
目前 NAdam
不支持 Sparse Parameter Optimization(稀疏参数优化)。
代码示例¶
>>> import paddle
>>> inp = paddle.rand([10,10], dtype="float32")
>>> linear = paddle.nn.Linear(10, 10)
>>> out = linear(inp)
>>> loss = paddle.mean(out)
>>> nadam = paddle.optimizer.NAdam(learning_rate=0.1,
... parameters=linear.parameters())
>>> out.backward()
>>> nadam.step()
>>> nadam.clear_grad()
>>> # Note that the learning_rate of linear_2 is 0.01.
>>> linear_1 = paddle.nn.Linear(10, 10)
>>> linear_2 = paddle.nn.Linear(10, 10)
>>> inp = paddle.uniform(shape=[10, 10], min=-0.1, max=0.1)
>>> out = linear_1(inp)
>>> out = linear_2(out)
>>> loss = paddle.mean(out)
>>> opt = paddle.optimizer.NAdam(
... learning_rate=0.1,
... parameters=[{
... 'params': linear_1.parameters()
... }, {
... 'params': linear_2.parameters(),
... 'weight_decay': 0.001,
... 'learning_rate': 0.1,
... 'beta1': 0.8
... }],
... weight_decay=0.01,
... beta1=0.9
... )
>>> loss.backward()
>>> opt.step()
>>> opt.clear_grad()
方法¶
step()¶
该 API 只在 Dygraph 模式下生效。
执行一次优化器并进行参数更新。
返回
无。
代码示例
>>> import paddle
>>> a = paddle.arange(26, dtype="float32").reshape([2, 13])
>>> linear = paddle.nn.Linear(13, 5)
>>> # This can be any optimizer supported by dygraph.
>>> adam = paddle.optimizer.Adam(learning_rate = 0.01,
... parameters = linear.parameters())
>>> out = linear(a)
>>> out.backward()
>>> adam.step()
>>> adam.clear_grad()
minimize(loss, startup_program=None, parameters=None, no_grad_set=None)¶
为网络添加反向计算过程,并根据反向计算所得的梯度,更新 parameters 中的 Parameters,最小化网络损失值 loss。
参数
loss (Tensor) - 需要最小化的损失值变量。
startup_program (Program,可选) - 用于初始化 parameters 中参数的 Program,默认值为 None,此时将使用 default_startup_program。
parameters (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 组成集合,默认值为 None。
返回
tuple(optimize_ops, params_grads),其中 optimize_ops 为参数优化 OP 列表;param_grads 为由(param, param_grad)组成的列表,其中 param 和 param_grad 分别为参数和参数的梯度。在静态图模式下,该返回值可以加入到
Executor.run()
接口的fetch_list
参数中,若加入,则会重写use_prune
参数为 True,并根据feed
和fetch_list
进行剪枝,详见Executor
的文档。
代码示例
>>> import paddle
>>> linear = paddle.nn.Linear(10, 10)
>>> input = paddle.uniform(shape=[10, 10], min=-0.1, max=0.1)
>>> out = linear(input)
>>> loss = paddle.mean(out)
>>> beta1 = paddle.to_tensor([0.9], dtype="float32")
>>> beta2 = paddle.to_tensor([0.99], dtype="float32")
>>> adam = paddle.optimizer.Adam(learning_rate=0.1,
... parameters=linear.parameters(),
... weight_decay=0.01)
>>> loss.backward()
>>> adam.minimize(loss)
>>> adam.clear_grad()
clear_grad()¶
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
>>> a = paddle.arange(26, dtype="float32").reshape([2, 13])
>>> linear = paddle.nn.Linear(13, 5)
>>> # This can be any optimizer supported by dygraph.
>>> adam = paddle.optimizer.Adam(learning_rate = 0.01,
... parameters = linear.parameters())
>>> out = linear(a)
>>> out.backward()
>>> adam.step()
>>> adam.clear_grad()
set_lr(value)¶
该 API 只在 Dygraph 模式下生效。
手动设置当前 optimizer
的学习率。当使用_LRScheduler 时,无法使用该 API 手动设置学习率,因为这将导致冲突。
参数
value (float) - 需要设置的学习率的值。
返回
无。
代码示例
>>> import paddle
>>> linear = paddle.nn.Linear(10, 10)
>>> adam = paddle.optimizer.Adam(0.1, parameters=linear.parameters())
>>> # set learning rate manually by python float value
>>> lr_list = [0.2, 0.3, 0.4, 0.5, 0.6]
>>> for i in range(5):
... adam.set_lr(lr_list[i])
... lr = adam.get_lr()
... print("current lr is {}".format(lr))
current lr is 0.2
current lr is 0.3
current lr is 0.4
current lr is 0.5
current lr is 0.6
set_lr_scheduler(scheduler)¶
该 API 只在 Dygraph 模式下生效。
手动设置当前 optimizer
的学习率为 LRScheduler 类。
参数
scheduler (LRScheduler) - 需要设置的学习率的 LRScheduler 类。
返回
无。
代码示例
>>> import paddle
>>> linear = paddle.nn.Linear(10, 10)
>>> adam = paddle.optimizer.Adam(0.1, parameters=linear.parameters())
>>> # set learning rate manually by class LRScheduler
>>> scheduler = paddle.optimizer.lr.MultiStepDecay(learning_rate=0.5, milestones=[2,4,6], gamma=0.8)
>>> adam.set_lr_scheduler(scheduler)
>>> lr = adam.get_lr()
>>> print("current lr is {}".format(lr))
current lr is 0.5
>>> # set learning rate manually by another LRScheduler
>>> scheduler = paddle.optimizer.lr.StepDecay(learning_rate=0.1, step_size=5, gamma=0.6)
>>> adam.set_lr_scheduler(scheduler)
>>> lr = adam.get_lr()
>>> print("current lr is {}".format(lr))
current lr is 0.1
get_lr()¶
该 API 只在 Dygraph 模式下生效。
获取当前步骤的学习率。当不使用_LRScheduler 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
float,当前步骤的学习率。
代码示例
>>> # train on default dynamic graph mode
>>> import paddle
>>> import numpy as np
>>> emb = paddle.nn.Embedding(10, 3)
>>> ## example1: LRScheduler is not used, return the same value is all the same
>>> adam = paddle.optimizer.Adam(0.01, parameters = emb.parameters())
>>> for batch in range(10):
... input = paddle.randint(low=0, high=5, shape=[5])
... out = emb(input)
... out.backward()
... print("Learning rate of step{}: {}".format(batch, adam.get_lr())) # 0.01
... adam.step()
Learning rate of step0: 0.01
Learning rate of step1: 0.01
Learning rate of step2: 0.01
Learning rate of step3: 0.01
Learning rate of step4: 0.01
Learning rate of step5: 0.01
Learning rate of step6: 0.01
Learning rate of step7: 0.01
Learning rate of step8: 0.01
Learning rate of step9: 0.01
>>> ## example2: StepDecay is used, return the scheduled learning rate
>>> scheduler = paddle.optimizer.lr.StepDecay(learning_rate=0.5, step_size=2, gamma=0.1)
>>> adam = paddle.optimizer.Adam(scheduler, parameters = emb.parameters())
>>> for batch in range(10):
... input = paddle.randint(low=0, high=5, shape=[5])
... out = emb(input)
... out.backward()
... print("Learning rate of step{}: {}".format(batch, adam.get_lr())) # 0.5->0.05...
... adam.step()
... scheduler.step()
Learning rate of step0: 0.5
Learning rate of step1: 0.5
Learning rate of step2: 0.05
Learning rate of step3: 0.05
Learning rate of step4: 0.005000000000000001
Learning rate of step5: 0.005000000000000001
Learning rate of step6: 0.0005000000000000001
Learning rate of step7: 0.0005000000000000001
Learning rate of step8: 5.000000000000001e-05
Learning rate of step9: 5.000000000000001e-05
>>> # train on static graph mode
>>> paddle.enable_static()
>>> main_prog = paddle.static.Program()
>>> start_prog = paddle.static.Program()
>>> with paddle.static.program_guard(main_prog, start_prog):
... x = paddle.static.data(name='x', shape=[None, 10])
... z = paddle.static.nn.fc(x, 100)
... loss = paddle.mean(z)
... scheduler = paddle.optimizer.lr.StepDecay(learning_rate=0.5, step_size=2, gamma=0.1)
... adam = paddle.optimizer.Adam(learning_rate=scheduler)
... adam.minimize(loss)
>>> exe = paddle.static.Executor()
>>> exe.run(start_prog)
>>> for batch in range(10):
... print("Learning rate of step{}: {}".format(batch, adam.get_lr())) # 0.5->0.05->0.005...
... out = exe.run(main_prog, feed={'x': np.random.randn(3, 10).astype('float32')})
... scheduler.step()
Learning rate of step0: 0.5
Learning rate of step1: 0.5
Learning rate of step2: 0.05
Learning rate of step3: 0.05
Learning rate of step4: 0.005000000000000001
Learning rate of step5: 0.005000000000000001
Learning rate of step6: 0.0005000000000000001
Learning rate of step7: 0.0005000000000000001
Learning rate of step8: 5.000000000000001e-05
Learning rate of step9: 5.000000000000001e-05