erf

逐元素计算 Erf 激活函数。更多细节请参考 Error function

erf - 图1

  • 参数:
    • x (Variable) - Erf Op 的输入,多维 Tensor 或 LoDTensor,数据类型为 float16, float32 或 float64。
  • 返回:
    • 多维 Tensor 或 LoDTensor, 数据类型为 float16, float32 或 float64, 和输入 x 的数据类型相同,形状和输入 x 相同。
  • 返回类型:
    • Variable

代码示例

  1. # declarative mode
  2. import numpy as np
  3. from paddle import fluid
  4.  
  5. x = fluid.data(name="x", shape=(-1, 3), dtype="float32")
  6. y = fluid.layers.erf(x)
  7.  
  8. place = fluid.CPUPlace()
  9. exe = fluid.Executor(place)
  10. start = fluid.default_startup_program()
  11. main = fluid.default_main_program()
  12.  
  13. data = np.random.randn(2, 3).astype("float32")
  14. exe.run(start)
  15.  
  16. y_np, = exe.run(main, feed={"x": data}, fetch_list=[y])
  17.  
  18. data
  19. # array([[ 0.4643714 , -1.1509596 , 1.2538221 ],
  20. # [ 0.34369683, 0.27478245, 1.1805398 ]], dtype=float32)
  21. y_np
  22. # array([[ 0.48863927, -0.8964121 , 0.9237998 ],
  23. # [ 0.37307587, 0.30242872, 0.9049887 ]], dtype=float32)
  1. # imperative mode
  2. import numpy as np
  3. from paddle import fluid
  4. import paddle.fluid.dygraph as dg
  5.  
  6. data = np.random.randn(2, 3).astype("float32")
  7. place = fluid.CPUPlace()
  8. with dg.guard(place) as g:
  9. x = dg.to_variable(data)
  10. y = fluid.layers.erf(x)
  11. y_np = y.numpy()
  12. data
  13. # array([[ 0.4643714 , -1.1509596 , 1.2538221 ],
  14. # [ 0.34369683, 0.27478245, 1.1805398 ]], dtype=float32)
  15. y_np
  16. # array([[ 0.48863927, -0.8964121 , 0.9237998 ],
  17. # [ 0.37307587, 0.30242872, 0.9049887 ]], dtype=float32)