tensorflow求导和梯度计算

• 
  
  
  import
  tensorflow
  as
  tf
  
  
• 
  
  tf.enable_eager_execution()
  
  
• 
  
  tfe=tf.contrib.eager
  
  
• 
  
  
  from
  math
  import
  pi
  
  
• 
  
  def f(x):
  
  
• 
  
  
  return
  tf.square(tf.sin(x))
  
  
• 
  
  
  assert
  f(pi/
  2
  ).numpy()==
  1.0
  
  
  
• 
  
  sess=tf.Session()
  
  
• 
  
  grad_f=tfe.gradients_function(f)
  
  
• 
  
  print(grad_f(np.zeros(
  1
  ))[
  0
  ].numpy())
  
  
  

• 
  
  
  import
  numpy
  as
  np
  
  
• 
  
  def f(x):
  
  
• 
  
  
  return
  tf.square(tf.sin(x))
  
  
• 
  
  
  
  
• 
  
  def grad(f):
  
  
• 
  
  
  return
  lambda
  x:tfe.gradients_function(f)(x)[
  0
  ]
  
  
• 
  
  
  
  
• 
  
  x=tf.lin_space(
  -2
  *pi,
  2
  *pi,
  100
  )
  
  
• 
  
  
  # print(grad(f)(x).numpy())
  
  
  
• 
  
  x=x.numpy()
  
  
• 
  
  
  import
  matplotlib.pyplot
  as
  plt
  
  
• 
  
  plt.plot(x,f(x).numpy(),label=
  "f"
  )
  
  
• 
  
  plt.plot(x,grad(f)(x).numpy(),label=
  "first derivative"
  )
  #一阶导
  
  
  
• 
  
  plt.plot(x,grad(grad(f))(x).numpy(),label=
  "second derivative"
  )
  #二阶导
  
  
  
• 
  
  plt.plot(x,grad(grad(grad(f)))(x).numpy(),label=
  "third derivative"
  )
  #三阶导
  
  
  
• 
  
  plt.legend()
  
  
• 
  
  plt.show()
  
  
  

• 
  
  def f(x,y):
  
  
• 
  
  output=
  1
  
  
  
• 
  
  
  for
  i
  in
  range(int(y)):
  
  
• 
  
  output=tf.multiply(output,x)
  
  
• 
  
  
  return
  output
  
  
• 
  
  
  
  
• 
  
  def g(x,y):
  
  
• 
  
  
  return
  tfe.gradients_function(f)(x,y)[
  0
  ]
  
  
• 
  
  
  
  
• 
  
  print(f(
  3.0
  ,
  2
  ).numpy())
  #f(x)=x^2
  
  
  
• 
  
  print(g(
  3.0
  ,
  2
  ).numpy())
  #f'(x)=2*x
  
  
  
• 
  
  print(f(
  4.0
  ,
  3
  ).numpy())
  #f(x)=x^3
  
  
  
• 
  
  print(g(
  4.0
  ,
  3
  ).numpy())
  #f(x)=3x^2
  
  
  
  

• 
  
  x=tf.ones((
  2
  ,
  2
  ))
  
  
• 
  
  
  with
  tf.GradientTape(persistent=
  True
  )
  as
  t:
  
  
• 
  
  t.watch(x)
  
  
• 
  
  y=tf.reduce_sum(x)
  
  
• 
  
  z=tf.multiply(y,y)
  
  
• 
  
  
  
  
• 
  
  dz_dy=t.gradient(z,y)
  
  
• 
  
  print(dz_dy.numpy())
  
  
• 
  
  dz_dx=t.gradient(z,x)
  
  
• 
  
  print(dz_dx.numpy())
  
  
• 
  
  
  for
  i
  in
  [
  0
  ,
  1
  ]:
  
  
• 
  
  
  for
  j
  in
  [
  0
  ,
  1
  ]:
  
  
• 
  
  print(dz_dx[j].numpy() )
  
  
  

• 
  
  x=tf.constant(
  2.0
  )
  
  
• 
  
  
  with
  tf.GradientTape()
  as
  t:
  
  
• 
  
  
  with
  tf.GradientTape()
  as
  t2:
  
  
• 
  
  t2.watch(x)
  
  
• 
  
  y=x*x*x
  
  
• 
  
  dy_dx=t2.gradient(y,x)
  
  
• 
  
  d2y_dx2=t.gradient(dy_dx,x)
  
  
• 
  
  
  
  
• 
  
  print(dy_dx.numpy())
  
  
• 
  
  print(d2y_dx2.numpy())
  
  
  

更多免费技术资料可关注：annalin1203