[英]Problem computing partial derivatives with GradientTape() in TensorFlow2
i have problems in the computation of gradients using automatic differentiation in TensorFlow.我在使用 TensorFlow 中的自动微分计算梯度时遇到问题。 Basically i want to create a neural network which has just one output-value f and get an input of two values (x,t).基本上我想创建一个只有一个输出值 f 并获得两个值 (x,t) 的输入的神经网络。 The network should act like a mathematical function, so in this case f(x,t) where x and t are the input-variables and i want to compute partial derivatives, for example df_dx, d2f/dx2
or df_dt
.网络应该像数学 function 一样,所以在这种情况下 f(x,t) 其中 x 和 t 是输入变量,我想计算偏导数,例如df_dx, d2f/dx2
或df_dt
。 I need those partial derivatives later for a specific loss-function.我稍后需要这些偏导数来获得特定的损失函数。 Here is my simplified code:这是我的简化代码:
import numpy as np
import tensorflow as tf
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras import Model
class MyModel(Model):
def __init__(self):
super(MyModel, self).__init__()
self.flatten = Flatten(input_shape=(2, 1))
self.d1 = Dense(28)
self.f = Dense(1)
def call(self, y):
y = self.flatten(y)
y = self.d1(y)
y = self.f(y)
return y
if __name__ == "__main__":
#inp contains the input-variables (x,t)
inp = np.random.rand(1,2,1)
inp_tf = tf.convert_to_tensor(inp, np.float32)
#Create a Model
model = MyModel()
#Here comes the important part:
x = inp_tf[0][0]
t = inp_tf[0][1]
with tf.GradientTape(persistent=True) as tape:
tape.watch(inp_tf[0][0])
tape.watch(inp_tf)
f = model(inp_tf)
df_dx = tape.gradient(f, inp_tf[0][0]) #Derivative df_dx
grad_f = tape.gradient(f, inp_tf)
tf.print(f) #--> [[-0.0968768075]]
tf.print(df_dx) #--> None
tf.print(grad_f) #--> [[[0.284864038]
# [-0.243642956]]]
What i expected was that i get df_dx = [0.284864038]
(the first component of grad_f), but it results in None
.我所期望的是我得到df_dx = [0.284864038]
(grad_f 的第一个组件),但它导致None
。 My questions are:我的问题是:
None
?如果是:我必须在我的代码中更改计算 df_dx 不会导致None
? What i think could do is to modify the architecture of the class MyModel
that i use two different Inputlayer (one for x and one for t) so that i can call the model like f = model(x,t)
but that seems unnatural for me and i think there should be an easier way.我认为可以做的是修改class MyModel
的体系结构,我使用两个不同的 Inputlayer(一个用于 x,一个用于 t),以便我可以像f = model(x,t)
一样调用 model 但这似乎不自然我和我认为应该有一个更简单的方法。
Another point is that i don't get an Error when i change the input_shape of the Flattenlayer for example to self.flatten = Flatten(input_shape=(5,1)
but my inputvector has shape(1,2,1), so i expect to get an error but that's not the case, why? I'm grateful for your help:)另一点是,当我将 Flattenlayer 的 input_shape 更改为self.flatten = Flatten(input_shape=(5,1)
但我的 inputvector 具有 shape(1,2,1) 时,我没有收到错误,所以我期望得到一个错误,但事实并非如此,为什么?我很感激你的帮助:)
I use the following configurations:我使用以下配置:
Each time you do inp_tf[0][0]
or inp_tf[0][1]
you are creating a new tensor, but that new tensor is not used as input to your model, inp_tf
is.每次执行inp_tf[0][0]
或inp_tf[0][1]
时,您都在创建一个新张量,但该新张量不用作 model 的输入, inp_tf
是。 Even if inp_tf[0][0]
if part of inp_tf
, from the point of view of TensorFlow there is no computation graph between your newly created inp_tf[0][0]
and f
, hence there is no gradient.即使inp_tf[0][0]
是inp_tf
的一部分,从 TensorFlow 的角度来看,您新创建的inp_tf[0][0]
和f
之间也没有计算图,因此没有梯度。 You have to compute the gradient with respect to inp_tf
and then take the parts of the gradient that you want from there.你必须计算关于inp_tf
的梯度,然后从那里获取你想要的梯度部分。
In addition to that, as shown in the documentation of tf.GradientTape
, you can use nested tapes to compute second order derivatives.除此之外,如tf.GradientTape
的文档中所示,您可以使用嵌套磁带来计算二阶导数。 And, if you use the jacobian
, you can avoid using persistent=True
, which is better for performance.而且,如果您使用jacobian
,则可以避免使用persistent=True
,这对性能更好。 Here is how it could work in your example (I changed the layer activation functions to sigmoid
, as the default linear activation would not have a second order derivative).这是它在您的示例中的工作方式(我将层激活函数更改为sigmoid
,因为默认的线性激活没有二阶导数)。
import numpy as np
import tensorflow as tf
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras import Model
class MyModel(Model):
def __init__(self):
super(MyModel, self).__init__()
self.flatten = Flatten(input_shape=(2, 1))
self.d1 = Dense(28, activation='sigmoid')
self.f = Dense(1, activation='sigmoid')
def call(self, y):
y = self.flatten(y)
y = self.d1(y)
y = self.f(y)
return y
np.random.seed(0)
inp = np.random.rand(1, 2, 1)
inp_tf = tf.convert_to_tensor(inp, np.float32)
model = MyModel()
with tf.GradientTape() as tape:
tape.watch(inp_tf)
with tf.GradientTape() as tape2:
tape2.watch(inp_tf)
f = model(inp_tf)
grad_f = tape2.gradient(f, inp_tf)
df_dx = grad_f[0, 0]
df_dt = grad_f[0, 1]
j = tape.jacobian(grad_f, inp_tf)
d2f_dx2 = j[0, 0, :, 0, 0]
d2f_dyx = j[0, 0, :, 0, 1]
d2f_dy2 = j[0, 1, :, 0, 1]
d2f_dxy = j[0, 1, :, 0, 0]
tf.print(df_dx)
# [0.0104712956]
tf.print(df_dt)
# [-0.00301733566]
tf.print(d2f_dx2)
# [[-0.000243180315]]
tf.print(d2f_dyx)
# [[-0.000740956515]]
tf.print(d2f_dy2)
# [[1.49392872e-05]]
tf.print(d2f_dxy)
# [[-0.000740956573]]
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.