使用矩阵 运行 的计算雅可比行列式的自动求导出错
Using autograd of compute Jacobian of a matrix ran into error
有人能告诉我为什么以下计算核矩阵雅可比的代码不起作用吗:
import autograd.numpy as np
# import numpy as np
from autograd import grad
from autograd import jacobian
from numpy import linalg as LA
def kernel(x1,x2,l):
return np.exp(-((x1-x2)**2).sum()/(2*(l**2)))
def kernel_matrixx(top_k_history):
k_t_X_list = []
for i in range(k-1):
# print(kernel(top_k_history[i],observation,l))
k_t_X_list.append(np.expand_dims(np.expand_dims((kernel(top_k_history[0],top_k_history[i+1],l)), axis=0), axis=0))
# print(k_t_X_list[0].item())
# k_t_X = np.expand_dims(np.asarray(k_t_X_list), axis=0)
k_t_X = np.expand_dims(np.expand_dims((kernel(top_k_history[0],top_k_history[0],l)), axis=0), axis=0)
for i in range(k-1):
# temp = np.expand_dims(np.expand_dims(np.asarray(kernel(observation,top_k_history[i+1],l)), axis=0), axis=0)
k_t_X = np.concatenate([k_t_X, k_t_X_list[i]], axis=1)
k_t_X_first = k_t_X
k_t_X_list_list = []
for j in range(k-1):
k_t_X_list = []
for i in range(k-1):
# print(kernel(top_k_history[i],observation,l))
k_t_X_list.append(np.expand_dims(np.expand_dims((kernel(top_k_history[j+1],top_k_history[i+1],l)), axis=0), axis=0))
# print(k_t_X_list[0].item())
# k_t_X = np.expand_dims(np.asarray(k_t_X_list), axis=0)
k_t_X = np.expand_dims(np.expand_dims((kernel(top_k_history[j+1],top_k_history[0],l)), axis=0), axis=0)
for i in range(k-1):
# temp = np.expand_dims(np.expand_dims(np.asarray(kernel(observation,top_k_history[i+1],l)), axis=0), axis=0)
k_t_X = np.concatenate([k_t_X, k_t_X_list[i]], axis=1)
k_t_X_list_list.append(k_t_X)
for i in range(k-1):
k_t_X_first = np.concatenate([k_t_X_first, k_t_X_list_list[i]], axis=0)
return k_t_X_first
k=10
l=19
top_k_history = []
for i in range(10):
top_k_history.append(np.random.rand(10))
jac = jacobian(kernel_matrixx)
jac(top_k_history)
我得到的错误是:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_15016/2419460232.py in <module>
1 jac = jacobian(kernel_matrixx)
----> 2 jac(top_k_history)
~\Anaconda3\envs\unlearning\lib\site-packages\autograd\wrap_util.py in nary_f(*args, **kwargs)
18 else:
19 x = tuple(args[i] for i in argnum)
---> 20 return unary_operator(unary_f, x, *nary_op_args, **nary_op_kwargs)
21 return nary_f
22 return nary_operator
~\Anaconda3\envs\unlearning\lib\site-packages\autograd\differential_operators.py in jacobian(fun, x)
57 vjp, ans = _make_vjp(fun, x)
58 ans_vspace = vspace(ans)
---> 59 jacobian_shape = ans_vspace.shape + vspace(x).shape
60 grads = map(vjp, ans_vspace.standard_basis())
61 return np.reshape(np.stack(grads), jacobian_shape)
TypeError: can only concatenate tuple (not "list") to tuple
我已经知道我无法创建一个零矩阵(或单位矩阵)然后用嵌套的 for 循环填充值。因此我创建 np.array 然后连接它们。我使用相同的方法来计算同一内核矩阵的其他一些输出的梯度,它确实有效,所以我不确定为什么它对雅可比矩阵不起作用。
编辑:错误现在应该可以重现
存在数据类型问题。我的代码 top_k_history
的类型为 list
,包含 10 个一维数组,每个长度为 10。如果将其转换为形状为 (10, 10)
的 1 个二维数组,则错误应该消失:
# <original code except the last line>
top_k_history = np.array(top_k_history) # new
jac(top_k_history) # original last line
有人能告诉我为什么以下计算核矩阵雅可比的代码不起作用吗:
import autograd.numpy as np
# import numpy as np
from autograd import grad
from autograd import jacobian
from numpy import linalg as LA
def kernel(x1,x2,l):
return np.exp(-((x1-x2)**2).sum()/(2*(l**2)))
def kernel_matrixx(top_k_history):
k_t_X_list = []
for i in range(k-1):
# print(kernel(top_k_history[i],observation,l))
k_t_X_list.append(np.expand_dims(np.expand_dims((kernel(top_k_history[0],top_k_history[i+1],l)), axis=0), axis=0))
# print(k_t_X_list[0].item())
# k_t_X = np.expand_dims(np.asarray(k_t_X_list), axis=0)
k_t_X = np.expand_dims(np.expand_dims((kernel(top_k_history[0],top_k_history[0],l)), axis=0), axis=0)
for i in range(k-1):
# temp = np.expand_dims(np.expand_dims(np.asarray(kernel(observation,top_k_history[i+1],l)), axis=0), axis=0)
k_t_X = np.concatenate([k_t_X, k_t_X_list[i]], axis=1)
k_t_X_first = k_t_X
k_t_X_list_list = []
for j in range(k-1):
k_t_X_list = []
for i in range(k-1):
# print(kernel(top_k_history[i],observation,l))
k_t_X_list.append(np.expand_dims(np.expand_dims((kernel(top_k_history[j+1],top_k_history[i+1],l)), axis=0), axis=0))
# print(k_t_X_list[0].item())
# k_t_X = np.expand_dims(np.asarray(k_t_X_list), axis=0)
k_t_X = np.expand_dims(np.expand_dims((kernel(top_k_history[j+1],top_k_history[0],l)), axis=0), axis=0)
for i in range(k-1):
# temp = np.expand_dims(np.expand_dims(np.asarray(kernel(observation,top_k_history[i+1],l)), axis=0), axis=0)
k_t_X = np.concatenate([k_t_X, k_t_X_list[i]], axis=1)
k_t_X_list_list.append(k_t_X)
for i in range(k-1):
k_t_X_first = np.concatenate([k_t_X_first, k_t_X_list_list[i]], axis=0)
return k_t_X_first
k=10
l=19
top_k_history = []
for i in range(10):
top_k_history.append(np.random.rand(10))
jac = jacobian(kernel_matrixx)
jac(top_k_history)
我得到的错误是:
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_15016/2419460232.py in <module>
1 jac = jacobian(kernel_matrixx)
----> 2 jac(top_k_history)
~\Anaconda3\envs\unlearning\lib\site-packages\autograd\wrap_util.py in nary_f(*args, **kwargs)
18 else:
19 x = tuple(args[i] for i in argnum)
---> 20 return unary_operator(unary_f, x, *nary_op_args, **nary_op_kwargs)
21 return nary_f
22 return nary_operator
~\Anaconda3\envs\unlearning\lib\site-packages\autograd\differential_operators.py in jacobian(fun, x)
57 vjp, ans = _make_vjp(fun, x)
58 ans_vspace = vspace(ans)
---> 59 jacobian_shape = ans_vspace.shape + vspace(x).shape
60 grads = map(vjp, ans_vspace.standard_basis())
61 return np.reshape(np.stack(grads), jacobian_shape)
TypeError: can only concatenate tuple (not "list") to tuple
我已经知道我无法创建一个零矩阵(或单位矩阵)然后用嵌套的 for 循环填充值。因此我创建 np.array 然后连接它们。我使用相同的方法来计算同一内核矩阵的其他一些输出的梯度,它确实有效,所以我不确定为什么它对雅可比矩阵不起作用。
编辑:错误现在应该可以重现
存在数据类型问题。我的代码 top_k_history
的类型为 list
,包含 10 个一维数组,每个长度为 10。如果将其转换为形状为 (10, 10)
的 1 个二维数组,则错误应该消失:
# <original code except the last line>
top_k_history = np.array(top_k_history) # new
jac(top_k_history) # original last line