不能在需要 grad 的张量上调用 numpy()。改用 tensor.detach().numpy()

Question

这是我对这个问题的第二个问题。最初，我有AttributeError错误:'numpy。narray ' object没有属性'log'。然后U12-Forward帮我解决了这个问题。但是一个新的问题出现了。

import torch
import numpy as np
import matplotlib.pyplot as plt
x = torch.tensor([[5., 10.],
[1., 2.]], requires_grad=True)
var_history = []
fn_history = []
alpha = 0.001
optimizer = torch.optim.SGD([x], lr=alpha)
def function_parabola(variable):
return np.prod(np.log(np.log(variable + 7)))

def make_gradient_step(function, variable):
function_result = function(variable)
function_result.backward()
optimizer.step()
optimizer.zero_grad()

for i in range(500):
var_history.append(x.data.numpy().copy())
fn_history.append(function_parabola(x).data.cpu().detach().numpy().copy())
make_gradient_step(function_parabola, x)
print(x)
def show_contours(objective,
x_lims=[-10.0, 10.0],
y_lims=[-10.0, 10.0],
x_ticks=100,
y_ticks=100):
x_step = (x_lims[1] - x_lims[0]) / x_ticks
y_step = (y_lims[1] - y_lims[0]) / y_ticks
X, Y = np.mgrid[x_lims[0]:x_lims[1]:x_step, y_lims[0]:y_lims[1]:y_step]
res = []
for x_index in range(X.shape[0]):
res.append([])
for y_index in range(X.shape[1]):
x_val = X[x_index, y_index]
y_val = Y[x_index, y_index]
res[-1].append(objective(np.array([[x_val, y_val]]).T))
res = np.array(res)
plt.figure(figsize=(7,7))
plt.contour(X, Y, res, 100)
plt.xlabel('$x_1$')
plt.ylabel('$x_2$')
show_contours(function_parabola)
plt.scatter(np.array(var_history)[:,0], np.array(var_history)[:,1], s=10, c='r');
plt.show()

Answer 1

修改function_抛物线()来操作PyTorch张量，并利用PyTorch等效的原始numpy操作，如下所示:

import torch
import numpy as np
import matplotlib.pyplot as plt
x = torch.tensor([[5., 10.],
[1., 2.]], requires_grad=True)
var_history = []
fn_history = []
alpha = 0.001
optimizer = torch.optim.SGD([x], lr=alpha)
def function_parabola(variable):
return (torch.prod(torch.log(torch.log(torch.as_tensor(variable + 7)))))

def make_gradient_step(function, variable):
function_result = function(variable)
function_result.backward()
optimizer.step()
optimizer.zero_grad()

for i in range(500):
var_history.append(x.data.numpy().copy())
fn_history.append(function_parabola(x).data.cpu().detach().numpy())
make_gradient_step(function_parabola, x)
print(x)
def show_contours(objective,
x_lims=[-10.0, 10.0],
y_lims=[-10.0, 10.0],
x_ticks=100,
y_ticks=100):
x_step = (x_lims[1] - x_lims[0]) / x_ticks
y_step = (y_lims[1] - y_lims[0]) / y_ticks
X, Y = np.mgrid[x_lims[0]:x_lims[1]:x_step, y_lims[0]:y_lims[1]:y_step]
res = []
for x_index in range(X.shape[0]):
res.append([])
for y_index in range(X.shape[1]):
x_val = X[x_index, y_index]
y_val = Y[x_index, y_index]
res[-1].append(objective(np.array([[x_val, y_val]]).T))
res = np.array(res)
plt.figure(figsize=(7,7))
plt.contour(X, Y, res, 100)
plt.xlabel('$x_1$')
plt.ylabel('$x_2$')
show_contours(function_parabola)
plt.scatter(np.array(var_history)[:,0], np.array(var_history)[:,1], s=10, c='r');
plt.show()