Работа с пакетом torch:
import torch
from torch.autograd import Variable
x_data = [1.0,2.0,3.0]
y_data = [2.0,4.0,6.0]
w = Variable(torch.Tensor([1.0]), requires_grad = True)
def forward(x):
return x*w
def loss(x,y):
y_pred = forward(x)
return (y_pred-y)*(y_pred-y)
print("my prediction before training",4,forward(4))
for epoch in range(10):
for x_val, y_val in zip(x_data,y_data):
l= loss(x_val, y_val)
l.backward()
print("\tgrad: ", x_val, y_val, w.grad.data[0])
w.data=w.data-0.01*w.grad.data
w.grad.data.zero_()
print("progress:", epoch, l.data[0] )
print("my new prediction after training ", forward(4))
Получена ошибка:
runfile('C:/gdrive/python/temp2.py', wdir='C:/gdrive/python')
Traceback (most recent call last):
File "C:\gdrive\python\temp2.py", line 11, in <module>
from torch.autograd import Variable
ModuleNotFoundError: No module named 'torch.autograd'
Команда conda list pytorch приносит:
# packages in environment at C:\Users\g\.conda\envs\test:
#
# Name Version Build Channel
(test) PS C:\gdrive\python>
Как исправить эту проблему?