Reputation: 9
so this is my code
import torch.nn.functional as F
import torch
inputs = [1,2,3]
input = torch.tensor(inputs)
output = F.softmax(input, dim=1)
print(output)
is the reason why the code not working because of the dim? the error here:
File "c:\Users\user\Desktop\AI\pytorch_jovian\linear_reg.py", line 19, in <module>
output = F.softmax(input, dim=1)
File "C:\Users\user\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\nn\functional.py", line 1583, in softmax
ret = input.softmax(dim)
IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)
Upvotes: 0
Views: 4032
Reputation: 17219
Apart from dim=0
, there is another issue in your code. Softmax
doesn't work on a long tensor
, so it should be converted to a float
or double
tensor first
>>> input = torch.tensor([1, 2, 3])
>>> input
tensor([1, 2, 3])
>>> F.softmax(input.float(), dim=0)
tensor([0.0900, 0.2447, 0.6652])
Upvotes: 1