PyTorch - multiplying tensor with scalar results in zero vector
I have no idea why the result is all 0 with tensor. Anything wrong here?
>>> import torch
>>> import numpy as np
>>> import math
>>> torch.__version__
'0.4.1'
>>> np.__version__
'1.15.4'
>>> torch.arange(0, 10, 2) *-(math.log(10000.0) / 10)
tensor([0, 0, 0, 0, 0])
>>> np.arange(0, 10, 2) *-(math.log(10000.0) / 10)
array([-0. , -1.84206807, -3.68413615, -5.52620422, -7.3682723 ])
>>> torch.arange(0, 10, 2)
tensor([0, 2, 4, 6, 8])
>>> np.arange(0, 10, 2)
array([0, 2, 4, 6, 8])
python numpy pytorch
edited Nov 25 '18 at 20:43
blue-phoenox
4,395101748
asked Nov 25 '18 at 11:33
KuoKuo
287
add a comment |
I have no idea why the result is all 0 with tensor. Anything wrong here?
>>> import torch
>>> import numpy as np
>>> import math
>>> torch.__version__
'0.4.1'
>>> np.__version__
'1.15.4'
>>> torch.arange(0, 10, 2) *-(math.log(10000.0) / 10)
tensor([0, 0, 0, 0, 0])
>>> np.arange(0, 10, 2) *-(math.log(10000.0) / 10)
array([-0. , -1.84206807, -3.68413615, -5.52620422, -7.3682723 ])
>>> torch.arange(0, 10, 2)
tensor([0, 2, 4, 6, 8])
>>> np.arange(0, 10, 2)
array([0, 2, 4, 6, 8])
python numpy pytorch
edited Nov 25 '18 at 20:43
blue-phoenox
4,395101748
asked Nov 25 '18 at 11:33
KuoKuo
287
Results intensor([-0.0000, -1.8421, -3.6841, -5.5262, -7.3683])for me, v0.4.0a0+3749c58
– blue-phoenox
Nov 25 '18 at 11:46
Python version 3.7.1
– Kuo
Nov 25 '18 at 11:54
add a comment |
I have no idea why the result is all 0 with tensor. Anything wrong here?
>>> import torch
>>> import numpy as np
>>> import math
>>> torch.__version__
'0.4.1'
>>> np.__version__
'1.15.4'
>>> torch.arange(0, 10, 2) *-(math.log(10000.0) / 10)
tensor([0, 0, 0, 0, 0])
>>> np.arange(0, 10, 2) *-(math.log(10000.0) / 10)
array([-0. , -1.84206807, -3.68413615, -5.52620422, -7.3682723 ])
>>> torch.arange(0, 10, 2)
tensor([0, 2, 4, 6, 8])
>>> np.arange(0, 10, 2)
array([0, 2, 4, 6, 8])
python numpy pytorch
edited Nov 25 '18 at 20:43
blue-phoenox
4,395101748
asked Nov 25 '18 at 11:33
KuoKuo
287
I have no idea why the result is all 0 with tensor. Anything wrong here?
>>> import torch
>>> import numpy as np
>>> import math
>>> torch.__version__
'0.4.1'
>>> np.__version__
'1.15.4'
>>> torch.arange(0, 10, 2) *-(math.log(10000.0) / 10)
tensor([0, 0, 0, 0, 0])
>>> np.arange(0, 10, 2) *-(math.log(10000.0) / 10)
array([-0. , -1.84206807, -3.68413615, -5.52620422, -7.3682723 ])
>>> torch.arange(0, 10, 2)
tensor([0, 2, 4, 6, 8])
>>> np.arange(0, 10, 2)
array([0, 2, 4, 6, 8])
python numpy pytorch
python numpy pytorch
edited Nov 25 '18 at 20:43
blue-phoenox
4,395101748
asked Nov 25 '18 at 11:33
KuoKuo
287
edited Nov 25 '18 at 20:43
blue-phoenox
4,395101748
asked Nov 25 '18 at 11:33
KuoKuo
287
edited Nov 25 '18 at 20:43
blue-phoenox
4,395101748
edited Nov 25 '18 at 20:43
blue-phoenox
4,395101748
edited Nov 25 '18 at 20:43
blue-phoenox
4,395101748
4,395101748
asked Nov 25 '18 at 11:33
KuoKuo
287
asked Nov 25 '18 at 11:33
KuoKuo
287
asked Nov 25 '18 at 11:33
KuoKuo
287
287
Results intensor([-0.0000, -1.8421, -3.6841, -5.5262, -7.3683])for me, v0.4.0a0+3749c58
– blue-phoenox
Nov 25 '18 at 11:46
Python version 3.7.1
– Kuo
Nov 25 '18 at 11:54
add a comment |
Results intensor([-0.0000, -1.8421, -3.6841, -5.5262, -7.3683])for me, v0.4.0a0+3749c58
– blue-phoenox
Nov 25 '18 at 11:46
Python version 3.7.1
– Kuo
Nov 25 '18 at 11:54
Results in
tensor([-0.0000, -1.8421, -3.6841, -5.5262, -7.3683]) for me, v0.4.0a0+3749c58– blue-phoenox
Nov 25 '18 at 11:46
Results in
tensor([-0.0000, -1.8421, -3.6841, -5.5262, -7.3683]) for me, v0.4.0a0+3749c58– blue-phoenox
Nov 25 '18 at 11:46
Python version 3.7.1
– Kuo
Nov 25 '18 at 11:54
Python version 3.7.1
– Kuo
Nov 25 '18 at 11:54
add a comment |
1 Answer
1
active
oldest
votes
As written in the comment when using 0.4.0 get the same results as with numpy:
tensor([-0.0000, -1.8421, -3.6841, -5.5262, -7.3683])
However with 0.4.1 I'm getting a zero vector too.
The reason for this is that torch.arange(0, 10, 2) returns a tensor of type float for 0.4.0 while it returns a tensor of type long for 0.4.1.
So casting your tensor to float should work for you:
torch.arange(0, 10, 2).float() *-(math.log(10000.0) / 10)
Multiplying long and float works by heavy rounding, as the result is still a tensor of type long. So when converting a FloatTensor to a LongTensor values between -1 and 1 will be rounded to 0.
Since -(math.log(10000.0) / 10) results in -0.9210340371976183 your result is 0. So effectively -0.9210340371976183 is converted to type long before multiplying. But when converting it will be round down to 0, see this example:
t = torch.tensor((-(math.log(10000.0) / 10)))
print('FloatTensor:', t)
print('Converted to Long:', t.long())
Outout:
FloatTensor: tensor(-0.9210)
Converted to Long: tensor(0)
Thus:
torch.arange(0, 10, 2).float() *-(math.log(10000.0) / 10)
becomes:
torch.arange(0, 10, 2).float() * 0
Therefore you get a tensor of zeros as result.
Some more examples:
If you multiply it with a value between 1 and 2, lets say 1.7, it will always been rounded down to 1:
t = torch.tensor(range(5), dtype=torch.long)
print(t)
print(t * 1.7)
Output:
tensor([ 0, 1, 2, 3, 4])
tensor([ 0, 1, 2, 3, 4])
And similarly when multiplying with 2.7 results in an effective multiplication of 2:
t = torch.tensor(range(5), dtype=torch.long)
print(t)
print(t * 2.7)
Output:
tensor([ 0, 1, 2, 3, 4])
tensor([ 0, 2, 4, 6, 8])
answered Nov 25 '18 at 11:54
blue-phoenoxblue-phoenox
4,395101748
Yes. Can you elaborate a bit more on why is that? Without .float(), I add/minus 1,2... to (math.log(10000.0) / 10) and will get something like tensor([ 0, -2, -4, -6, -8]), tensor([0, 0, 0, 0, 0]), tensor([0, 2, 4, 6, 8])...
– Kuo
Nov 25 '18 at 12:08
@Kuo Thanks, I added some more examples to make the behaviour of multiplicationlong*floatmore clear!
– blue-phoenox
Nov 25 '18 at 12:19
add a comment |
Your Answer
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53467011%2fpytorch-multiplying-tensor-with-scalar-results-in-zero-vector%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
As written in the comment when using 0.4.0 get the same results as with numpy:
tensor([-0.0000, -1.8421, -3.6841, -5.5262, -7.3683])
However with 0.4.1 I'm getting a zero vector too.
The reason for this is that torch.arange(0, 10, 2) returns a tensor of type float for 0.4.0 while it returns a tensor of type long for 0.4.1.
So casting your tensor to float should work for you:
torch.arange(0, 10, 2).float() *-(math.log(10000.0) / 10)
Multiplying long and float works by heavy rounding, as the result is still a tensor of type long. So when converting a FloatTensor to a LongTensor values between -1 and 1 will be rounded to 0.
Since -(math.log(10000.0) / 10) results in -0.9210340371976183 your result is 0. So effectively -0.9210340371976183 is converted to type long before multiplying. But when converting it will be round down to 0, see this example:
t = torch.tensor((-(math.log(10000.0) / 10)))
print('FloatTensor:', t)
print('Converted to Long:', t.long())
Outout:
FloatTensor: tensor(-0.9210)
Converted to Long: tensor(0)
Thus:
torch.arange(0, 10, 2).float() *-(math.log(10000.0) / 10)
becomes:
torch.arange(0, 10, 2).float() * 0
Therefore you get a tensor of zeros as result.
Some more examples:
If you multiply it with a value between 1 and 2, lets say 1.7, it will always been rounded down to 1:
t = torch.tensor(range(5), dtype=torch.long)
print(t)
print(t * 1.7)
Output:
tensor([ 0, 1, 2, 3, 4])
tensor([ 0, 1, 2, 3, 4])
And similarly when multiplying with 2.7 results in an effective multiplication of 2:
t = torch.tensor(range(5), dtype=torch.long)
print(t)
print(t * 2.7)
Output:
tensor([ 0, 1, 2, 3, 4])
tensor([ 0, 2, 4, 6, 8])
answered Nov 25 '18 at 11:54
blue-phoenoxblue-phoenox
4,395101748
Yes. Can you elaborate a bit more on why is that? Without .float(), I add/minus 1,2... to (math.log(10000.0) / 10) and will get something like tensor([ 0, -2, -4, -6, -8]), tensor([0, 0, 0, 0, 0]), tensor([0, 2, 4, 6, 8])...
– Kuo
Nov 25 '18 at 12:08
@Kuo Thanks, I added some more examples to make the behaviour of multiplicationlong*floatmore clear!
– blue-phoenox
Nov 25 '18 at 12:19
add a comment |
As written in the comment when using 0.4.0 get the same results as with numpy:
tensor([-0.0000, -1.8421, -3.6841, -5.5262, -7.3683])
However with 0.4.1 I'm getting a zero vector too.
The reason for this is that torch.arange(0, 10, 2) returns a tensor of type float for 0.4.0 while it returns a tensor of type long for 0.4.1.
So casting your tensor to float should work for you:
torch.arange(0, 10, 2).float() *-(math.log(10000.0) / 10)
Multiplying long and float works by heavy rounding, as the result is still a tensor of type long. So when converting a FloatTensor to a LongTensor values between -1 and 1 will be rounded to 0.
Since -(math.log(10000.0) / 10) results in -0.9210340371976183 your result is 0. So effectively -0.9210340371976183 is converted to type long before multiplying. But when converting it will be round down to 0, see this example:
t = torch.tensor((-(math.log(10000.0) / 10)))
print('FloatTensor:', t)
print('Converted to Long:', t.long())
Outout:
FloatTensor: tensor(-0.9210)
Converted to Long: tensor(0)
Thus:
torch.arange(0, 10, 2).float() *-(math.log(10000.0) / 10)
becomes:
torch.arange(0, 10, 2).float() * 0
Therefore you get a tensor of zeros as result.
Some more examples:
If you multiply it with a value between 1 and 2, lets say 1.7, it will always been rounded down to 1:
t = torch.tensor(range(5), dtype=torch.long)
print(t)
print(t * 1.7)
Output:
tensor([ 0, 1, 2, 3, 4])
tensor([ 0, 1, 2, 3, 4])
And similarly when multiplying with 2.7 results in an effective multiplication of 2:
t = torch.tensor(range(5), dtype=torch.long)
print(t)
print(t * 2.7)
Output:
tensor([ 0, 1, 2, 3, 4])
tensor([ 0, 2, 4, 6, 8])
answered Nov 25 '18 at 11:54
blue-phoenoxblue-phoenox
4,395101748
Yes. Can you elaborate a bit more on why is that? Without .float(), I add/minus 1,2... to (math.log(10000.0) / 10) and will get something like tensor([ 0, -2, -4, -6, -8]), tensor([0, 0, 0, 0, 0]), tensor([0, 2, 4, 6, 8])...
– Kuo
Nov 25 '18 at 12:08
@Kuo Thanks, I added some more examples to make the behaviour of multiplicationlong*floatmore clear!
– blue-phoenox
Nov 25 '18 at 12:19
add a comment |
As written in the comment when using 0.4.0 get the same results as with numpy:
tensor([-0.0000, -1.8421, -3.6841, -5.5262, -7.3683])
However with 0.4.1 I'm getting a zero vector too.
The reason for this is that torch.arange(0, 10, 2) returns a tensor of type float for 0.4.0 while it returns a tensor of type long for 0.4.1.
So casting your tensor to float should work for you:
torch.arange(0, 10, 2).float() *-(math.log(10000.0) / 10)
Multiplying long and float works by heavy rounding, as the result is still a tensor of type long. So when converting a FloatTensor to a LongTensor values between -1 and 1 will be rounded to 0.
Since -(math.log(10000.0) / 10) results in -0.9210340371976183 your result is 0. So effectively -0.9210340371976183 is converted to type long before multiplying. But when converting it will be round down to 0, see this example:
t = torch.tensor((-(math.log(10000.0) / 10)))
print('FloatTensor:', t)
print('Converted to Long:', t.long())
Outout:
FloatTensor: tensor(-0.9210)
Converted to Long: tensor(0)
Thus:
torch.arange(0, 10, 2).float() *-(math.log(10000.0) / 10)
becomes:
torch.arange(0, 10, 2).float() * 0
Therefore you get a tensor of zeros as result.
Some more examples:
If you multiply it with a value between 1 and 2, lets say 1.7, it will always been rounded down to 1:
t = torch.tensor(range(5), dtype=torch.long)
print(t)
print(t * 1.7)
Output:
tensor([ 0, 1, 2, 3, 4])
tensor([ 0, 1, 2, 3, 4])
And similarly when multiplying with 2.7 results in an effective multiplication of 2:
t = torch.tensor(range(5), dtype=torch.long)
print(t)
print(t * 2.7)
Output:
tensor([ 0, 1, 2, 3, 4])
tensor([ 0, 2, 4, 6, 8])
answered Nov 25 '18 at 11:54
blue-phoenoxblue-phoenox
4,395101748
As written in the comment when using 0.4.0 get the same results as with numpy:
tensor([-0.0000, -1.8421, -3.6841, -5.5262, -7.3683])
However with 0.4.1 I'm getting a zero vector too.
The reason for this is that torch.arange(0, 10, 2) returns a tensor of type float for 0.4.0 while it returns a tensor of type long for 0.4.1.
So casting your tensor to float should work for you:
torch.arange(0, 10, 2).float() *-(math.log(10000.0) / 10)
Multiplying long and float works by heavy rounding, as the result is still a tensor of type long. So when converting a FloatTensor to a LongTensor values between -1 and 1 will be rounded to 0.
Since -(math.log(10000.0) / 10) results in -0.9210340371976183 your result is 0. So effectively -0.9210340371976183 is converted to type long before multiplying. But when converting it will be round down to 0, see this example:
t = torch.tensor((-(math.log(10000.0) / 10)))
print('FloatTensor:', t)
print('Converted to Long:', t.long())
Outout:
FloatTensor: tensor(-0.9210)
Converted to Long: tensor(0)
Thus:
torch.arange(0, 10, 2).float() *-(math.log(10000.0) / 10)
becomes:
torch.arange(0, 10, 2).float() * 0
Therefore you get a tensor of zeros as result.
Some more examples:
If you multiply it with a value between 1 and 2, lets say 1.7, it will always been rounded down to 1:
t = torch.tensor(range(5), dtype=torch.long)
print(t)
print(t * 1.7)
Output:
tensor([ 0, 1, 2, 3, 4])
tensor([ 0, 1, 2, 3, 4])
And similarly when multiplying with 2.7 results in an effective multiplication of 2:
t = torch.tensor(range(5), dtype=torch.long)
print(t)
print(t * 2.7)
Output:
tensor([ 0, 1, 2, 3, 4])
tensor([ 0, 2, 4, 6, 8])
answered Nov 25 '18 at 11:54
blue-phoenoxblue-phoenox
4,395101748
edited Nov 25 '18 at 16:21
answered Nov 25 '18 at 11:54
blue-phoenoxblue-phoenox
4,395101748
answered Nov 25 '18 at 11:54
blue-phoenoxblue-phoenox
4,395101748
answered Nov 25 '18 at 11:54
blue-phoenoxblue-phoenox
4,395101748
4,395101748
Yes. Can you elaborate a bit more on why is that? Without .float(), I add/minus 1,2... to (math.log(10000.0) / 10) and will get something like tensor([ 0, -2, -4, -6, -8]), tensor([0, 0, 0, 0, 0]), tensor([0, 2, 4, 6, 8])...
– Kuo
Nov 25 '18 at 12:08
@Kuo Thanks, I added some more examples to make the behaviour of multiplicationlong*floatmore clear!
– blue-phoenox
Nov 25 '18 at 12:19
add a comment |
Yes. Can you elaborate a bit more on why is that? Without .float(), I add/minus 1,2... to (math.log(10000.0) / 10) and will get something like tensor([ 0, -2, -4, -6, -8]), tensor([0, 0, 0, 0, 0]), tensor([0, 2, 4, 6, 8])...
– Kuo
Nov 25 '18 at 12:08
@Kuo Thanks, I added some more examples to make the behaviour of multiplicationlong*floatmore clear!
– blue-phoenox
Nov 25 '18 at 12:19
Yes. Can you elaborate a bit more on why is that? Without .float(), I add/minus 1,2... to (math.log(10000.0) / 10) and will get something like tensor([ 0, -2, -4, -6, -8]), tensor([0, 0, 0, 0, 0]), tensor([0, 2, 4, 6, 8])...
– Kuo
Nov 25 '18 at 12:08
Yes. Can you elaborate a bit more on why is that? Without .float(), I add/minus 1,2... to (math.log(10000.0) / 10) and will get something like tensor([ 0, -2, -4, -6, -8]), tensor([0, 0, 0, 0, 0]), tensor([0, 2, 4, 6, 8])...
– Kuo
Nov 25 '18 at 12:08
@Kuo Thanks, I added some more examples to make the behaviour of multiplication
long * float more clear!– blue-phoenox
Nov 25 '18 at 12:19
@Kuo Thanks, I added some more examples to make the behaviour of multiplication
long * float more clear!– blue-phoenox
Nov 25 '18 at 12:19
add a comment |
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53467011%2fpytorch-multiplying-tensor-with-scalar-results-in-zero-vector%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Results in
tensor([-0.0000, -1.8421, -3.6841, -5.5262, -7.3683])for me, v0.4.0a0+3749c58– blue-phoenox
Nov 25 '18 at 11:46
Python version 3.7.1
– Kuo
Nov 25 '18 at 11:54