What could be the cause of the little difference between Caffe convolution and Tensorflow output?
up vote
3
down vote
favorite
I have Tensorflow network and I ported it in the Caffe format. All weights and algorithm is correct in Caffe and TF, I checked it several times.
But when I run both frameworks and compare their output layer-by-layer, small differences start to appear.
For example, if the result of the BatchNormalization at the one point in Caffe is 0.940091 then for TF at the same point it is 0.939559, so the difference is 0.0005319999999999769 . Very small but it gets amplified deeper in the network we go, and at the end values are very different.
For Convolution difference is present also(-2.7540846 Caffe -2.7540843 TF) but it gets more noticeable after first BatchNormalization
I suppose it might be some internal difference and casting between some sort of FP16, FP32, FP64. Have no idea how TF handles conversion from python graph to C++ graph.
May be someone encountered same problem?
python tensorflow caffe
asked Nov 15 at 16:44
Il'ya Zhenin
4592921
add a comment |
up vote
3
down vote
favorite
I have Tensorflow network and I ported it in the Caffe format. All weights and algorithm is correct in Caffe and TF, I checked it several times.
But when I run both frameworks and compare their output layer-by-layer, small differences start to appear.
For example, if the result of the BatchNormalization at the one point in Caffe is 0.940091 then for TF at the same point it is 0.939559, so the difference is 0.0005319999999999769 . Very small but it gets amplified deeper in the network we go, and at the end values are very different.
For Convolution difference is present also(-2.7540846 Caffe -2.7540843 TF) but it gets more noticeable after first BatchNormalization
I suppose it might be some internal difference and casting between some sort of FP16, FP32, FP64. Have no idea how TF handles conversion from python graph to C++ graph.
May be someone encountered same problem?
python tensorflow caffe
asked Nov 15 at 16:44
Il'ya Zhenin
4592921
It might be due to "floating point" numbers innacuracy, see this stackoverflow.com/questions/21895756/…
– MedAli
Nov 15 at 17:00
Caffe and Tensorflow have some differences in the implementation of the Batch norm layer. Caffe has divided it into a normalization layer followed by a scaling and bias layer. Another possible issue could be that Caffe expects the input shape with channels first [CxHxW] while Tensorflow wants [HxWxC] by default (see 'data_format' parameter)
– Claes Rolen
Nov 27 at 20:08
add a comment |
up vote
3
down vote
favorite
up vote
3
down vote
favorite
I have Tensorflow network and I ported it in the Caffe format. All weights and algorithm is correct in Caffe and TF, I checked it several times.
But when I run both frameworks and compare their output layer-by-layer, small differences start to appear.
For example, if the result of the BatchNormalization at the one point in Caffe is 0.940091 then for TF at the same point it is 0.939559, so the difference is 0.0005319999999999769 . Very small but it gets amplified deeper in the network we go, and at the end values are very different.
For Convolution difference is present also(-2.7540846 Caffe -2.7540843 TF) but it gets more noticeable after first BatchNormalization
I suppose it might be some internal difference and casting between some sort of FP16, FP32, FP64. Have no idea how TF handles conversion from python graph to C++ graph.
May be someone encountered same problem?
python tensorflow caffe
asked Nov 15 at 16:44
Il'ya Zhenin
4592921
I have Tensorflow network and I ported it in the Caffe format. All weights and algorithm is correct in Caffe and TF, I checked it several times.
But when I run both frameworks and compare their output layer-by-layer, small differences start to appear.
For example, if the result of the BatchNormalization at the one point in Caffe is 0.940091 then for TF at the same point it is 0.939559, so the difference is 0.0005319999999999769 . Very small but it gets amplified deeper in the network we go, and at the end values are very different.
For Convolution difference is present also(-2.7540846 Caffe -2.7540843 TF) but it gets more noticeable after first BatchNormalization
I suppose it might be some internal difference and casting between some sort of FP16, FP32, FP64. Have no idea how TF handles conversion from python graph to C++ graph.
May be someone encountered same problem?
python tensorflow caffe
python tensorflow caffe
asked Nov 15 at 16:44
Il'ya Zhenin
4592921
asked Nov 15 at 16:44
Il'ya Zhenin
4592921
edited Nov 15 at 16:56
asked Nov 15 at 16:44
Il'ya Zhenin
4592921
asked Nov 15 at 16:44
Il'ya Zhenin
4592921
asked Nov 15 at 16:44
Il'ya Zhenin
4592921
4592921
It might be due to "floating point" numbers innacuracy, see this stackoverflow.com/questions/21895756/…
– MedAli
Nov 15 at 17:00
Caffe and Tensorflow have some differences in the implementation of the Batch norm layer. Caffe has divided it into a normalization layer followed by a scaling and bias layer. Another possible issue could be that Caffe expects the input shape with channels first [CxHxW] while Tensorflow wants [HxWxC] by default (see 'data_format' parameter)
– Claes Rolen
Nov 27 at 20:08
add a comment |
It might be due to "floating point" numbers innacuracy, see this stackoverflow.com/questions/21895756/…
– MedAli
Nov 15 at 17:00
Caffe and Tensorflow have some differences in the implementation of the Batch norm layer. Caffe has divided it into a normalization layer followed by a scaling and bias layer. Another possible issue could be that Caffe expects the input shape with channels first [CxHxW] while Tensorflow wants [HxWxC] by default (see 'data_format' parameter)
– Claes Rolen
Nov 27 at 20:08
It might be due to "floating point" numbers innacuracy, see this stackoverflow.com/questions/21895756/…
– MedAli
Nov 15 at 17:00
It might be due to "floating point" numbers innacuracy, see this stackoverflow.com/questions/21895756/…
– MedAli
Nov 15 at 17:00
Caffe and Tensorflow have some differences in the implementation of the Batch norm layer. Caffe has divided it into a normalization layer followed by a scaling and bias layer. Another possible issue could be that Caffe expects the input shape with channels first [CxHxW] while Tensorflow wants [HxWxC] by default (see 'data_format' parameter)
– Claes Rolen
Nov 27 at 20:08
Caffe and Tensorflow have some differences in the implementation of the Batch norm layer. Caffe has divided it into a normalization layer followed by a scaling and bias layer. Another possible issue could be that Caffe expects the input shape with channels first [CxHxW] while Tensorflow wants [HxWxC] by default (see 'data_format' parameter)
– Claes Rolen
Nov 27 at 20:08
add a comment |
active
oldest
votes
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',
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%2f53324147%2fwhat-could-be-the-cause-of-the-little-difference-between-caffe-convolution-and-t%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
active
oldest
votes
active
oldest
votes
active
oldest
votes
active
oldest
votes
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.
Some of your past answers have not been well-received, and you're in danger of being blocked from answering.
Please pay close attention to the following guidance:
- 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%2f53324147%2fwhat-could-be-the-cause-of-the-little-difference-between-caffe-convolution-and-t%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
It might be due to "floating point" numbers innacuracy, see this stackoverflow.com/questions/21895756/…
– MedAli
Nov 15 at 17:00
Caffe and Tensorflow have some differences in the implementation of the Batch norm layer. Caffe has divided it into a normalization layer followed by a scaling and bias layer. Another possible issue could be that Caffe expects the input shape with channels first [CxHxW] while Tensorflow wants [HxWxC] by default (see 'data_format' parameter)
– Claes Rolen
Nov 27 at 20:08