What could be the cause of the little difference between Caffe convolution and Tensorflow output?











up vote
3
down vote

favorite
1












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?










share|improve this question
























  • 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















up vote
3
down vote

favorite
1












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?










share|improve this question
























  • 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













up vote
3
down vote

favorite
1









up vote
3
down vote

favorite
1






1





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?










share|improve this question















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






share|improve this question















share|improve this question













share|improve this question




share|improve this question








edited Nov 15 at 16:56

























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


















  • 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

















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
});


}
});














draft saved

draft discarded


















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
















draft saved

draft discarded




















































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.




draft saved


draft discarded














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





















































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







Popular posts from this blog

How to change which sound is reproduced for terminal bell?

Can I use Tabulator js library in my java Spring + Thymeleaf project?

Title Spacing in Bjornstrup Chapter, Removing Chapter Number From Contents