Training VGG16 with CIFAR-10 dataset in TensorFlow, can't get good accuracy
I am a beginner to study ML. I am studying the VGG16 model in TensorFlow. My study is here.
Now I meet a question and still can't find the reason. I studied the two case.
- Study pre-trained VGG16-A model to do predict. (VGG in TensorFlow)
- Study VGG16-B model with CIFAR-10 dataset to do training. (Ashing00/Tensorflow_VGG)
They all work fine. But now I want to simulate the Case 2.'s procedure, try to use VGG16-A model to do training with CIFAR-10 dataset. But I am failed, I can't get good accuracy.
The testing is in vgg16f_training_cifar10.ipynb. Can someone give me some hint?
Thanks a lot.
tensorflow
asked Nov 26 '18 at 7:00
NienFeng YaoNienFeng Yao
165
add a comment |
I am a beginner to study ML. I am studying the VGG16 model in TensorFlow. My study is here.
Now I meet a question and still can't find the reason. I studied the two case.
- Study pre-trained VGG16-A model to do predict. (VGG in TensorFlow)
- Study VGG16-B model with CIFAR-10 dataset to do training. (Ashing00/Tensorflow_VGG)
They all work fine. But now I want to simulate the Case 2.'s procedure, try to use VGG16-A model to do training with CIFAR-10 dataset. But I am failed, I can't get good accuracy.
The testing is in vgg16f_training_cifar10.ipynb. Can someone give me some hint?
Thanks a lot.
tensorflow
asked Nov 26 '18 at 7:00
NienFeng YaoNienFeng Yao
165
I add batch normalization in each hidden layer. Now we can get good accuracy.
– NienFeng Yao
Nov 28 '18 at 7:45
add a comment |
I am a beginner to study ML. I am studying the VGG16 model in TensorFlow. My study is here.
Now I meet a question and still can't find the reason. I studied the two case.
- Study pre-trained VGG16-A model to do predict. (VGG in TensorFlow)
- Study VGG16-B model with CIFAR-10 dataset to do training. (Ashing00/Tensorflow_VGG)
They all work fine. But now I want to simulate the Case 2.'s procedure, try to use VGG16-A model to do training with CIFAR-10 dataset. But I am failed, I can't get good accuracy.
The testing is in vgg16f_training_cifar10.ipynb. Can someone give me some hint?
Thanks a lot.
tensorflow
asked Nov 26 '18 at 7:00
NienFeng YaoNienFeng Yao
165
I am a beginner to study ML. I am studying the VGG16 model in TensorFlow. My study is here.
Now I meet a question and still can't find the reason. I studied the two case.
- Study pre-trained VGG16-A model to do predict. (VGG in TensorFlow)
- Study VGG16-B model with CIFAR-10 dataset to do training. (Ashing00/Tensorflow_VGG)
They all work fine. But now I want to simulate the Case 2.'s procedure, try to use VGG16-A model to do training with CIFAR-10 dataset. But I am failed, I can't get good accuracy.
The testing is in vgg16f_training_cifar10.ipynb. Can someone give me some hint?
Thanks a lot.
tensorflow
tensorflow
asked Nov 26 '18 at 7:00
NienFeng YaoNienFeng Yao
165
asked Nov 26 '18 at 7:00
NienFeng YaoNienFeng Yao
165
edited Nov 26 '18 at 7:09
NienFeng Yao
asked Nov 26 '18 at 7:00
NienFeng YaoNienFeng Yao
165
asked Nov 26 '18 at 7:00
NienFeng YaoNienFeng Yao
165
asked Nov 26 '18 at 7:00
NienFeng YaoNienFeng Yao
165
165
I add batch normalization in each hidden layer. Now we can get good accuracy.
– NienFeng Yao
Nov 28 '18 at 7:45
add a comment |
I add batch normalization in each hidden layer. Now we can get good accuracy.
– NienFeng Yao
Nov 28 '18 at 7:45
I add batch normalization in each hidden layer. Now we can get good accuracy.
– NienFeng Yao
Nov 28 '18 at 7:45
I add batch normalization in each hidden layer. Now we can get good accuracy.
– NienFeng Yao
Nov 28 '18 at 7:45
add a comment |
1 Answer
1
active
oldest
votes
I add batch normalization in each hidden layer. Now we can get good accuracy.
answered Nov 29 '18 at 3:53
NienFeng YaoNienFeng Yao
165
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%2f53476098%2ftraining-vgg16-with-cifar-10-dataset-in-tensorflow-cant-get-good-accuracy%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
I add batch normalization in each hidden layer. Now we can get good accuracy.
answered Nov 29 '18 at 3:53
NienFeng YaoNienFeng Yao
165
add a comment |
I add batch normalization in each hidden layer. Now we can get good accuracy.
answered Nov 29 '18 at 3:53
NienFeng YaoNienFeng Yao
165
add a comment |
I add batch normalization in each hidden layer. Now we can get good accuracy.
answered Nov 29 '18 at 3:53
NienFeng YaoNienFeng Yao
165
I add batch normalization in each hidden layer. Now we can get good accuracy.
answered Nov 29 '18 at 3:53
NienFeng YaoNienFeng Yao
165
answered Nov 29 '18 at 3:53
NienFeng YaoNienFeng Yao
165
answered Nov 29 '18 at 3:53
NienFeng YaoNienFeng Yao
165
answered Nov 29 '18 at 3:53
NienFeng YaoNienFeng Yao
165
165
add a comment |
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%2f53476098%2ftraining-vgg16-with-cifar-10-dataset-in-tensorflow-cant-get-good-accuracy%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
I add batch normalization in each hidden layer. Now we can get good accuracy.
– NienFeng Yao
Nov 28 '18 at 7:45