New images always predict one label
0
$begingroup$
I have trained a SVM for image classification using RGB histogram as features and a couple of other ones.
These are my feature and label sizes:
STATUS] feature vector size (11244, 525)
[STATUS] training Labels (11244,)
[STATUS] training labels encoded...
[STATUS] feature vector normalized...
[STATUS] target labels: [0 0 0 ... 1 1 1]
[STATUS] target labels shape: (11244,)
I am using sklearn's train_test_split with ratio of 0.15 for test.
Following is the classification report(100% recall and precision on test). This is weird!!
Tuning hyper-parameters for precision
Best parameters set found on development set:
{'C': 1, 'kernel': 'linear'}
Grid scores on development set:
0.991 (+/-0.005) for {'C': 1, 'gamma': 0.001, 'kernel': 'rbf'}
0.852 (+/-0.003) for {'C': 1, 'gamma': 0.0001, 'kernel': 'rbf'}
0.993 (+/-0.003) for {'C': 10, 'gamma': 0.001, 'kernel': 'rbf'}
0.991 (+/-0.005) for {'C': 10, 'gamma': 0.0001, 'kernel': 'rbf'}
0.999 (+/-0.002) for {'C': 100, 'gamma': 0.001, 'kernel': 'rbf'}
0.993 (+/-0.003) for {'C': 100, 'gamma': 0.0001, 'kernel': 'rbf'}
1.000 (+/-0.000) for {'C': 1000, 'gamma': 0.001, 'kernel': 'rbf'}
0.999 (+/-0.002) for {'C': 1000, 'gamma': 0.0001, 'kernel': 'rbf'}
1.000 (+/-0.000) for {'C': 1, 'kernel': 'linear'}
1.000 (+/-0.000) for {'C': 10, 'kernel': 'linear'}
1.000 (+/-0.000) for {'C': 100, 'kernel': 'linear'}
1.000 (+/-0.000) for {'C': 1000, 'kernel': 'linear'}
Detailed classification report:
The model is trained on the full development set.
The scores are computed on the full evaluation set.
precision recall f1-score support
0 1.00 1.00 1.00 574
1 1.00 1.00 1.00 1113
micro avg 1.00 1.00 1.00 1687
macro avg 1.00 1.00 1.00 1687
weighted avg 1.00 1.00 1.00 1687
# Tuning hyper-parameters for recall
Best parameters set found on development set:
{'C': 1, 'kernel': 'linear'}
Grid scores on development set:
0.986 (+/-0.006) for {'C': 1, 'gamma': 0.001, 'kernel': 'rbf'}
0.633 (+/-0.009) for {'C': 1, 'gamma': 0.0001, 'kernel': 'rbf'}
0.988 (+/-0.005) for {'C': 10, 'gamma': 0.001, 'kernel': 'rbf'}
0.986 (+/-0.006) for {'C': 10, 'gamma': 0.0001, 'kernel': 'rbf'}
0.998 (+/-0.003) for {'C': 100, 'gamma': 0.001, 'kernel': 'rbf'}
0.988 (+/-0.005) for {'C': 100, 'gamma': 0.0001, 'kernel': 'rbf'}
1.000 (+/-0.001) for {'C': 1000, 'gamma': 0.001, 'kernel': 'rbf'}
0.998 (+/-0.003) for {'C': 1000, 'gamma': 0.0001, 'kernel': 'rbf'}
1.000 (+/-0.000) for {'C': 1, 'kernel': 'linear'}
1.000 (+/-0.001) for {'C': 10, 'kernel': 'linear'}
1.000 (+/-0.001) for {'C': 100, 'kernel': 'linear'}
1.000 (+/-0.001) for {'C': 1000, 'kernel': 'linear'}
Detailed classification report:
The model is trained on the full development set.
The scores are computed on the full evaluation set.
precision recall f1-score support
0 1.00 1.00 1.00 574
1 1.00 1.00 1.00 1113
micro avg 1.00 1.00 1.00 1687
macro avg 1.00 1.00 1.00 1687
weighted avg 1.00 1.00 1.00 1687
BUT, on new images(sampled from same distribution), I am not getting even a single classification right. What could be going wrong?
scikit-learn svm
asked 19 hours ago
1.6181.618
1
New contributor
1.618 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
0
$begingroup$
I have trained a SVM for image classification using RGB histogram as features and a couple of other ones.
These are my feature and label sizes:
STATUS] feature vector size (11244, 525)
[STATUS] training Labels (11244,)
[STATUS] training labels encoded...
[STATUS] feature vector normalized...
[STATUS] target labels: [0 0 0 ... 1 1 1]
[STATUS] target labels shape: (11244,)
I am using sklearn's train_test_split with ratio of 0.15 for test.
Following is the classification report(100% recall and precision on test). This is weird!!
Tuning hyper-parameters for precision
Best parameters set found on development set:
{'C': 1, 'kernel': 'linear'}
Grid scores on development set:
0.991 (+/-0.005) for {'C': 1, 'gamma': 0.001, 'kernel': 'rbf'}
0.852 (+/-0.003) for {'C': 1, 'gamma': 0.0001, 'kernel': 'rbf'}
0.993 (+/-0.003) for {'C': 10, 'gamma': 0.001, 'kernel': 'rbf'}
0.991 (+/-0.005) for {'C': 10, 'gamma': 0.0001, 'kernel': 'rbf'}
0.999 (+/-0.002) for {'C': 100, 'gamma': 0.001, 'kernel': 'rbf'}
0.993 (+/-0.003) for {'C': 100, 'gamma': 0.0001, 'kernel': 'rbf'}
1.000 (+/-0.000) for {'C': 1000, 'gamma': 0.001, 'kernel': 'rbf'}
0.999 (+/-0.002) for {'C': 1000, 'gamma': 0.0001, 'kernel': 'rbf'}
1.000 (+/-0.000) for {'C': 1, 'kernel': 'linear'}
1.000 (+/-0.000) for {'C': 10, 'kernel': 'linear'}
1.000 (+/-0.000) for {'C': 100, 'kernel': 'linear'}
1.000 (+/-0.000) for {'C': 1000, 'kernel': 'linear'}
Detailed classification report:
The model is trained on the full development set.
The scores are computed on the full evaluation set.
precision recall f1-score support
0 1.00 1.00 1.00 574
1 1.00 1.00 1.00 1113
micro avg 1.00 1.00 1.00 1687
macro avg 1.00 1.00 1.00 1687
weighted avg 1.00 1.00 1.00 1687
# Tuning hyper-parameters for recall
Best parameters set found on development set:
{'C': 1, 'kernel': 'linear'}
Grid scores on development set:
0.986 (+/-0.006) for {'C': 1, 'gamma': 0.001, 'kernel': 'rbf'}
0.633 (+/-0.009) for {'C': 1, 'gamma': 0.0001, 'kernel': 'rbf'}
0.988 (+/-0.005) for {'C': 10, 'gamma': 0.001, 'kernel': 'rbf'}
0.986 (+/-0.006) for {'C': 10, 'gamma': 0.0001, 'kernel': 'rbf'}
0.998 (+/-0.003) for {'C': 100, 'gamma': 0.001, 'kernel': 'rbf'}
0.988 (+/-0.005) for {'C': 100, 'gamma': 0.0001, 'kernel': 'rbf'}
1.000 (+/-0.001) for {'C': 1000, 'gamma': 0.001, 'kernel': 'rbf'}
0.998 (+/-0.003) for {'C': 1000, 'gamma': 0.0001, 'kernel': 'rbf'}
1.000 (+/-0.000) for {'C': 1, 'kernel': 'linear'}
1.000 (+/-0.001) for {'C': 10, 'kernel': 'linear'}
1.000 (+/-0.001) for {'C': 100, 'kernel': 'linear'}
1.000 (+/-0.001) for {'C': 1000, 'kernel': 'linear'}
Detailed classification report:
The model is trained on the full development set.
The scores are computed on the full evaluation set.
precision recall f1-score support
0 1.00 1.00 1.00 574
1 1.00 1.00 1.00 1113
micro avg 1.00 1.00 1.00 1687
macro avg 1.00 1.00 1.00 1687
weighted avg 1.00 1.00 1.00 1687
BUT, on new images(sampled from same distribution), I am not getting even a single classification right. What could be going wrong?
scikit-learn svm
asked 19 hours ago
1.6181.618
1
New contributor
1.618 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
0
0
0
$begingroup$
I have trained a SVM for image classification using RGB histogram as features and a couple of other ones.
These are my feature and label sizes:
STATUS] feature vector size (11244, 525)
[STATUS] training Labels (11244,)
[STATUS] training labels encoded...
[STATUS] feature vector normalized...
[STATUS] target labels: [0 0 0 ... 1 1 1]
[STATUS] target labels shape: (11244,)
I am using sklearn's train_test_split with ratio of 0.15 for test.
Following is the classification report(100% recall and precision on test). This is weird!!
Tuning hyper-parameters for precision
Best parameters set found on development set:
{'C': 1, 'kernel': 'linear'}
Grid scores on development set:
0.991 (+/-0.005) for {'C': 1, 'gamma': 0.001, 'kernel': 'rbf'}
0.852 (+/-0.003) for {'C': 1, 'gamma': 0.0001, 'kernel': 'rbf'}
0.993 (+/-0.003) for {'C': 10, 'gamma': 0.001, 'kernel': 'rbf'}
0.991 (+/-0.005) for {'C': 10, 'gamma': 0.0001, 'kernel': 'rbf'}
0.999 (+/-0.002) for {'C': 100, 'gamma': 0.001, 'kernel': 'rbf'}
0.993 (+/-0.003) for {'C': 100, 'gamma': 0.0001, 'kernel': 'rbf'}
1.000 (+/-0.000) for {'C': 1000, 'gamma': 0.001, 'kernel': 'rbf'}
0.999 (+/-0.002) for {'C': 1000, 'gamma': 0.0001, 'kernel': 'rbf'}
1.000 (+/-0.000) for {'C': 1, 'kernel': 'linear'}
1.000 (+/-0.000) for {'C': 10, 'kernel': 'linear'}
1.000 (+/-0.000) for {'C': 100, 'kernel': 'linear'}
1.000 (+/-0.000) for {'C': 1000, 'kernel': 'linear'}
Detailed classification report:
The model is trained on the full development set.
The scores are computed on the full evaluation set.
precision recall f1-score support
0 1.00 1.00 1.00 574
1 1.00 1.00 1.00 1113
micro avg 1.00 1.00 1.00 1687
macro avg 1.00 1.00 1.00 1687
weighted avg 1.00 1.00 1.00 1687
# Tuning hyper-parameters for recall
Best parameters set found on development set:
{'C': 1, 'kernel': 'linear'}
Grid scores on development set:
0.986 (+/-0.006) for {'C': 1, 'gamma': 0.001, 'kernel': 'rbf'}
0.633 (+/-0.009) for {'C': 1, 'gamma': 0.0001, 'kernel': 'rbf'}
0.988 (+/-0.005) for {'C': 10, 'gamma': 0.001, 'kernel': 'rbf'}
0.986 (+/-0.006) for {'C': 10, 'gamma': 0.0001, 'kernel': 'rbf'}
0.998 (+/-0.003) for {'C': 100, 'gamma': 0.001, 'kernel': 'rbf'}
0.988 (+/-0.005) for {'C': 100, 'gamma': 0.0001, 'kernel': 'rbf'}
1.000 (+/-0.001) for {'C': 1000, 'gamma': 0.001, 'kernel': 'rbf'}
0.998 (+/-0.003) for {'C': 1000, 'gamma': 0.0001, 'kernel': 'rbf'}
1.000 (+/-0.000) for {'C': 1, 'kernel': 'linear'}
1.000 (+/-0.001) for {'C': 10, 'kernel': 'linear'}
1.000 (+/-0.001) for {'C': 100, 'kernel': 'linear'}
1.000 (+/-0.001) for {'C': 1000, 'kernel': 'linear'}
Detailed classification report:
The model is trained on the full development set.
The scores are computed on the full evaluation set.
precision recall f1-score support
0 1.00 1.00 1.00 574
1 1.00 1.00 1.00 1113
micro avg 1.00 1.00 1.00 1687
macro avg 1.00 1.00 1.00 1687
weighted avg 1.00 1.00 1.00 1687
BUT, on new images(sampled from same distribution), I am not getting even a single classification right. What could be going wrong?
scikit-learn svm
asked 19 hours ago
1.6181.618
1
New contributor
1.618 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
I have trained a SVM for image classification using RGB histogram as features and a couple of other ones.
These are my feature and label sizes:
STATUS] feature vector size (11244, 525)
[STATUS] training Labels (11244,)
[STATUS] training labels encoded...
[STATUS] feature vector normalized...
[STATUS] target labels: [0 0 0 ... 1 1 1]
[STATUS] target labels shape: (11244,)
I am using sklearn's train_test_split with ratio of 0.15 for test.
Following is the classification report(100% recall and precision on test). This is weird!!
Tuning hyper-parameters for precision
Best parameters set found on development set:
{'C': 1, 'kernel': 'linear'}
Grid scores on development set:
0.991 (+/-0.005) for {'C': 1, 'gamma': 0.001, 'kernel': 'rbf'}
0.852 (+/-0.003) for {'C': 1, 'gamma': 0.0001, 'kernel': 'rbf'}
0.993 (+/-0.003) for {'C': 10, 'gamma': 0.001, 'kernel': 'rbf'}
0.991 (+/-0.005) for {'C': 10, 'gamma': 0.0001, 'kernel': 'rbf'}
0.999 (+/-0.002) for {'C': 100, 'gamma': 0.001, 'kernel': 'rbf'}
0.993 (+/-0.003) for {'C': 100, 'gamma': 0.0001, 'kernel': 'rbf'}
1.000 (+/-0.000) for {'C': 1000, 'gamma': 0.001, 'kernel': 'rbf'}
0.999 (+/-0.002) for {'C': 1000, 'gamma': 0.0001, 'kernel': 'rbf'}
1.000 (+/-0.000) for {'C': 1, 'kernel': 'linear'}
1.000 (+/-0.000) for {'C': 10, 'kernel': 'linear'}
1.000 (+/-0.000) for {'C': 100, 'kernel': 'linear'}
1.000 (+/-0.000) for {'C': 1000, 'kernel': 'linear'}
Detailed classification report:
The model is trained on the full development set.
The scores are computed on the full evaluation set.
precision recall f1-score support
0 1.00 1.00 1.00 574
1 1.00 1.00 1.00 1113
micro avg 1.00 1.00 1.00 1687
macro avg 1.00 1.00 1.00 1687
weighted avg 1.00 1.00 1.00 1687
# Tuning hyper-parameters for recall
Best parameters set found on development set:
{'C': 1, 'kernel': 'linear'}
Grid scores on development set:
0.986 (+/-0.006) for {'C': 1, 'gamma': 0.001, 'kernel': 'rbf'}
0.633 (+/-0.009) for {'C': 1, 'gamma': 0.0001, 'kernel': 'rbf'}
0.988 (+/-0.005) for {'C': 10, 'gamma': 0.001, 'kernel': 'rbf'}
0.986 (+/-0.006) for {'C': 10, 'gamma': 0.0001, 'kernel': 'rbf'}
0.998 (+/-0.003) for {'C': 100, 'gamma': 0.001, 'kernel': 'rbf'}
0.988 (+/-0.005) for {'C': 100, 'gamma': 0.0001, 'kernel': 'rbf'}
1.000 (+/-0.001) for {'C': 1000, 'gamma': 0.001, 'kernel': 'rbf'}
0.998 (+/-0.003) for {'C': 1000, 'gamma': 0.0001, 'kernel': 'rbf'}
1.000 (+/-0.000) for {'C': 1, 'kernel': 'linear'}
1.000 (+/-0.001) for {'C': 10, 'kernel': 'linear'}
1.000 (+/-0.001) for {'C': 100, 'kernel': 'linear'}
1.000 (+/-0.001) for {'C': 1000, 'kernel': 'linear'}
Detailed classification report:
The model is trained on the full development set.
The scores are computed on the full evaluation set.
precision recall f1-score support
0 1.00 1.00 1.00 574
1 1.00 1.00 1.00 1113
micro avg 1.00 1.00 1.00 1687
macro avg 1.00 1.00 1.00 1687
weighted avg 1.00 1.00 1.00 1687
BUT, on new images(sampled from same distribution), I am not getting even a single classification right. What could be going wrong?
scikit-learn svm
scikit-learn svm
asked 19 hours ago
1.6181.618
1
New contributor
1.618 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked 19 hours ago
1.6181.618
1
New contributor
1.618 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked 19 hours ago
1.6181.618
1
New contributor
1.618 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked 19 hours ago
1.6181.618
1
asked 19 hours ago
1.6181.618
1
1
New contributor
1.618 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
New contributor
1.618 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
1.618 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
add a comment |
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "557"
};
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: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
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
});
}
});
1.618 is a new contributor. Be nice, and check out our Code of Conduct.
draft saved
draft discarded
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%2fdatascience.stackexchange.com%2fquestions%2f49251%2fnew-images-always-predict-one-label%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
1.618 is a new contributor. Be nice, and check out our Code of Conduct.
draft saved
draft discarded
1.618 is a new contributor. Be nice, and check out our Code of Conduct.
1.618 is a new contributor. Be nice, and check out our Code of Conduct.
1.618 is a new contributor. Be nice, and check out our Code of Conduct.
Thanks for contributing an answer to Data Science Stack Exchange!
- 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.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
draft saved
draft discarded
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%2fdatascience.stackexchange.com%2fquestions%2f49251%2fnew-images-always-predict-one-label%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
