sklearn - How to generate proper labels with multiple values
In my course, we have to implement a working traffic light recognition algorithm using python with the common modules (numpy, sklearn, etc.)
In my simple_train dataset, there are 209 pictures where each of those pictures has no, one or multiple traffic lights on it. For simplification, I modified my loading algorithm to just return a single traffic light (if there is one or more).
My independet dataset (picture arrays) has a shape of (209, 720, 1280, 3) and I noticed that I have to reshape it into an 2d array - so my feature set array has a shape of (209, 2764800).
Now there's the tricky part I'm stuck at. Each traffic light consists of four coordinates (x_min, x_max, y_min and y_max). This means for the first three pictures, my label would look like this:
array([None, None, (610, 351, 615, 358), ... ])
On the first two pictures, there are no traffic lights but on the third one, there's a traffic light with the given boundaries.
Calling the .fit function of the MLPClassifier I get the following error message:
ValueError: Unknown label type: (array([None, None, (610, 351, 615, 358), ...])
How do I have to modify my label to get this to work?
python machine-learning scikit-learn classification
asked Nov 26 '18 at 12:14
C4p741nZC4p741nZ
4631723
add a comment |
In my course, we have to implement a working traffic light recognition algorithm using python with the common modules (numpy, sklearn, etc.)
In my simple_train dataset, there are 209 pictures where each of those pictures has no, one or multiple traffic lights on it. For simplification, I modified my loading algorithm to just return a single traffic light (if there is one or more).
My independet dataset (picture arrays) has a shape of (209, 720, 1280, 3) and I noticed that I have to reshape it into an 2d array - so my feature set array has a shape of (209, 2764800).
Now there's the tricky part I'm stuck at. Each traffic light consists of four coordinates (x_min, x_max, y_min and y_max). This means for the first three pictures, my label would look like this:
array([None, None, (610, 351, 615, 358), ... ])
On the first two pictures, there are no traffic lights but on the third one, there's a traffic light with the given boundaries.
Calling the .fit function of the MLPClassifier I get the following error message:
ValueError: Unknown label type: (array([None, None, (610, 351, 615, 358), ...])
How do I have to modify my label to get this to work?
python machine-learning scikit-learn classification
asked Nov 26 '18 at 12:14
C4p741nZC4p741nZ
4631723
You could add(0,0,0,0)label, for theno traffic light, and attempt. During prediction(0,0,0,0)should be defined to be no traffic light. However that is kinda brute forcing. Not sure of the scope of your model, but there are many recognition models out there you can research on.
– Dinari
Nov 26 '18 at 12:20
No, the task you described is object-detection and will be too complex for scikit-learn models. You can start by only predicting if any traffic light is present in the given picture or not. This can be done by changing the labels to[False, False, True]or[0, 0, 1]for your given examples.
– Vivek Kumar
Nov 26 '18 at 13:38
add a comment |
In my course, we have to implement a working traffic light recognition algorithm using python with the common modules (numpy, sklearn, etc.)
In my simple_train dataset, there are 209 pictures where each of those pictures has no, one or multiple traffic lights on it. For simplification, I modified my loading algorithm to just return a single traffic light (if there is one or more).
My independet dataset (picture arrays) has a shape of (209, 720, 1280, 3) and I noticed that I have to reshape it into an 2d array - so my feature set array has a shape of (209, 2764800).
Now there's the tricky part I'm stuck at. Each traffic light consists of four coordinates (x_min, x_max, y_min and y_max). This means for the first three pictures, my label would look like this:
array([None, None, (610, 351, 615, 358), ... ])
On the first two pictures, there are no traffic lights but on the third one, there's a traffic light with the given boundaries.
Calling the .fit function of the MLPClassifier I get the following error message:
ValueError: Unknown label type: (array([None, None, (610, 351, 615, 358), ...])
How do I have to modify my label to get this to work?
python machine-learning scikit-learn classification
asked Nov 26 '18 at 12:14
C4p741nZC4p741nZ
4631723
In my course, we have to implement a working traffic light recognition algorithm using python with the common modules (numpy, sklearn, etc.)
In my simple_train dataset, there are 209 pictures where each of those pictures has no, one or multiple traffic lights on it. For simplification, I modified my loading algorithm to just return a single traffic light (if there is one or more).
My independet dataset (picture arrays) has a shape of (209, 720, 1280, 3) and I noticed that I have to reshape it into an 2d array - so my feature set array has a shape of (209, 2764800).
Now there's the tricky part I'm stuck at. Each traffic light consists of four coordinates (x_min, x_max, y_min and y_max). This means for the first three pictures, my label would look like this:
array([None, None, (610, 351, 615, 358), ... ])
On the first two pictures, there are no traffic lights but on the third one, there's a traffic light with the given boundaries.
Calling the .fit function of the MLPClassifier I get the following error message:
ValueError: Unknown label type: (array([None, None, (610, 351, 615, 358), ...])
How do I have to modify my label to get this to work?
python machine-learning scikit-learn classification
python machine-learning scikit-learn classification
asked Nov 26 '18 at 12:14
C4p741nZC4p741nZ
4631723
asked Nov 26 '18 at 12:14
C4p741nZC4p741nZ
4631723
asked Nov 26 '18 at 12:14
C4p741nZC4p741nZ
4631723
asked Nov 26 '18 at 12:14
C4p741nZC4p741nZ
4631723
asked Nov 26 '18 at 12:14
C4p741nZC4p741nZ
4631723
4631723
You could add(0,0,0,0)label, for theno traffic light, and attempt. During prediction(0,0,0,0)should be defined to be no traffic light. However that is kinda brute forcing. Not sure of the scope of your model, but there are many recognition models out there you can research on.
– Dinari
Nov 26 '18 at 12:20
No, the task you described is object-detection and will be too complex for scikit-learn models. You can start by only predicting if any traffic light is present in the given picture or not. This can be done by changing the labels to[False, False, True]or[0, 0, 1]for your given examples.
– Vivek Kumar
Nov 26 '18 at 13:38
add a comment |
You could add(0,0,0,0)label, for theno traffic light, and attempt. During prediction(0,0,0,0)should be defined to be no traffic light. However that is kinda brute forcing. Not sure of the scope of your model, but there are many recognition models out there you can research on.
– Dinari
Nov 26 '18 at 12:20
No, the task you described is object-detection and will be too complex for scikit-learn models. You can start by only predicting if any traffic light is present in the given picture or not. This can be done by changing the labels to[False, False, True]or[0, 0, 1]for your given examples.
– Vivek Kumar
Nov 26 '18 at 13:38
You could add
(0,0,0,0) label, for the no traffic light, and attempt. During prediction (0,0,0,0) should be defined to be no traffic light. However that is kinda brute forcing. Not sure of the scope of your model, but there are many recognition models out there you can research on.– Dinari
Nov 26 '18 at 12:20
You could add
(0,0,0,0) label, for the no traffic light, and attempt. During prediction (0,0,0,0) should be defined to be no traffic light. However that is kinda brute forcing. Not sure of the scope of your model, but there are many recognition models out there you can research on.– Dinari
Nov 26 '18 at 12:20
No, the task you described is object-detection and will be too complex for scikit-learn models. You can start by only predicting if any traffic light is present in the given picture or not. This can be done by changing the labels to
[False, False, True] or [0, 0, 1] for your given examples.– Vivek Kumar
Nov 26 '18 at 13:38
No, the task you described is object-detection and will be too complex for scikit-learn models. You can start by only predicting if any traffic light is present in the given picture or not. This can be done by changing the labels to
[False, False, True] or [0, 0, 1] for your given examples.– Vivek Kumar
Nov 26 '18 at 13:38
add a comment |
0
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',
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%2f53480919%2fsklearn-how-to-generate-proper-labels-with-multiple-values%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
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%2f53480919%2fsklearn-how-to-generate-proper-labels-with-multiple-values%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
You could add
(0,0,0,0)label, for theno traffic light, and attempt. During prediction(0,0,0,0)should be defined to be no traffic light. However that is kinda brute forcing. Not sure of the scope of your model, but there are many recognition models out there you can research on.– Dinari
Nov 26 '18 at 12:20
No, the task you described is object-detection and will be too complex for scikit-learn models. You can start by only predicting if any traffic light is present in the given picture or not. This can be done by changing the labels to
[False, False, True]or[0, 0, 1]for your given examples.– Vivek Kumar
Nov 26 '18 at 13:38