Images Score Regression only regresses to the average of the target values
$begingroup$
I have 700 3D images, each one having a target value. The target value distribution after standardizing looks as below
After training, my validation set MSE (10% of data) does not go down and R2 score remains below 0.1 and predicted v.s. real values look like as
What I am seeing is that model is only trying to set all values as the mean value, and cannot get the values away from the mean right. I am using MSE loss and have also tried Huber loss. I have tried normalizing my data to [0,1] and also [-1,1] (enforcing the last 1-neuron layer with a sigmoid or tanh activation function to this range as well) but haven't seen any improvement.
FYI, my architecture is 3 times (conv3d, conv3d, maxpool) + 2 times(dense layer) + a one unit dense layer. Adam optimizer, leaky-relu activations, regularizations and drop outs.
FYI, I have done an extensive hyperparameter study as well, but never any improvements.
Any idea why this is happening, maybe a need of changing my data range?
regression cnn convolution image-preprocessing
$endgroup$
add a comment |
$begingroup$
I have 700 3D images, each one having a target value. The target value distribution after standardizing looks as below
After training, my validation set MSE (10% of data) does not go down and R2 score remains below 0.1 and predicted v.s. real values look like as
What I am seeing is that model is only trying to set all values as the mean value, and cannot get the values away from the mean right. I am using MSE loss and have also tried Huber loss. I have tried normalizing my data to [0,1] and also [-1,1] (enforcing the last 1-neuron layer with a sigmoid or tanh activation function to this range as well) but haven't seen any improvement.
FYI, my architecture is 3 times (conv3d, conv3d, maxpool) + 2 times(dense layer) + a one unit dense layer. Adam optimizer, leaky-relu activations, regularizations and drop outs.
FYI, I have done an extensive hyperparameter study as well, but never any improvements.
Any idea why this is happening, maybe a need of changing my data range?
regression cnn convolution image-preprocessing
$endgroup$
add a comment |
$begingroup$
I have 700 3D images, each one having a target value. The target value distribution after standardizing looks as below
After training, my validation set MSE (10% of data) does not go down and R2 score remains below 0.1 and predicted v.s. real values look like as
What I am seeing is that model is only trying to set all values as the mean value, and cannot get the values away from the mean right. I am using MSE loss and have also tried Huber loss. I have tried normalizing my data to [0,1] and also [-1,1] (enforcing the last 1-neuron layer with a sigmoid or tanh activation function to this range as well) but haven't seen any improvement.
FYI, my architecture is 3 times (conv3d, conv3d, maxpool) + 2 times(dense layer) + a one unit dense layer. Adam optimizer, leaky-relu activations, regularizations and drop outs.
FYI, I have done an extensive hyperparameter study as well, but never any improvements.
Any idea why this is happening, maybe a need of changing my data range?
regression cnn convolution image-preprocessing
$endgroup$
I have 700 3D images, each one having a target value. The target value distribution after standardizing looks as below
After training, my validation set MSE (10% of data) does not go down and R2 score remains below 0.1 and predicted v.s. real values look like as
What I am seeing is that model is only trying to set all values as the mean value, and cannot get the values away from the mean right. I am using MSE loss and have also tried Huber loss. I have tried normalizing my data to [0,1] and also [-1,1] (enforcing the last 1-neuron layer with a sigmoid or tanh activation function to this range as well) but haven't seen any improvement.
FYI, my architecture is 3 times (conv3d, conv3d, maxpool) + 2 times(dense layer) + a one unit dense layer. Adam optimizer, leaky-relu activations, regularizations and drop outs.
FYI, I have done an extensive hyperparameter study as well, but never any improvements.
Any idea why this is happening, maybe a need of changing my data range?
regression cnn convolution image-preprocessing
regression cnn convolution image-preprocessing
asked 12 mins ago
SoyolSoyol
1112
1112
add a comment |
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function () {
return StackExchange.using("mathjaxEditing", function () {
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
});
});
}, "mathjax-editing");
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
});
}
});
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%2f44672%2fimages-score-regression-only-regresses-to-the-average-of-the-target-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 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.
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%2f44672%2fimages-score-regression-only-regresses-to-the-average-of-the-target-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