Proper way for creating mask for segmentation
0
Im creating the mask as follows for the sake of segmentation task.
lbl = load_img(im)
lbl = scipy.misc.imresize(lbl, (self.image_shape[1], self.image_shape[0]))
bg_color = np.array([255, 255, 255])
building_color = np.array([255, 0, 0])
road_color = np.array([0, 0, 255])
gt_bg = np.all(lbl == bg_color, axis=2)
building_bg = np.all(lbl == building_color, axis=2)
road_bg = np.all(lbl == road_color, axis=2)
building_bg = gt_bg.reshape(*building_bg.shape, 1)
road_bg = gt_bg.reshape(*road_bg.shape, 1)
gt_bg = gt_bg.reshape(*gt_bg.shape, 1)
lbl = np.concatenate((gt_bg, building_bg, road_bg), axis=2)
return np.array([lbl])
I'm trying to segment three attributes so there are three different pixel values. Is this still a correct way of creating mask? because the training loss tends to be less than 50.
python tensorflow keras image-segmentation semantic-segmentation
asked Jan 19 at 14:14
user1241241user1241241
16810
add a comment |
0
Im creating the mask as follows for the sake of segmentation task.
lbl = load_img(im)
lbl = scipy.misc.imresize(lbl, (self.image_shape[1], self.image_shape[0]))
bg_color = np.array([255, 255, 255])
building_color = np.array([255, 0, 0])
road_color = np.array([0, 0, 255])
gt_bg = np.all(lbl == bg_color, axis=2)
building_bg = np.all(lbl == building_color, axis=2)
road_bg = np.all(lbl == road_color, axis=2)
building_bg = gt_bg.reshape(*building_bg.shape, 1)
road_bg = gt_bg.reshape(*road_bg.shape, 1)
gt_bg = gt_bg.reshape(*gt_bg.shape, 1)
lbl = np.concatenate((gt_bg, building_bg, road_bg), axis=2)
return np.array([lbl])
I'm trying to segment three attributes so there are three different pixel values. Is this still a correct way of creating mask? because the training loss tends to be less than 50.
python tensorflow keras image-segmentation semantic-segmentation
asked Jan 19 at 14:14
user1241241user1241241
16810
Hi, to create mask for segmentation, you don't want to use a RGB like format for the training. Usually, each class will have its own channel in the label tensor. That way, each pixel has its own class probabilities. Here : bg = [1, 0, 0]; building = [0, 1, 0]; road = [0, 0, 1]
– Pierre-Nicolas Piquin
yesterday
add a comment |
0
0
0
Im creating the mask as follows for the sake of segmentation task.
lbl = load_img(im)
lbl = scipy.misc.imresize(lbl, (self.image_shape[1], self.image_shape[0]))
bg_color = np.array([255, 255, 255])
building_color = np.array([255, 0, 0])
road_color = np.array([0, 0, 255])
gt_bg = np.all(lbl == bg_color, axis=2)
building_bg = np.all(lbl == building_color, axis=2)
road_bg = np.all(lbl == road_color, axis=2)
building_bg = gt_bg.reshape(*building_bg.shape, 1)
road_bg = gt_bg.reshape(*road_bg.shape, 1)
gt_bg = gt_bg.reshape(*gt_bg.shape, 1)
lbl = np.concatenate((gt_bg, building_bg, road_bg), axis=2)
return np.array([lbl])
I'm trying to segment three attributes so there are three different pixel values. Is this still a correct way of creating mask? because the training loss tends to be less than 50.
python tensorflow keras image-segmentation semantic-segmentation
asked Jan 19 at 14:14
user1241241user1241241
16810
Im creating the mask as follows for the sake of segmentation task.
lbl = load_img(im)
lbl = scipy.misc.imresize(lbl, (self.image_shape[1], self.image_shape[0]))
bg_color = np.array([255, 255, 255])
building_color = np.array([255, 0, 0])
road_color = np.array([0, 0, 255])
gt_bg = np.all(lbl == bg_color, axis=2)
building_bg = np.all(lbl == building_color, axis=2)
road_bg = np.all(lbl == road_color, axis=2)
building_bg = gt_bg.reshape(*building_bg.shape, 1)
road_bg = gt_bg.reshape(*road_bg.shape, 1)
gt_bg = gt_bg.reshape(*gt_bg.shape, 1)
lbl = np.concatenate((gt_bg, building_bg, road_bg), axis=2)
return np.array([lbl])
I'm trying to segment three attributes so there are three different pixel values. Is this still a correct way of creating mask? because the training loss tends to be less than 50.
python tensorflow keras image-segmentation semantic-segmentation
python tensorflow keras image-segmentation semantic-segmentation
asked Jan 19 at 14:14
user1241241user1241241
16810
asked Jan 19 at 14:14
user1241241user1241241
16810
asked Jan 19 at 14:14
user1241241user1241241
16810
asked Jan 19 at 14:14
user1241241user1241241
16810
asked Jan 19 at 14:14
user1241241user1241241
16810
16810
Hi, to create mask for segmentation, you don't want to use a RGB like format for the training. Usually, each class will have its own channel in the label tensor. That way, each pixel has its own class probabilities. Here : bg = [1, 0, 0]; building = [0, 1, 0]; road = [0, 0, 1]
– Pierre-Nicolas Piquin
yesterday
add a comment |
Hi, to create mask for segmentation, you don't want to use a RGB like format for the training. Usually, each class will have its own channel in the label tensor. That way, each pixel has its own class probabilities. Here : bg = [1, 0, 0]; building = [0, 1, 0]; road = [0, 0, 1]
– Pierre-Nicolas Piquin
yesterday
Hi, to create mask for segmentation, you don't want to use a RGB like format for the training. Usually, each class will have its own channel in the label tensor. That way, each pixel has its own class probabilities. Here : bg = [1, 0, 0]; building = [0, 1, 0]; road = [0, 0, 1]
– Pierre-Nicolas Piquin
yesterday
Hi, to create mask for segmentation, you don't want to use a RGB like format for the training. Usually, each class will have its own channel in the label tensor. That way, each pixel has its own class probabilities. Here : bg = [1, 0, 0]; building = [0, 1, 0]; road = [0, 0, 1]
– Pierre-Nicolas Piquin
yesterday
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
});
}
});
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%2fstackoverflow.com%2fquestions%2f54267982%2fproper-way-for-creating-mask-for-segmentation%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
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.
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%2fstackoverflow.com%2fquestions%2f54267982%2fproper-way-for-creating-mask-for-segmentation%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
Hi, to create mask for segmentation, you don't want to use a RGB like format for the training. Usually, each class will have its own channel in the label tensor. That way, each pixel has its own class probabilities. Here : bg = [1, 0, 0]; building = [0, 1, 0]; road = [0, 0, 1]
– Pierre-Nicolas Piquin
yesterday