yolov2 keras model output interpretation
I try to figure out how to interpret yolov2 output.
I have converted yolo.cft & yolo.weights to yolo.h5 which is Keras Model.
Then I run model.predict(img) which gives me output with shape (1, 19, 19, 425).
As far as I know, the interpretation of this shape is:
Image is divided for 19x19 grid cell
425 is 5 x 85 where 5 is number of anchor boxes and 85 is (isObject, Boxx, Boxy, Boxw, Boxh, class1, class2, ..., class80).
But I wonder how can I read this data? Or there is sth to do with output before reading?
For example:
output_data = model.predict(img)
is output_data[0][0][0][0] checking if in box [0, 0] in anchor_box 0 is any object? Then output_data[0][0][0][1:4] is data corelated with bounding box details and output_data[0][0][0][5:85] tells me which class is cougth in box? Are my suspections right or I'm totally wrong?
Thanks in advance
Btw. I've used cfg file form here
python-3.x machine-learning keras computer-vision yolo
asked Nov 14 '18 at 20:25
Patryk KaczmarekPatryk Kaczmarek
63
add a comment |
I try to figure out how to interpret yolov2 output.
I have converted yolo.cft & yolo.weights to yolo.h5 which is Keras Model.
Then I run model.predict(img) which gives me output with shape (1, 19, 19, 425).
As far as I know, the interpretation of this shape is:
Image is divided for 19x19 grid cell
425 is 5 x 85 where 5 is number of anchor boxes and 85 is (isObject, Boxx, Boxy, Boxw, Boxh, class1, class2, ..., class80).
But I wonder how can I read this data? Or there is sth to do with output before reading?
For example:
output_data = model.predict(img)
is output_data[0][0][0][0] checking if in box [0, 0] in anchor_box 0 is any object? Then output_data[0][0][0][1:4] is data corelated with bounding box details and output_data[0][0][0][5:85] tells me which class is cougth in box? Are my suspections right or I'm totally wrong?
Thanks in advance
Btw. I've used cfg file form here
python-3.x machine-learning keras computer-vision yolo
asked Nov 14 '18 at 20:25
Patryk KaczmarekPatryk Kaczmarek
63
add a comment |
I try to figure out how to interpret yolov2 output.
I have converted yolo.cft & yolo.weights to yolo.h5 which is Keras Model.
Then I run model.predict(img) which gives me output with shape (1, 19, 19, 425).
As far as I know, the interpretation of this shape is:
Image is divided for 19x19 grid cell
425 is 5 x 85 where 5 is number of anchor boxes and 85 is (isObject, Boxx, Boxy, Boxw, Boxh, class1, class2, ..., class80).
But I wonder how can I read this data? Or there is sth to do with output before reading?
For example:
output_data = model.predict(img)
is output_data[0][0][0][0] checking if in box [0, 0] in anchor_box 0 is any object? Then output_data[0][0][0][1:4] is data corelated with bounding box details and output_data[0][0][0][5:85] tells me which class is cougth in box? Are my suspections right or I'm totally wrong?
Thanks in advance
Btw. I've used cfg file form here
python-3.x machine-learning keras computer-vision yolo
asked Nov 14 '18 at 20:25
Patryk KaczmarekPatryk Kaczmarek
63
I try to figure out how to interpret yolov2 output.
I have converted yolo.cft & yolo.weights to yolo.h5 which is Keras Model.
Then I run model.predict(img) which gives me output with shape (1, 19, 19, 425).
As far as I know, the interpretation of this shape is:
Image is divided for 19x19 grid cell
425 is 5 x 85 where 5 is number of anchor boxes and 85 is (isObject, Boxx, Boxy, Boxw, Boxh, class1, class2, ..., class80).
But I wonder how can I read this data? Or there is sth to do with output before reading?
For example:
output_data = model.predict(img)
is output_data[0][0][0][0] checking if in box [0, 0] in anchor_box 0 is any object? Then output_data[0][0][0][1:4] is data corelated with bounding box details and output_data[0][0][0][5:85] tells me which class is cougth in box? Are my suspections right or I'm totally wrong?
Thanks in advance
Btw. I've used cfg file form here
python-3.x machine-learning keras computer-vision yolo
python-3.x machine-learning keras computer-vision yolo
asked Nov 14 '18 at 20:25
Patryk KaczmarekPatryk Kaczmarek
63
asked Nov 14 '18 at 20:25
Patryk KaczmarekPatryk Kaczmarek
63
edited Nov 14 '18 at 21:54
Patryk Kaczmarek
asked Nov 14 '18 at 20:25
Patryk KaczmarekPatryk Kaczmarek
63
asked Nov 14 '18 at 20:25
Patryk KaczmarekPatryk Kaczmarek
63
asked Nov 14 '18 at 20:25
Patryk KaczmarekPatryk Kaczmarek
63
63
add a comment |
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%2f53308234%2fyolov2-keras-model-output-interpretation%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%2f53308234%2fyolov2-keras-model-output-interpretation%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
