Run Mask RCNN (matterport) trained model in C++ TensorFlow API. But SAME WRONG values in results

up vote
0
down vote

favorite

Use following lines, I could get my output_detections and output_mrcnn_mask

tensorflow::Status run_status = session->Run({ { "input_image", inputTensor },{ "input_image_meta", inputMetadataTensor },{"input_anchors",input_anchors } },

        { "output_detections", "output_mrcnn_class", "output_mrcnn_bbox", "output_mrcnn_mask",

                "output_rois", "output_rpn_class", "output_rpn_bbox" },

        {},

        &outputs);



auto detectionsMap = outputs[0].tensor<float, 3>();

auto y1 = detectionsMap(0, i, 0); float x1 = detectionsMap(0, i, 1); auto y2 = detectionsMap(0, i, 2); float x2 = detectionsMap(0, i, 3) ;

But I always get the following results, no matter which image I have input.

x1 = x2 = 1.00392

I have tried infering with the pb file in Python. The result is the same with the result of C++ except for x1 and x2.

Environment:

Windows 10

Visual Studio 2015

Python 3.5

TensorFlow 1.4.0 in Python and C++

PS: I build TensorFlow for Visual Studio using:
(Build a Tensorflow C++ Library)

Does anyone have any idea to fix this problem? Thanks!!!!

edited Nov 15 at 2:12

asked Nov 13 at 3:20

Peter Zeng

add a comment |

up vote
0
down vote

favorite

Use following lines, I could get my output_detections and output_mrcnn_mask

tensorflow::Status run_status = session->Run({ { "input_image", inputTensor },{ "input_image_meta", inputMetadataTensor },{"input_anchors",input_anchors } },

        { "output_detections", "output_mrcnn_class", "output_mrcnn_bbox", "output_mrcnn_mask",

                "output_rois", "output_rpn_class", "output_rpn_bbox" },

        {},

        &outputs);



auto detectionsMap = outputs[0].tensor<float, 3>();

auto y1 = detectionsMap(0, i, 0); float x1 = detectionsMap(0, i, 1); auto y2 = detectionsMap(0, i, 2); float x2 = detectionsMap(0, i, 3) ;

But I always get the following results, no matter which image I have input.

x1 = x2 = 1.00392

I have tried infering with the pb file in Python. The result is the same with the result of C++ except for x1 and x2.

Environment:

Windows 10

Visual Studio 2015

Python 3.5

TensorFlow 1.4.0 in Python and C++

PS: I build TensorFlow for Visual Studio using:
(Build a Tensorflow C++ Library)

Does anyone have any idea to fix this problem? Thanks!!!!

edited Nov 15 at 2:12

asked Nov 13 at 3:20

Peter Zeng

add a comment |

up vote
0
down vote

favorite

Use following lines, I could get my output_detections and output_mrcnn_mask

tensorflow::Status run_status = session->Run({ { "input_image", inputTensor },{ "input_image_meta", inputMetadataTensor },{"input_anchors",input_anchors } },

        { "output_detections", "output_mrcnn_class", "output_mrcnn_bbox", "output_mrcnn_mask",

                "output_rois", "output_rpn_class", "output_rpn_bbox" },

        {},

        &outputs);



auto detectionsMap = outputs[0].tensor<float, 3>();

auto y1 = detectionsMap(0, i, 0); float x1 = detectionsMap(0, i, 1); auto y2 = detectionsMap(0, i, 2); float x2 = detectionsMap(0, i, 3) ;

But I always get the following results, no matter which image I have input.

x1 = x2 = 1.00392

I have tried infering with the pb file in Python. The result is the same with the result of C++ except for x1 and x2.

Environment:

Windows 10

Visual Studio 2015

Python 3.5

TensorFlow 1.4.0 in Python and C++

PS: I build TensorFlow for Visual Studio using:
(Build a Tensorflow C++ Library)

Does anyone have any idea to fix this problem? Thanks!!!!

edited Nov 15 at 2:12

asked Nov 13 at 3:20

Peter Zeng

Use following lines, I could get my output_detections and output_mrcnn_mask

tensorflow::Status run_status = session->Run({ { "input_image", inputTensor },{ "input_image_meta", inputMetadataTensor },{"input_anchors",input_anchors } },

        { "output_detections", "output_mrcnn_class", "output_mrcnn_bbox", "output_mrcnn_mask",

                "output_rois", "output_rpn_class", "output_rpn_bbox" },

        {},

        &outputs);



auto detectionsMap = outputs[0].tensor<float, 3>();

auto y1 = detectionsMap(0, i, 0); float x1 = detectionsMap(0, i, 1); auto y2 = detectionsMap(0, i, 2); float x2 = detectionsMap(0, i, 3) ;

But I always get the following results, no matter which image I have input.

x1 = x2 = 1.00392

I have tried infering with the pb file in Python. The result is the same with the result of C++ except for x1 and x2.

Environment:

Windows 10

Visual Studio 2015

Python 3.5

TensorFlow 1.4.0 in Python and C++

PS: I build TensorFlow for Visual Studio using:
(Build a Tensorflow C++ Library)

Does anyone have any idea to fix this problem? Thanks!!!!

python c++ tensorflow deep-learning computer-vision

edited Nov 15 at 2:12

asked Nov 13 at 3:20

Peter Zeng

edited Nov 15 at 2:12

asked Nov 13 at 3:20

Peter Zeng

edited Nov 15 at 2:12

asked Nov 13 at 3:20

Peter Zeng

asked Nov 13 at 3:20

Peter Zeng

asked Nov 13 at 3:20

Peter Zeng

add a comment |

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',
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');
});

Post as a guest

Name

Required, but never shown

StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53273306%2frun-mask-rcnn-matterport-trained-model-in-c-tensorflow-api-but-same-wrong-v%23new-answer', 'question_page');
}
);

Post as a guest

Name

Required, but never shown

active

oldest

votes

draft saved

draft discarded

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Post as a guest

Name

Required, but never shown

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Name

Required, but never shown

Name

Required, but never shown

This page is only for reference, If you need detailed information, please check here

搜尋此網誌

Cfrgtkky