Ask Your Question

Revision history [back]

click to hide/show revision 1
initial version

conversion working but wrong output :-(

result from opencv c++ read

daisy 9.26857e-06 dandelion 0.000130691 roses 0.99399 sun0.00144483 tul0.00442559

used function -> Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false);

result from standard label function from tensorflow for tulip image is OK tulips 0.9127952 roses 0.0797129 sunflowers 0.0060887286 daisy 0.0010076686 dandelion 0.00039551986

conversion working but wrong output :-(

result from opencv c++ read

daisy 9.26857e-06 dandelion 0.000130691 roses 0.99399 sun0.00144483 tul0.00442559

used function -> Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false);

result from standard label function from tensorflow for tulip image is OK tulips 0.9127952 roses 0.0797129 sunflowers 0.0060887286 daisy 0.0010076686 dandelion 0.00039551986

maybee is something wrong with read blob I use modified googlenet c++ source, I only changed resolution from 224,244 to 299, 299.

Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false); //Convert Mat to batch
inputBlob -= 117.0; //! [Set input blob] net.setInput(inputBlob, inBlobName); //set the network input

conversion working but wrong output :-(

result from opencv c++ read

daisy 9.26857e-06 dandelion 0.000130691 roses 0.99399 sun0.00144483 tul0.00442559

used function -> Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false);

result from standard label function from tensorflow for tulip image is OK tulips 0.9127952 roses 0.0797129 sunflowers 0.0060887286 daisy 0.0010076686 dandelion 0.00039551986

maybee is something wrong with read blob I use modified googlenet c++ source, I only changed resolution from 224,244 to 299, 299.

Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false); //Convert Mat to batch
inputBlob -= 117.0; //! [Set input blob] net.setInput(inputBlob, inBlobName); //set the network input

conversion working but wrong output :-(

result from opencv c++ read

daisy 9.26857e-06 dandelion 0.000130691 roses 0.99399 sun0.00144483 tul0.00442559

used function -> Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false);

result from standard label function from tensorflow for tulip image is OK tulips 0.9127952 roses 0.0797129 sunflowers 0.0060887286 daisy 0.0010076686 dandelion 0.00039551986

maybee is something wrong with read blob I use modified googlenet c++ source, I only changed resolution from 224,244 to 299, 299.

Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false); //Convert Mat to batch
inputBlob -= 117.0; //! [Set input blob] net.setInput(inputBlob, inBlobName); //set the network inputC:\fakepath\tulip.jpg

conversion working but wrong output :-(

result from opencv c++ read

daisy 9.26857e-06 dandelion 0.000130691 roses 0.99399 sun0.00144483 tul0.00442559

used function -> Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false);

result from standard label function from tensorflow for tulip image is OK tulips 0.9127952 roses 0.0797129 sunflowers 0.0060887286 daisy 0.0010076686 dandelion 0.00039551986

maybee is something wrong with read blob I use modified googlenet c++ source, I only changed resolution from 224,244 to 299, 299.

Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false); //Convert Mat to batch
inputBlob -= 117.0; //! [Set input blob] net.setInput(inputBlob, inBlobName); //set the network input

files used if you want to reproduce, this error:

C:\fakepath\tulip.jpg

http://193.87.95.129/inf_predn/final_graph.pb

conversion working but wrong output :-(

result from opencv c++ read

daisy 9.26857e-06 dandelion 0.000130691 roses 0.99399 sun0.00144483 tul0.00442559

used function -> Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false);

result from standard label function from tensorflow for tulip image is OK tulips 0.9127952 roses 0.0797129 sunflowers 0.0060887286 daisy 0.0010076686 dandelion 0.00039551986

maybee is something wrong with read blob I use modified googlenet c++ source, I only changed resolution from 224,244 to 299, 299.

Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false); //Convert Mat to batch
inputBlob -= 117.0; //! [Set input blob] net.setInput(inputBlob, inBlobName); //set the network input

files used if you want to reproduce, this error:

error: input image C:\fakepath\tulip.jpg

optimized and trasformed model http://193.87.95.129/inf_predn/final_graph.pb

c++ example http://193.87.95.129/inf_predn/opencv.cpp

conversion working but wrong output :-(

result from opencv c++ read

daisy 9.26857e-06 dandelion 0.000130691 roses 0.99399 sun0.00144483 tul0.00442559

used function -> Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false);

result from standard label function from tensorflow for tulip image is OK tulips 0.9127952 roses 0.0797129 sunflowers 0.0060887286 daisy 0.0010076686 dandelion 0.00039551986

maybee is something wrong with read blob I use modified googlenet c++ source, I only changed resolution from 224,244 to 299, 299.

Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false); //Convert Mat to batch
inputBlob -= 117.0; //! [Set input blob] net.setInput(inputBlob, inBlobName); //set the network input

files used if you want to reproduce, this error: input image C:\fakepath\tulip.jpg

optimized and trasformed model http://193.87.95.129/inf_predn/final_graph.pb

c++ example http://193.87.95.129/inf_predn/opencv.cpp

used tensorflow 1.7 gpu gtx 1050 for retrain

conversion working but wrong output :-(

result from opencv c++ read

daisy 9.26857e-06 dandelion 0.000130691 roses 0.99399 sun0.00144483 tul0.00442559

used function -> Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false);

result from standard label function from tensorflow for tulip image is OK tulips 0.9127952 roses 0.0797129 sunflowers 0.0060887286 daisy 0.0010076686 dandelion 0.00039551986

maybee is something wrong with read blob I use modified googlenet c++ source, I only changed resolution from 224,244 to 299, 299.

Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false); //Convert Mat to batch
inputBlob -= 117.0; //! [Set input blob] net.setInput(inputBlob, inBlobName); //set the network input

files used if you want to reproduce, this error: input image C:\fakepath\tulip.jpg

optimized and trasformed model http://193.87.95.129/inf_predn/final_graph.pb

c++ example http://193.87.95.129/inf_predn/opencv.cpp

retrained model output_graph.ph is OK but optimized and transformed graph final_graph not working good in C++ opencv

used tensorflow 1.7 gpu gtx 1050 for retrain

conversion working but wrong output :-(

result from opencv c++ read

daisy 9.26857e-06 dandelion 0.000130691 roses 0.99399 sun0.00144483 tul0.00442559

used function -> Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false);

result from standard label function from tensorflow for tulip image is OK tulips 0.9127952 roses 0.0797129 sunflowers 0.0060887286 daisy 0.0010076686 dandelion 0.00039551986

maybee is something wrong with read blob I use modified googlenet c++ source, I only changed resolution from 224,244 to 299, 299.

Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false); //Convert Mat to batch
inputBlob -= 117.0; //! [Set input blob] net.setInput(inputBlob, inBlobName); //set the network input

files used if you want to reproduce, this error: input image C:\fakepath\tulip.jpg

optimized and trasformed model http://193.87.95.129/inf_predn/final_graph.pb

c++ example http://193.87.95.129/inf_predn/opencv.cpp

retrained model output_graph.ph output_graph.pb is OK but optimized and transformed graph final_graph not working good in C++ opencvpython_label tested retrained model final_graph.pb is OK python_label tested some problem to reading model by C++?

used tensorflow 1.7 gpu gtx 1050 for retrain

conversion working but wrong output from C++ opencv :-(

result from opencv c++ read

daisy 9.26857e-06 dandelion 0.000130691 roses 0.99399 sun0.00144483 tul0.00442559

used function -> Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false);

result from standard label function from tensorflow for tulip image is OK tulips 0.9127952 roses 0.0797129 sunflowers 0.0060887286 daisy 0.0010076686 dandelion 0.00039551986

maybee is something wrong with read blob I use modified googlenet c++ source, I only changed resolution from 224,244 to 299, 299.

Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false); //Convert Mat to batch
inputBlob -= 117.0; //! [Set input blob] net.setInput(inputBlob, inBlobName); //set the network input

files used if you want to reproduce, this error: input image C:\fakepath\tulip.jpg

optimized and trasformed model http://193.87.95.129/inf_predn/final_graph.pb

c++ example http://193.87.95.129/inf_predn/opencv.cpp

retrained -retrained model output_graph.pb is OK python_label tested retrained -retrained model final_graph.pb is OK python_label tested some problem to reading model by C++?

used tensorflow 1.7 gpu gtx 1050 for retrain

conversion working but wrong cca lower accurency 20% down output from C++ opencv :-(

result from opencv c++ read

daisy 9.26857e-06 dandelion 0.000130691 Probability: 75.1135% daisy6.75558e-06,dan0.000468269,ros0.2483,sun9.00434e-05,roses 0.99399tul0.751135 sun0.00144483 tul0.00442559

used function -> Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false);

result from standard label function from tensorflow for tulip image is OK tulips 0.9127952 roses 0.0797129 sunflowers 0.0060887286 daisy 0.0010076686 dandelion 0.00039551986

maybee is something wrong with read blob I use modified googlenet c++ source, I only changed resolution from 224,244 to 299, 299.

Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false); //Convert Mat to batch
inputBlob -= 117.0; //! [Set input blob] net.setInput(inputBlob, inBlobName); //set the network input

files used if you want to reproduce, this error: input image C:\fakepath\tulip.jpg

optimized and trasformed model http://193.87.95.129/inf_predn/final_graph.pb

c++ example http://193.87.95.129/inf_predn/opencv.cpp

-retrained model output_graph.pb is OK python_label tested -retrained model final_graph.pb is OK python_label tested some problem to reading model by C++?C++ with same precission?

used tensorflow 1.7 gpu gtx 1050 for retrain

conversion working but wrong cca lower accurency 20% down output from C++ opencv :-(

result from opencv c++ read

Probability: 75.1135% daisy6.75558e-06,dan0.000468269,ros0.2483,sun9.00434e-05,tul0.751135

result from standard label function from tensorflow for tulip image is OK tulips 0.9127952 roses 0.0797129 sunflowers 0.0060887286 daisy 0.0010076686 dandelion 0.00039551986

maybee is something wrong with read blob I use modified googlenet c++ source, I only changed resolution from 224,244 to 299, 299.

Mat inputBlob = blobFromImage(img, 1.0f, Size(299, 299), Scalar(), true, false); //Convert Mat to batch
inputBlob -= 117.0; //! [Set input blob] net.setInput(inputBlob, inBlobName); //set the network input

files used if you want to reproduce, this error: input image C:\fakepath\tulip.jpg

optimized and trasformed model http://193.87.95.129/inf_predn/final_graph.pb

c++ example http://193.87.95.129/inf_predn/opencv.cpp

-retrained model output_graph.pb is OK python_label tested -retrained model final_graph.pb is OK python_label tested some problem to reading model by C++ with same precission?

used tensorflow 1.7 gpu gtx 1050 for retrain