2017-12-21 06:46:01 -0600 | marked best answer | (DNN) different results between version 3.3.0 and 3.3.1 System information (version) OpenCV => 3.3.0/3.3.1 Operating System / Platform => Windows 10 64 Bit Compiler => Visual Studio 2015 Detailed description I have a network that works fine in Opencv 3.3.0, but after updating my opencv to the version 3.3.1 I'm getting wrong results with the same code. What I already tried: *Compile on Linux -> I got the same wrong results *Compile on windows with Mingw -> I got the same wrong results *Compile on windows with Visual Studio 14 x32 -> I got the same wrong results *Compile the master brach of opencv on windows with Visual Studio 14 x32 -> I got the same wrong results Complementar tests: I used the "tensorflow_inception_graph.pb" network, with this network I got the same results in version 3.3.0 and 3.3.1, I do not know if it is a correct predictions. Using the caffe model network from the opencv examples worked as well with correct prediction for both versions. Maybe my problem is my network, but why my network works on opencv 3.3.0 and dont work on 3.3.1? Steps to reproduce NetworkInput: 1x1x28x92 (grayscale image) Normalization: 0..1 The same code is used in opencv 3.3.0 and 3.3.1 my network you can find here (more) |
2017-12-21 06:46:01 -0600 | received badge | ● Scholar (source) |
2017-12-21 06:45:41 -0600 | commented answer | (DNN) different results between version 3.3.0 and 3.3.1 @dkurt, thanks a lot, your modifications will help me a lot |
2017-12-21 06:44:00 -0600 | commented answer | (DNN) different results between version 3.3.0 and 3.3.1 @dkurt, I tested what did you said. First I downloaded the last version of opencv-master and replaced with your files Te |
2017-12-21 04:48:14 -0600 | commented question | (DNN) different results between version 3.3.0 and 3.3.1 I create my batchs doing something like this: im=cv2.imread("example.jpg",0) #It will load in grayscale im=im/255.0 #sc |
2017-12-21 04:14:19 -0600 | received badge | ● Enthusiast |
2017-12-20 12:46:50 -0600 | commented answer | (DNN) different results between version 3.3.0 and 3.3.1 for sure, I will test it tomorrow morning and I post the results here |
2017-12-20 12:45:43 -0600 | commented question | (DNN) different results between version 3.3.0 and 3.3.1 I create my batchs doing something like this: im=cv2.imread("example.jpg",0) #It will load in grayscale im=im/255.0 #sc |
2017-12-19 10:28:50 -0600 | answered a question | (DNN) different results between version 3.3.0 and 3.3.1 Thank you so much Dkurt, I would never found this answer by myself. I will test as soon as possible, thank you |
2017-12-15 06:14:15 -0600 | asked a question | (DNN) different results between version 3.3.0 and 3.3.1 (DNN) different results between version 3.3.0 and 3.3.1 System information (version) OpenCV => 3.3.0/3.3.1 Operatin |
2017-11-13 08:53:54 -0600 | answered a question | (dnn/tensorflow) Very different results tf X dnn here it is the problem: #9177 |
2017-11-09 11:01:43 -0600 | asked a question | (dnn/tensorflow) Very different results tf X dnn (dnn/tensorflow) Very different results tf X dnn Hello, I created a keras model and converted to tensorflow, I had some |