2018-05-29 14:51:12 -0600 | commented answer | DNN opencv with SSD resnet return wrong face dimension Now is working like a charm. Thanks as always berak, your help is precious. |
2018-05-29 04:03:24 -0600 | commented answer | Unspecified error (Can't create layer "data" of type "Input") in getLayerInstance @dkurt that's a good point. I will try it. |
2018-05-29 03:39:02 -0600 | commented answer | DNN opencv with SSD resnet return wrong face dimension Now is working like a charm. Thanks as always berak, you are help is precious. |
2018-05-29 03:31:59 -0600 | commented answer | DNN opencv with SSD resnet return wrong face dimension Is it not enought to check the last layer of network? Perfect. Make sense. Thought could be a problem, it was not. Ok. |
2018-05-29 03:27:59 -0600 | marked best answer | DNN opencv with SSD resnet return wrong face dimension Hello, I playing with face and DNN but I cannot figure out of to solve an issue. I am processing image 256x256. Using deploy.prototxt and res10_300x300_ssd_iter_140000.caffemodel (same one on dnn directory). Some code. Nothing too exotic, I just write down what I found in What I miss? Can some help to figure out? I have also some questions about this example:
Thanks in advance. |
2018-05-28 19:47:25 -0600 | edited question | DNN opencv with SSD resnet return wrong face dimension DNN opencv with SSD resnet return wrong face dimension Hello, I playing with face and DNN but I cannot figure out of to |
2018-05-28 19:45:21 -0600 | asked a question | DNN opencv with SSD resnet return wrong face dimension DNN opencv with SSD resnet return wrong face dimension Hello, I playing with face and DNN but I cannot figure out of to |
2018-05-28 19:12:32 -0600 | commented question | Compile OpenCV 3.4 and Cuda 9 with MS VS15 2017 As reported here Visual Studio 15.6 is the last one supported for CUDA 9.2. If you want to run (compile etc) CUDA with y |
2018-05-28 16:16:31 -0600 | commented answer | Unspecified error (Can't create layer "data" of type "Input") in getLayerInstance It does not make much sense to be wrong? |
2018-05-28 06:57:42 -0600 | commented answer | Unspecified error (Can't create layer "data" of type "Input") in getLayerInstance @berak Is there no way to use a grayscale image? You suggest to use color images just for dim=3 channels in prototxt? Sw |
2018-05-27 06:07:37 -0600 | commented question | Compile OpenCV 3.4 and Cuda 9 with MS VS15 2017 What version of Visual Studio are you using? 15.6 is the last one supported by CUDA 9.2. P.S.: next time do not put you |
2018-05-27 06:07:24 -0600 | commented question | Compile OpenCV 3.4 and Cuda 9 with MS VS15 2017 What version of Visual Studio are you using? 15.6 is the last one supported by CUDA 9.2. P.S.: next time do not put you |
2018-05-27 06:06:06 -0600 | commented question | Compile OpenCV 3.4 and Cuda 9 with MS VS15 2017 What version of Visual Studio are you using? 15.6 is the last one supported by CUDA 9.2. |
2018-05-07 15:43:36 -0600 | commented question | Grouping images by a person appearing on them Is there something that can discriminate between them? For example, image name. However this is not a question related t |
2018-05-07 10:38:07 -0600 | commented question | Grouping images by a person appearing on them Is there something that can discriminate between them? For example, image name. However this is a question related to Op |
2018-05-07 10:37:09 -0600 | commented question | Grouping images by a person appearing on them Is there something that can discriminate between them? For example, image name. |
2018-05-07 05:35:33 -0600 | received badge | ● Critic (source) |
2018-05-07 05:35:32 -0600 | commented question | how can i upgrade the detection of cv.findContours Add some code and image example. |
2018-05-03 09:07:25 -0600 | edited answer | Edge detection You can try in this way: Apply threholding because you need a binary image. Apply morphological operator: first Open, |
2018-05-03 09:06:16 -0600 | answered a question | Edge detection You can try in this way: Apply threholding because you need a binary image. Apply morphological operator: first Open, |
2018-05-03 06:39:46 -0600 | commented question | I am not able to build my opencv project in eclipse I get it, but how do you install opencv on your machine? Do you compile it or get binary from site? |
2018-05-03 04:26:16 -0600 | received badge | ● Citizen Patrol (source) |
2018-05-03 03:33:21 -0600 | commented question | I am not able to build my opencv project in eclipse How you compile OpenCV? With VC? MinGW? |
2018-05-03 03:17:40 -0600 | edited answer | What is the BGR to YUV and BGR to LAB conversion formula used by OpenCV Have you checked documentaion here https://docs.opencv.org/3.4.1/de/d25/imgproc_color_conversions.html? |
2018-05-02 14:21:30 -0600 | received badge | ● Nice Answer (source) |
2018-05-02 12:54:22 -0600 | received badge | ● Teacher (source) |
2018-05-02 09:44:38 -0600 | commented question | What is the BGR to YUV and BGR to LAB conversion formula used by OpenCV https://docs.opencv.org/3.4.1/de/d25/imgproc_color_conversions.html checked? |
2018-05-02 09:33:59 -0600 | commented question | OpenCV DNN module slower in C++ than in python Well, without any code is difficult to answer, but I guess that OpenCV is not correcly installed, at least in release. H |
2018-04-30 09:41:48 -0600 | commented question | OpenCV DNN module slower in C++ than in python Have you try to switch from Debug mode to Release mode? Do you add AVX, AVX2 or something else? |
2018-04-09 14:54:58 -0600 | marked best answer | BOWKMeansTrainer and features extraction After some months, I start again to do some optimization with my code, but I forgot somethink, I think. I need to perform Bag of Words to clusterize features extracted from images. Let's see some code. Extract features and put them into a vector. Them, I want to clusterize them with BOWKMeansTrainer. Then, preare for bag of words in this way Now I can start bag of words As you can see, in this way, I perform features extraction from image two time: first one with the first loop, and the second one with the last loop (see comments on code), because I need descriptors to clusterize with BOWKMeansTrainer, but I need keypoints to calculate bowDescriptors with BOWImgDescriptorExtractor (matching and so on). My question is: Is this necessary or can I avoid that? I failed something? Can I take from keypoints from somewhere in the last loop without re-detect them? Can I just save keypoints detected in the first loop and then re-use them in the last loop to computer BOWImgDescriptorExtractor? Thanks for your answer. |
2018-04-09 12:37:54 -0600 | commented answer | BOWKMeansTrainer and features extraction So can I use descriptors saved into featuresVector? Seems awesome, did not see this overloading. |
2018-04-07 06:40:47 -0600 | asked a question | BOWKMeansTrainer and features extraction BOWKMeansTrainer and features extraction After some months, I start again to do some optimization with my code, but I fo |
2017-11-13 04:52:47 -0600 | received badge | ● Enthusiast |
2017-11-12 13:51:26 -0600 | commented question | SVM predict on OpenCV: how can I extract the same number of features I tried with LINEAR, but result is not good (around 40%). About the last question: I did no try, but - as a profane - se |
2017-11-12 11:21:45 -0600 | commented question | SVM predict on OpenCV: how can I extract the same number of features Nope, I only try to go with my own solution. I thought you were spurring me in this direction :D. By the way, now just f |
2017-11-12 11:07:08 -0600 | commented question | SVM predict on OpenCV: how can I extract the same number of features Hey @berak, have you seen the last edit of question? I tried to follow your suggestion and for now I am working with dat |
2017-11-12 10:52:25 -0600 | edited question | SVM predict on OpenCV: how can I extract the same number of features SVM predict on OpenCV: how can I extract the same number of features I am play with OpenCV and SVM to make a classifier |
2017-11-12 10:50:01 -0600 | edited question | SVM predict on OpenCV: how can I extract the same number of features SVM predict on OpenCV: how can I extract the same number of features I am play with OpenCV and SVM to make a classifier |
2017-11-12 10:35:21 -0600 | commented question | SVM predict on OpenCV: how can I extract the same number of features Back from work, I have two questions, if you can answer: I need to re-use centers for the unseen images, right? I do n |
2017-11-10 10:32:31 -0600 | commented question | SVM predict on OpenCV: how can I extract the same number of features Back from work, I have two questions, if you can answer: I need to re-use centers for the unseen images, right? I do n |
2017-11-02 13:25:55 -0600 | commented question | SVM predict on OpenCV: how can I extract the same number of features I missed the last comment and I am waiting here from 6 hours, auch. Anyway, I cannot understand why my approach is wrong |
2017-11-02 07:25:28 -0600 | received badge | ● Student (source) |
2017-11-02 06:18:07 -0600 | commented question | SVM predict on OpenCV: how can I extract the same number of features I read it 10 times but I am bit confused. In particular, I am refering to the third point. Okay, I get it. Get it too. |