2019-12-03 05:50:21 -0600 | received badge | ● Famous Question (source) |
2019-01-17 03:19:12 -0600 | received badge | ● Notable Question (source) |
2018-09-07 17:03:43 -0600 | received badge | ● Popular Question (source) |
2018-04-06 06:56:39 -0600 | edited answer | readNetFromTensorflow fails on retrained NN edit: Fixed it it was my error (but the lines below could have some use for others) it was the wrong blob: blob= cv2.dnn |
2018-04-06 06:36:42 -0600 | edited answer | readNetFromTensorflow fails on retrained NN I threw zideks graph into tensorflow and Opencv with the following scripts (some test functions i copy pasted and change |
2018-04-06 05:25:48 -0600 | commented answer | readNetFromTensorflow fails on retrained NN @dkurt looked into his graph and wrote a script in python that takes a picture and gives the output of the detection for |
2018-04-06 05:16:57 -0600 | edited answer | readNetFromTensorflow fails on retrained NN I threw zideks graph into tensorflow and Opencv with the following scripts (some test functions i copy pasted and change |
2018-04-06 05:01:22 -0600 | answered a question | readNetFromTensorflow fails on retrained NN I threw zideks graph into tensorflow and Opencv with the following scripts (some test functions i copy pasted and change |
2018-04-06 04:21:02 -0600 | commented answer | readNetFromTensorflow fails on retrained NN @dkurt looked into his graph and wrote a script in python that takes a picture and gives the output of the detection for |
2018-04-05 04:38:34 -0600 | commented answer | readNetFromTensorflow fails on retrained NN seems tensorflow 1.7 broke retrained nets completely can't even load one trained in 1.7 with tensorflow . Which version |
2018-04-05 03:47:19 -0600 | commented answer | readNetFromTensorflow fails on retrained NN I had the same problems haven't read about someone getting accurate results (compareable to those in Python) with a retr |
2018-01-03 12:22:00 -0600 | edited question | tensorflow retrained graph in 3.3.1 tensorflow retrained graph in 3.3.1 Hi, I still can't seem get a retrained graph working in Opencv it is either not load |
2018-01-03 11:48:50 -0600 | edited question | tensorflow retrained graph in 3.3.1 tensorflow retrained graph in 3.3.1 Hi, I still can't seem get a retrained graph working in Opencv it is either not load |
2018-01-03 11:47:25 -0600 | asked a question | tensorflow retrained graph in 3.3.1 tensorflow retrained graph in 3.3.1 Hi, I still can't seem get a retrained graph working in Opencv it is either not load |
2017-11-10 11:19:52 -0600 | commented answer | SSD_mobileNet displaying N/A 99% Opencv 3.3.0 or 3.3.1? |
2017-11-10 05:33:23 -0600 | commented question | Fail to compile OPENCV 3.3.1 LIB windows ARM with VC15 I gave up doing it on windows, too many small problems on all ends. I would try it on ubuntu. |
2017-11-08 04:07:29 -0600 | edited question | Make a NN work in 3.3.0 out of Tensorflow Make a NN work in 3.3.0 out of Tensorflow Hi, I already verified that the retrained NN (Tensorflow retrain script) are w |
2017-11-08 03:09:50 -0600 | asked a question | Make a NN work in 3.3.0 out of Tensorflow Make a NN work in 3.3.0 out of Tensorflow Hi, I already verified that the retrained NN (Tensorflow retrain script) are w |
2017-11-06 10:07:53 -0600 | commented answer | readNetFromTensorflow fails on retrained NN @Adez take that back i have no idea what it is @dkurt Installed 3.3.1 on ubuntu in VM and i can load it there and it see |
2017-11-06 08:45:43 -0600 | commented answer | readNetFromTensorflow fails on retrained NN @Adez take that back i have no idea what it is @dkurt Installed 3.3.1 on ubuntu in VM and i can load it there and it see |
2017-11-06 07:00:00 -0600 | commented answer | readNetFromTensorflow fails on retrained NN @Adez my guess would be the labels.txt ? @dkurt has the net revealed anything to you? |
2017-11-02 09:14:12 -0600 | commented answer | readNetFromTensorflow fails on retrained NN @dkurt of course upload: link text . That script however sadly throws a utf8 error ? \tensorflow\python\util\compat. |
2017-11-02 08:01:26 -0600 | commented answer | readNetFromTensorflow fails on retrained NN @dkurt Could it have anything to do with me training it with cuda (extra transform or inference needed?) |
2017-11-01 12:14:41 -0600 | commented answer | readNetFromTensorflow fails on retrained NN @dkurt I meant i created a "new" retrained net with exactly your commands and it throws the error, i posted a few minute |
2017-11-01 11:55:20 -0600 | commented answer | readNetFromTensorflow fails on retrained NN @dkurt First thanks again for your time. I had to retrain another net. I just tried too much stuff the last few days and |
2017-11-01 08:55:37 -0600 | commented answer | readNetFromTensorflow fails on retrained NN @dkurt Not in tf yet, i only tried to load it there (was loaded) in OpenCv, in python, it throws on net.Forward() = err |
2017-11-01 08:52:05 -0600 | commented answer | readNetFromTensorflow fails on retrained NN @dkurt Not in tf yet, i only tried to load it there (was loaded) in OpenCv, in python, it throws \opencv-3.3.0\modules\ |
2017-11-01 07:48:10 -0600 | commented answer | readNetFromTensorflow fails on retrained NN @dkurt I could load the retrained graph after doing everything exactly as described, but it seems to be empty? It is not |
2017-11-01 05:02:43 -0600 | commented answer | readNetFromTensorflow fails on retrained NN I could load the retrained graph after doing everything exactly as described, but it seems to be empty? It is not return |
2017-10-22 03:03:08 -0600 | received badge | ● Nice Question (source) |
2017-10-12 07:15:31 -0600 | marked best answer | OpenCV_CreateSamples and Training can't read negatives.txt OS: WIN 64 (German verison) BUILD In 32 around 3229 positives, 3000 negatives, all pos. are 24x24, all neg. are of different, larger resolutions (640x480 and bigger) It seems it can't open the negatives.txt i created. positives.txt looks like: negatives.txt (=neg.txt) looks like: also tried it with full path and without the "./" (no difference and it works with the positives). Converting negatives.txt to Ansi or UTF-8 without BOM hasn't helped either. If i understood it correctly, he should place images randomly into one of the background images i have in my negatives.txt. only shows positives shows nothing and crashes with Also i tried to build a training.vec with the negatives just to see if it will show something there. Trying to have a look into it "-show" does not return anything. Creating samples with only positives works flawless but the training will crash with different errors and is way too fast. Examples |
2017-10-12 07:15:31 -0600 | received badge | ● Scholar (source) |
2017-10-06 11:42:17 -0600 | marked best answer | readNetFromTensorflow fails on retrained NN Hi, I hope someone can help me. My plan is to train a CNN in Tensorflow and use it in a app that uses OpenCV3.3 . For testing purposes i used the retrain script delivered with Tensorflow and expanded it (Inception V3) with the Flowers. (their Tutorial https://www.tensorflow.org/tutorials/...) I trained two models with it (one mobile the other just a normal one) The resulting graph can be used in Tensorflow, but it fails to load in Opencv (Python, OpencCv 3.3, Win 7 64 ). The script does not create any Checkpoints so i can't freeze the graph (is it Frozen and can ich check this?) But i used the optimize_for_intereference to remove jpeg decoding. When i try to load those graphs in OpenCV it throws the following errors: mobile version: "...tensorflow\tf_importer.cpp:465: error: (-2) More than one input is Const op in function cv::dnn::experimental_dnn_v1::`anonymous-namespace'::TFImporter::getConstBlob" non mobile: "tensorflow\tf_importer.cpp:447: error: (-2) Input layer not found: conv/batchnorm in function cv::dnn::experimental_dnn_v1::`anonymous-namespace'::TFImporter::connect" Thanks for any help in advance ;-) |