2018-05-10 04:22:28 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection @dkurt, yes, it works now. Thanks! |
2018-05-10 01:32:22 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection @dkurt. Thanks, I got it! I have checked the difference between "cvOut" and "out". The difference is little. One more qu |
2018-05-10 01:30:55 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection @dkurt. Thanks, I got it! I have checked the difference between "cvOut" and "out". The difference is little. One more qu |
2018-05-10 01:26:14 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection @dkurt. Thanks, I got it! I have checked the difference between "cvOut" and "out". The difference is little. One more qu |
2018-05-10 01:22:39 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection @dkurt. Thanks, I see. I have checked the difference between "cvOut" and "out". The difference is little. One more quest |
2018-05-08 04:45:08 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection Hi @dkurt, A question. In the answer your provided above, in the step7 : check an accuracy. you compare "out" and "cvOu |
2018-05-08 04:43:36 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection Hi @dkurt, A question. In the answer your provided above, in the step7 : check an accuracy. you compare "out" and "cvOu |
2018-05-08 04:31:25 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection Hi @dkurt, One question. In the answer your provided above, the step : check an accuracy. you compare "out" and "cvOut" |
2018-05-01 20:13:48 -0600 | commented question | How to estimate a face's age/gender using cv::dnn APIs Hi, @StevenPuttemans @dkurt, Any suggestion on this? thanks |
2018-04-26 04:17:57 -0600 | commented question | How to estimate a face's age/gender using cv::dnn APIs They run fine. The result is 1 by 2 matrix, and I suppose 1st element is age and 2nd element is gender. However, the ans |
2018-04-26 04:16:28 -0600 | commented question | How to estimate a face's age/gender using cv::dnn APIs They run fine. The result is 1 by 2 matrix, and I suppose 1st element is age and 2nd element is gender. However, the ans |
2018-04-26 04:07:51 -0600 | commented question | How to estimate a face's age/gender using cv::dnn APIs OK, let me explain in more detail.. I am using DLib to detect the face and facial landmarks then I can crop and normalis |
2018-04-26 04:07:15 -0600 | commented question | How to estimate a face's age/gender using cv::dnn APIs OK, let me explain in more detail.. I am using DLib to detect the face and facial landmarks then I can crop and normalis |
2018-04-26 04:05:32 -0600 | commented question | How to estimate a face's age/gender using cv::dnn APIs OK, let me explain in more detail.. I am using DLib to detect the face and facial landmarks then I can crop and normalis |
2018-04-23 04:32:18 -0600 | asked a question | How to estimate a face's age/gender using cv::dnn APIs How to estimate a face's age/gender using cv::dnn APIs Hi, OpenCV developer, This is a subsequent question from http:/ |
2018-04-23 03:51:47 -0600 | marked best answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection Dear opencv dnn developers, [Environment] TensorFlow 1.5 python 3.5 Win7 opencv3.4 I am very new to the Tensor flow. Recently I found a pretrained dnn for age gender detection https://github.com/BoyuanJiang/Age-Gender-Estimate-TF. The model is defined in "inception_resnet_v1.py" and the latest model checkpoints can be found https://mega.nz/#!kaZkWDjb!xQvWi9B--FgyIPtIYfjzLDoJeh2PUBEZPotmzO9N6_M I loaded model with the latest check point into Tensor Flow and running detection ok, and managed to freeze the graph using freeze_graph.py but when I load this frozen graph by cv::dnn::readNetFromTensorflow("XXX.pb"), it gets error:..."Unknown layer type shape in op map/Shape)".... or I tried cv::dnn::readNetFromTensorflow("XXX.pb", "XXX.pbtxt"), it also gets error:...unknown enumeration values of "DT_RESOURCE" for field "type..." I have searched over the internet trying to find a solution... someone suggested using "optimize_for_inference" or "graph_transform" might help. As I have limited Tensor Flow knowledge, I do not understand how these two processes can solve the problem. and Also, cv::dnn::readNetFromTensorflow() method has the 2nd argument, which I also do not know in what situation I should/should not provide a .pbtxt for it? Please help. If there is any further information needed to clarify the question, just let me know and I will supply. Thanks in advance |
2018-04-23 03:51:47 -0600 | received badge | ● Scholar (source) |
2018-04-19 04:27:19 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection @dkurt, They run fine. The result is 1 by 2 matrix, and I suppose 1st element is age and 2nd element is gender. However, |
2018-04-19 04:05:58 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection @dkurt Now, here is the problem of my next step. I am using DLib to detect the face and facial landmarks thus I can crop |
2018-04-19 03:51:35 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection @dkurt Thanks for your suggestion. I use frozenGraph_ageGender.pb and frozen_inception_resnet_v1.pbtxt(download from you |
2018-04-19 03:51:04 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection @dkurt Thanks for your suggestion. I use frozenGraph_ageGender.pb and frozen_inception_resnet_v1.pbtxt(download from you |
2018-04-19 03:49:33 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection @dkurt Thanks for your suggestion. I use frozenGraph_ageGender.pb and frozen_inception_resnet_v1.pbtxt(download from you |
2018-03-31 04:01:13 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection @dkurt, I just updated from opencv3.4 to opencv3.4.1. However, the same Assertion fail still occurs. Any other suggestio |
2018-03-31 02:28:43 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection @dkurt, what do you exactly mean here? do you mean I go and comment out the Assertion failed(size==(int)dstBlob.total()) |
2018-03-30 22:38:31 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection @dkurt Thank you for your help. Just downloaded the "frozen_inception_resnet_v1.pbtxt" you provided and tried in my VS20 |
2018-03-29 23:01:41 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection @dkurt Upload the latest frozenGraph_agedGender.pbhttps://www.dropbox.com/s/h4vqsj4eu1ksmbm/frozenGraph_ageGender.pb?dl |
2018-03-29 22:59:09 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection @dkurt, after setting all "phase_train" and "is_training" flags equal to false, I ran tf.train.write_graph(...) and cal |
2018-03-28 20:29:37 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection yes, It has been done at line 76 convertGraphToPb.py ages, genders = sess.run([age, gender], feed_dict={images_pl: ali |
2018-03-18 22:50:09 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection Hi @dkurt, I have checked the cod and, to the best of my knowledge, there should not be any "isTraining==True" existed |
2018-03-15 20:22:51 -0600 | commented answer | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection Hi @dkurt, Thank you for your suggestion. I was switched to another project now, but will come back to this issue and t |
2018-03-13 21:40:15 -0600 | received badge | ● Enthusiast |
2018-03-12 20:37:08 -0600 | commented question | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection Hi @dkurt, is there any luck to fix this problem...? Everyone, any suggestions will be appreciated... Thank you |
2018-03-05 23:33:51 -0600 | commented question | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection Hi, dkurt, Thank you for your reply. The detail of getting the frozen graph is described below... ..... after loading t |
2018-03-05 23:32:43 -0600 | commented question | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection Hi, dkurt, Thank you for your reply. The detail of getting the frozen graph is described below... ..... after loading t |
2018-03-05 23:31:43 -0600 | commented question | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection then a frozenGraph.pb is generated. Here you can download my generated "graphDef.pb" "graphDef.pbtxt" and "frozenGraph |
2018-03-05 23:30:07 -0600 | commented question | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection then a frozenGraph.pb is generated. Here you can download my generated "graphDef.pb" "graphDef.pbtxt" and "frozenGraph |
2018-03-05 23:28:40 -0600 | commented question | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection Hi, dkurt, Thank you for your reply. The detail of getting the frozen graph is described below... ..... after loading t |
2018-03-04 23:01:43 -0600 | asked a question | dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection dnn::readNetFromTensorflow() fail on loading pre-trained network on age-gender detection Dear opencv dnn developers, [ |