This forum is disabled, please visit https://forum.opencv.org

2020-03-11 12:11:40 -0600 | received badge | ● Popular Question (source) |

2018-11-05 10:38:59 -0600 | marked best answer | How should a tensorflow model be saved so that it can be loaded in opencv3.3.1 Hi, I am using Tensorflow to train a neural network ( The neural network doesn't contain any variables ). This is my neural network graph in Tensorflow. I wanted to know how this graph should be saved in tensorflow so as to load it using readNetFromTensorflow |

2018-07-08 05:25:10 -0600 | asked a question | Does having a tf.nn.dropout layer in a tensorflow frozen graph affect dnn::forward Does having a tf.nn.dropout layer in a tensorflow frozen graph affect dnn::forward I wanted to know if frozen tensorflow |

2018-06-01 09:57:17 -0600 | asked a question | How to infer stride, padding information of a convolution layer after importing from a frozen graph (readNetFromTensorFlow) How to infer stride, padding information of a convolution layer after importing from a frozen graph (readNetFromTensorFl |

2018-05-17 04:24:47 -0600 | asked a question | Is it possible to use GPU for forward pass of a tensorflow model in opencv 3.4.1 dnn Is it possible to use GPU for forward pass of a tensorflow model in opencv 3.4.1 dnn Was trying to find a GPU implementa |

2018-05-17 04:12:54 -0600 | received badge | ● Enthusiast |

2018-04-13 07:13:09 -0600 | received badge | ● Student (source) |

2018-04-10 07:06:16 -0600 | marked best answer | How to import a tensorflow model with dropout in opencv Hi, I tried using the advice here -> https://github.com/opencv/opencv/issu.... Saving the checkpoint with dropout and saving the graph without dropout. Here is the issue that I face, along with the name of all the layers read by OpenCV 3.4.1:
Here is my tensorflow code ->https://pastebin.com/mMgRbHV0 ( Commented lines are uncommented and the lines corresponding to uncommented pool1, pool2 and saver.save is commented for saving graph without dropout ). Then I run the following commands to freeze the graph. python freeze_graph.py --input_graph=./input_graph.pb --input_checkpoint=./with_dropout.ckpt --output_graph=./output_graph.pb --output_node=Dense2/output_node followed by python optimize_for_inference.py --input output_graph.pb --output without_dropout.pb --frozen_graph True --input_names input_node --output_names Dense2/output_node and then I try to load the "without_dropout.pb" with OpenCV where I face the issue. |

2018-04-10 05:40:44 -0600 | commented answer | How to import a tensorflow model with dropout in opencv Sorry for wasting your time .... it turns out that I was using the wrong image size .... should I remove this question a |

2018-04-10 04:44:26 -0600 | commented question | How to import a tensorflow model with dropout in opencv Sorry for the mistake .... the input size is [NONE, 250, 250, 1] |

2018-04-10 03:36:53 -0600 | commented question | How to import a tensorflow model with dropout in opencv [NONE, 125, 125, 1] |

2018-04-10 03:09:02 -0600 | commented question | How to import a tensorflow model with dropout in opencv https://drive.google.com/file/d/1fIppXXv_FJEiWKP79xJ92ar0uFO_1iFj/view?usp=sharing |

2018-04-09 09:42:02 -0600 | asked a question | How to import a tensorflow model with dropout in opencv How to import a tensorflow model with dropout in opencv Hi, I tried using the advice here -> https://github.com/openc |

2018-04-03 09:05:34 -0600 | commented answer | Running tensorflow graph through OpenCV gives different result Should I close this question then .... since its an issue of using the latest version?? |

2018-04-03 08:45:39 -0600 | commented answer | Running tensorflow graph through OpenCV gives different result What version should I use ... 3.3 or 3.4 ?? |

2018-04-03 08:41:41 -0600 | commented answer | Running tensorflow graph through OpenCV gives different result Ohh .... thank you for the response :) .... will update OpenCV then. |

2018-04-03 08:18:33 -0600 | commented answer | Running tensorflow graph through OpenCV gives different result @dkurt .... here is the link -> https://drive.google.com/drive/folders/16nWtIdXJ4hjBJLBO3FABKZScfwXCyoRz?usp=sharing |

2018-04-03 07:49:04 -0600 | commented answer | Running tensorflow graph through OpenCV gives different result @dkurt ... its not working ... I checked the model midway and saw the values improved and thought that the problem got s |

2018-04-03 07:46:57 -0600 | received badge | ● Critic (source) |

2018-04-03 05:15:57 -0600 | commented answer | Running tensorflow graph through OpenCV gives different result Your answer solved it ..... initially I was saving using freeze_graph.py from tensorflow .... I saved the model as an in |

2018-04-03 05:07:47 -0600 | marked best answer | Running tensorflow graph through OpenCV gives different result I am trying to run an single channel image of size = ( 125, 125 ) through a frozen tensorflow graph. The result that I am expecting is a vector which is close to [ 125, 131, 203, 203 ]. My Tensorflow Graph is as follows -> https://pastebin.com/tDw3kTWw OpenCV code that I am using for running the graph:
The result that I get using OpenCV forward pass is [47.357735, 49.290573, 81.015984, 87.777328]. This is the Tensorflow code that I am using to run the forward pass:
The result that I am getting with tensorflow is relatively quite closer to the actual answer i.e. [[ 139.59773254 135.82391357 217.75576782 214.71946716]]. I am confused as to why there are separate results for after running the same graph. |

2018-04-03 03:30:52 -0600 | commented answer | Running tensorflow graph through OpenCV gives different result Really sorry for wasting your time with wrong edits @dkurt. |

2018-04-03 03:30:24 -0600 | edited question | Running tensorflow graph through OpenCV gives different result Running tensorflow graph through OpenCV gives different result I am trying to run an single channel image of size = ( 12 |

2018-04-03 03:29:52 -0600 | commented answer | Running tensorflow graph through OpenCV gives different result I apologize for the wrong tensorflow code @dkurt ... the tensorflow code also gets the image of size ( 125, 125 ) |

2018-04-03 03:16:53 -0600 | edited question | Running tensorflow graph through OpenCV gives different result Running tensorflow graph through OpenCV gives different result I am trying to run an single channel image of size = ( 12 |

2018-04-03 03:15:35 -0600 | commented answer | Running tensorflow graph through OpenCV gives different result I apologize for the wrong tensorflow code @dkurt ... the tensorflow code resizes the image first to ( 125, 125 ) |

2018-04-03 03:15:02 -0600 | commented answer | Running tensorflow graph through OpenCV gives different result I apologize for the wrong tensorflow code @dkurt ... the tensorflow code reshapes it to ( 125, 125 ) |

2018-04-03 03:13:58 -0600 | edited question | Running tensorflow graph through OpenCV gives different result Running tensorflow graph through OpenCV gives different result I am trying to run an single channel image of size = ( 12 |

2018-04-03 02:43:29 -0600 | commented answer | Running tensorflow graph through OpenCV gives different result @dkurt .... Have made the edits .... I found adding tensorflow code to the question quite difficilt, hence have added th |

2018-04-02 09:18:33 -0600 | commented answer | Running tensorflow graph through OpenCV gives different result dkurt .... Have made the edits .... I found adding tensorflow code to the question quite difficilt, hence have added the |

2018-04-02 09:16:57 -0600 | edited question | Running tensorflow graph through OpenCV gives different result How to set a 1 channel image as an input for cv::dnn::net I am trying to run an single channel image of size = ( 125, 1 |

2018-04-02 08:45:22 -0600 | edited question | Running tensorflow graph through OpenCV gives different result How to set a 1 channel image as an input for cv::dnn::net I am trying to run an single channel image of size = ( 125, 1 |

2018-04-02 07:39:41 -0600 | commented answer | Running tensorflow graph through OpenCV gives different result Thanks for the response dkurt .... I have added the graph reference on the stack overflow link .... Should I add another |

2018-04-02 05:29:59 -0600 | commented answer | Running tensorflow graph through OpenCV gives different result Thank you for pointing out the error. But I am still facing issue while running the image through OpenCV. I have asked t |

2018-04-02 05:28:59 -0600 | edited question | Running tensorflow graph through OpenCV gives different result How to set a 1 channel image as an input for cv::dnn::net I am trying to run an single channel image of size = ( 125, 1 |

2018-04-02 00:51:50 -0600 | edited question | Running tensorflow graph through OpenCV gives different result |

2018-04-02 00:51:50 -0600 | received badge | ● Editor (source) |

2018-04-02 00:49:02 -0600 | asked a question | Running tensorflow graph through OpenCV gives different result |

Copyright OpenCV foundation, 2012-2018. Content on this site is licensed under a Creative Commons Attribution Share Alike 3.0 license.