2020-11-19 02:15:26 -0600 | received badge | ● Popular Question (source) |
2019-06-03 11:00:42 -0600 | commented question | Camera for Gear Inspection Thanks @kbarni, I will keep this in mind |
2019-06-03 10:30:02 -0600 | commented question | Camera for Gear Inspection I think you are right in case of pixel size, thanks So if we are using a resolution of 6MP (3000*2000) and we have max |
2019-06-03 08:53:30 -0600 | commented question | Camera for Gear Inspection I think you are right in case of pixel size, thanks So if we are using a resolution of 6MP (3000*2000) and we have max |
2019-06-03 03:58:15 -0600 | commented question | Camera for Gear Inspection 5MP monochrome cameras give an accuracy of 2micrometreĆ2micrometre.Wont this be enough? How much transfer time do you t |
2019-06-03 00:24:16 -0600 | commented question | Camera for Gear Inspection Ok, Thanks for the info |
2019-06-03 00:23:56 -0600 | commented question | Camera for Gear Inspection Ok, Thanks for the info Amal |
2019-06-01 01:01:51 -0600 | asked a question | Camera for Gear Inspection Camera for Gear Inspection Hello, We are planning to setup a camera system for gear inspection and defect detection. Th |
2018-04-12 09:43:29 -0600 | received badge | ● Self-Learner (source) |
2018-04-12 09:38:19 -0600 | answered a question | Training CNN for NIST digits using tiny-dnn The problem was with high learning rate. When the learning rate was changed from the default value of 0.01 to 0.0001 the |
2018-04-12 07:14:27 -0600 | commented question | Training CNN for NIST digits using tiny-dnn 0% 10 20 30 40 50 60 70 80 90 100% |----|----|----|----|----|----|----|----|----|----| Training St |
2018-04-12 07:13:05 -0600 | commented question | Training CNN for NIST digits using tiny-dnn 0% 10 20 30 40 50 60 70 80 90 100% |----|----|----|----|----|----|----|----|----|----| Training Star |
2018-04-12 07:12:34 -0600 | commented question | Training CNN for NIST digits using tiny-dnn you mean 0-9 right!! what do you mean by shuffling data? Currently testing with a reduced learning rate of 0.0001 instea |
2018-04-12 05:46:23 -0600 | commented question | Training CNN for NIST digits using tiny-dnn That is 97% accuracy..on mnist.. right So I wonder why we are not getting accuracy on NIST (link text |
2018-04-12 03:56:32 -0600 | commented question | Training CNN for NIST digits using tiny-dnn link text This is the link The change in size should be because of padding |
2018-04-12 03:47:41 -0600 | commented question | Training CNN for NIST digits using tiny-dnn link text This is the link |
2018-04-12 03:47:08 -0600 | commented question | Training CNN for NIST digits using tiny-dnn link text |
2018-04-12 03:16:41 -0600 | commented question | Training CNN for NIST digits using tiny-dnn and in mnist digits they are getting more than 98% accuracy with this architecture..so the doubt. |
2018-04-12 03:05:04 -0600 | commented question | Training CNN for NIST digits using tiny-dnn ok.. i will try this out The mnist database example in the tiny-dnn website does a -1 to 1 normalisation. This is the re |
2018-04-12 02:56:05 -0600 | commented question | Training CNN for NIST digits using tiny-dnn ok.. i will try this out |
2018-04-12 02:05:58 -0600 | received badge | ● Student (source) |
2018-04-12 01:58:45 -0600 | asked a question | Training CNN for NIST digits using tiny-dnn Training CNN for NIST digits using tiny-dnn I have been trying to train a CNN using tiny-dnn library for digit recogniti |
2017-12-16 08:33:01 -0600 | edited question | OpenCV SVM performance poor compared to matlab ensemble OpenCV SVM performance poor compared to matlab ensemble Hello, I have been training a svm classifier for a 2 class forg |
2017-12-16 08:31:41 -0600 | asked a question | OpenCV SVM performance poor compared to matlab ensemble OpenCV SVM performance poor compared to matlab ensemble Hello, I have been training a svm classifier for a 2 class forg |
2017-12-11 22:44:03 -0600 | commented question | p, nu and coef0 parameters does not change during SVM::trainAuto training //Set up SVM's parameters CvSVMParams params; params.svm_type = CvSVM::C_SVC; par |
2017-12-11 22:42:16 -0600 | commented question | p, nu and coef0 parameters does not change during SVM::trainAuto training //Set up SVM's parameters CvSVMParams params; params.svm_type = CvSVM::C_SVC; params.kernel_t |
2017-12-11 22:41:41 -0600 | commented question | p, nu and coef0 parameters does not change during SVM::trainAuto training //Set up SVM's parameters CvSVMParams params; params.svm_type = CvSVM::C_SVC; params.kernel_type = CvSVM: |
2017-12-11 22:18:18 -0600 | commented answer | p, nu and coef0 parameters does not change during SVM::trainAuto training Thanks for the clarification @berak Regards Amal |
2017-12-11 22:17:18 -0600 | commented question | p, nu and coef0 parameters does not change during SVM::trainAuto training //Set up SVM's parameters CvSVMParams params; params.svm_type = CvSVM::C_SVC; params.kernel_type = CvSVM::RBF; params |
2017-12-11 22:17:01 -0600 | marked best answer | p, nu and coef0 parameters does not change during SVM::trainAuto training Hello, The values of p, nu and coef0 parameters are not getting updated in SVM::trainAuto training. It is always zero. The parameters gamma and cvalue are getting changed. Is this normal? Are the best values of these parameters usually zero? The kernel type used is RBF and svm type is C_SVC Also is there any way we can improve a two class classification other than making the parameter balanced = true in SVM::trainAuto training. The project is forgery detection where we have to distinguish between forged and pristine images. |
2017-12-11 10:21:14 -0600 | edited question | p, nu and coef0 parameters does not change during SVM::trainAuto training p, nu and coef0 parameters does not change during SVM::trainAuto training Hello, The values of p, nu and coef0 paramete |
2017-12-11 09:12:06 -0600 | asked a question | p, nu and coef0 parameters does not change during SVM::trainAuto training p, nu and coef0 parameters does not change during SVM::trainAuto training Hello, The values of p, nu and coef0 paramete |
2017-11-05 01:23:11 -0600 | commented question | Training a classifier if feature size is greater than RAM size This is a new information, thanks. Just looked up transfer learning in google. |
2017-11-03 00:56:20 -0600 | commented question | Training a classifier if feature size is greater than RAM size This is a new information, thanks. Just looked up in google about transfer learning. |
2017-10-31 08:55:46 -0600 | commented question | Training a classifier if feature size is greater than RAM size true Are you getting high accuracy than svm even with just 3 layers ? I don't have much experience in deep networks. Lo |
2017-10-31 05:57:56 -0600 | commented question | Training a classifier if feature size is greater than RAM size The main reasons for not using ANN are 1) Long training time 2) From experience other classifiers like svm gave better |
2017-10-31 05:57:30 -0600 | commented question | Training a classifier if feature size is greater than RAM size The main reasons for not using ANN are 1) Long training time 2) From experience other classifiers like svm gave better |
2017-10-31 05:56:57 -0600 | commented question | Training a classifier if feature size is greater than RAM size The main reasons for not using ANN are 1) Long training time 2) From experience other classifiers like svm gave better a |
2017-10-31 05:56:47 -0600 | commented question | Training a classifier if feature size is greater than RAM size The main reasons for not using ANN are 1) Long training time 2) From experience other classifiers like svm gave better a |
2017-10-30 23:24:28 -0600 | commented question | Training a classifier if feature size is greater than RAM size yep, that is the plan For 300 blocks per image and number of images equal to 500, the feature count will be 500*300=1,5 |
2017-10-30 23:23:42 -0600 | commented question | Training a classifier if feature size is greater than RAM size yep, that is the plan For 300 blocks per image and number of images equal to 500, the feature count will be 500*300=1,50 |
2017-10-30 11:49:45 -0600 | commented question | Training a classifier if feature size is greater than RAM size These are scrm features. A 2000x1000 image is divided into 32x 32 blocks with a stride of 16. Out of these blocks aroun |
2017-10-30 11:47:23 -0600 | commented question | Training a classifier if feature size is greater than RAM size These are scrm features. A 2000x1000 image is divided into 32x 32 blocks with a stride of 16. Out of these blocks aroun |
2017-10-30 11:43:54 -0600 | commented question | Training a classifier if feature size is greater than RAM size These are scrm features. A 2000x1000 image is divided into 32x 32 blocks with a stride of 16. Out of these blocks aroun |
2017-10-30 11:30:39 -0600 | asked a question | Training a classifier if feature size is greater than RAM size Training a classifier if feature size is greater than RAM size Hello, How can we train a classifier if the size of the |
2017-04-29 01:08:17 -0600 | commented question | Best way to Track an Object in Android It would have been better if you provided an image for reference Some tips you can use 1) Check for circular objects to detect ball. Take help of shape. 2) Look only in a small neighbourhood around the ball after the first frame while tracking the ball. This will reduce mistaking it with other objects. |
2017-04-29 00:55:43 -0600 | commented answer | Find rectangle from image in android? Yes, i think you can use thresholding followed by findContours |