tag:blogger.com,1999:blog-1106783043299925876.post3936206966404090628..comments2024-03-02T13:01:32.864+05:30Comments on Codes of Interest | Deep Learning Made Fun: Getting the LeNet model working with Face RecognitionThimira Amaratungahttp://www.blogger.com/profile/13330876639489088914noreply@blogger.comBlogger10125tag:blogger.com,1999:blog-1106783043299925876.post-7163817649177751192018-08-24T12:11:49.533+05:302018-08-24T12:11:49.533+05:30The trained weight from my model would only work w...The trained weight from my model would only work with the face dataset which I created and used.Thimira Amaratungahttps://www.blogger.com/profile/13330876639489088914noreply@blogger.comtag:blogger.com,1999:blog-1106783043299925876.post-83697862262459224882018-08-20T00:43:36.824+05:302018-08-20T00:43:36.824+05:30Sir, can you please give your trained weights.Sir, can you please give your trained weights.Anonymoushttps://www.blogger.com/profile/14059807641703437197noreply@blogger.comtag:blogger.com,1999:blog-1106783043299925876.post-81025420424400668772018-06-09T15:46:33.003+05:302018-06-09T15:46:33.003+05:30please reply how you passes weights and save model...please reply how you passes weights and save model through arguments...by giving the complete path ?Anonymoushttps://www.blogger.com/profile/09868887138704331641noreply@blogger.comtag:blogger.com,1999:blog-1106783043299925876.post-42396218770936540742017-09-12T20:35:08.377+05:302017-09-12T20:35:08.377+05:30grate work thank you for sharing, so i have proble...grate work thank you for sharing, so i have problem in inference phase of model, eg. i want to predict labels from some external images, so for that i have to save keras model right?, and lode it on front end script, now what should i do???? thankyou in advanceAnonymoushttps://www.blogger.com/profile/01581548683427684322noreply@blogger.comtag:blogger.com,1999:blog-1106783043299925876.post-70099802802300928792017-06-15T15:25:48.064+05:302017-06-15T15:25:48.064+05:30Hi, thanks you for this article.
However i would l...Hi, thanks you for this article.<br />However i would like to explain me how i can you this code i.e how i can execute it.<br />Thanks.Learnhttps://www.blogger.com/profile/00055272689023153804noreply@blogger.comtag:blogger.com,1999:blog-1106783043299925876.post-76339891829990838432017-04-05T02:31:46.926+05:302017-04-05T02:31:46.926+05:30Your answer explains it all. Thank you! Your answer explains it all. Thank you! The Biometrics Guyhttps://www.blogger.com/profile/03247077681001192108noreply@blogger.comtag:blogger.com,1999:blog-1106783043299925876.post-27349568628253520212017-04-04T12:37:08.338+05:302017-04-04T12:37:08.338+05:30Hi Abhilash,
I've actually created a small Py...Hi Abhilash,<br /><br />I've actually created a small Python script using OpenCV to create a set of face images from the webcam, and automatically save the cropped images of the face with a given label. <br /><br />I'll soon do a post on how I did it with the full code of that script. Thimira Amaratungahttps://www.blogger.com/profile/13330876639489088914noreply@blogger.comtag:blogger.com,1999:blog-1106783043299925876.post-67950009907060531612017-04-03T12:03:11.045+05:302017-04-03T12:03:11.045+05:30How can I create a dataset of images like you did....How can I create a dataset of images like you did.<br />Thank you.abhilashhttps://www.blogger.com/profile/00602687148163074280noreply@blogger.comtag:blogger.com,1999:blog-1106783043299925876.post-12535998397047741592017-03-31T12:55:44.040+05:302017-03-31T12:55:44.040+05:30Hi Kushal,
That's an interesting question.
I...Hi Kushal,<br /><br />That's an interesting question.<br /><br />If we take the terms 'classification' and 'recognition' generally (out of the context of 'face recognition'), then we can say the following:<br />Classification is when we group a set of items in to two or more categories, typically done via supervised learning using a labeled training set.<br />Recognition is when we attempt to identify general patters among our items set, typically done via unsupervised learning and without a training set.<br /><br />However, when we come back into the context of 'Face Recognition' the terms are used out of their general meaning.<br /><br />When we talk about Face Recognition, what we are actually doing is classification. (and all implementations of face recognition that I'm aware of are doing the same). We do use supervised learning, and we do use a training set.<br /><br />An algorithm that can perceive a face and recognize it unsupervised is yet to be developed. It's a good hard problem to tackle.<br /><br />Would like to hear your thoughts as well.Thimira Amaratungahttps://www.blogger.com/profile/13330876639489088914noreply@blogger.comtag:blogger.com,1999:blog-1106783043299925876.post-38097886206640436872017-03-31T01:11:56.942+05:302017-03-31T01:11:56.942+05:30I see that you have applied LeNet model which was ...I see that you have applied LeNet model which was used on MNIST dataset for classification to perform face recognition. So what do you think is the fundamental difference between the problem of "classification" and "recognition"?The Biometrics Guyhttps://www.blogger.com/profile/03247077681001192108noreply@blogger.com