Loading...
Answers
MenuSomeone with experience with the Tensor Flow library (image recognition).
I'm looking for someone with experience with the Tensor Flow library for image recognition. I want to create a small specific test just to see how accurate it is (comparing 2 files: one PDF file with peoples faces and names, and another file which is a photo of the people listed in the first PDF file). I would like to know how accurate it would be, assuming that I don't have additional images of those people which I could use to 'train' the algorithm. Thanks
Answers
Ok, I wish you had specified if the photo's are full body or just face so to give an accurate answer
I would recommend you move forward with MS Azure sevices which are too good
In my experience with AI learning models, there is one defined amount of training process to 'train' the algorithm. Some models depending on complexity will work with a little amount of training such as the one PDF file. It will greatly depend on the complexity you are looking for. Such as if you are trying to determine specific features, or tell the difference between one face or another. The model will work more effectively with more training data involved. If you are just looking for a face than this one PDF file may be sufficient. The answer is not a straight forward yes or no without further details into what type of data you are looking for as a differental identifier for each face.
Related Questions
-
What is the best programming language for building multi-platform mobile software that is scalable?
I've been involved in several projects that hinged upon this question (generally start-ups or web+mobile apps), and it's not a clean or easy answer unfortunately! Plus every developer you talk to is going to try to sell you their services, but what you need is simply the truth! I'd suggest that you consider shifting your focus away from finding a best language. That sort of premise can eliminate options that are actually quite valid solutions. Keep in mind that any mobile app will require multiple languages working in harmony - all while used in a commercially consistent and standards-based manner. That's the part that determines your technical scalability! Almost every programming language can achieve this functionality with an experienced developer on your team. The best advice I can give you, is to consult with at least two people on this, and three if your app is os-specific. The most important insight will come from a "full stack" developer. One who's got a variety of enterprise experience, and can code at all levels of the stack. This person needs to have experience in leading a team of other developers, which forces the strategy of which technologies to use and why onto their plates daily. Secondly, you'll want to consult with a "front end" developer, who can tell you what's possible using advanced OOP JavaScript techniques (like Google's angular.js), because in an absurdly fast change over the past 3 years, much of the formerly back-end work has made it's way to the front-end, and is driven by JavaScript, predominantly JSON data, and awesome API's. The game has changed and the front-enders are the poor souls dealing with this rapid shift daily. To do this, they're also fantastic JavaScript programmers, which is a language that runs on all mobile devices and all browsers, too. Love it or hate it JavaScript is the most commonly used language in the world. Finally, if your app is OS-specific, you'll want to consult with a developer who works predominantly with the OS your app is built for. This person lets you know what's possible from the device POV, should know what stacks and JavaScript approaches can and can't be done on that OS, and how to leverage the resources of the device for your app as well as extend it's functionality. BONUS - loop back to the full stack developer to double-check the claims of the front-ender and the mobile developers. Always double check with your most senior programmer ;) All of these consults together in addition to your own research and due diligence will get you comfortable and allow you to navigate on this rather daunting but deeply important journey. There aren't any turn-key options. Instead it's a series of inter-connected modules driven by different languages, and all working in tandem. Every solution will have bugs, and no one group of technologies can do everything without proper developers. If you'd like to go further down the rabbit hole, then we should definitely set-up some time to speak. Otherwise, I wish you great luck in research and encourage you to learn as much as you can! :) It's going to seem hard, and might give you a headache here or there, but learn everything you can about how different technologies "talk" to each other, and then you will be able to build a map for keeping your app and business scalable regardless of the changing tides of technology!MM
-
What is the best way to implement sharing in a native app and mobile website?
I've been developing web and iPhone apps for a while and I usually recommend to first use the provided sharing mechanisms. They provide great flexibility and as well don't require your app to request permissions on external networks. Using the iOS SDK sharing components will also save you precious development time. The most important part is the content that will be shared. On that side, make sure all the content has a unique URL, and can be properly consumed on all plateforms, desktop and mobile. Pay a particular attention to the head meta tags of those pages. Open graph and Twitter tags are not optional anymore and help driver a better visibility on the networks your content is being shared onto. Don't forget to track with an appropriate analytics tool how your users use the sharing module. Then you can evaluate the pertinence of building something custom.FV
-
Can I make money freelancing while learning how to program JavaScript?
Most jobs in the marketplace are going to require more skill and experience than you have currently. One avenue that may allow you to make some money while expanding your skills would be to bid on projects through the platform upwork.com. This is a platform designed to help people find freelancers to assist with various projects. Upwork.com has a constant stream of web development project of all shapes and sizes. You may be able to find some projects there that fit within your skillset and bid to complete them. Another unpaid opportunity could be to begin writing free/open source scripts, utilities, or tools and post them for public use. This would allow you to expand your capabilities while also building a body of work that you could show potential clients or employers as your skills improve and you begin seeking employment. Look for common problems and find ways to solve them. Even if there are other solutions out there you can exploit your limited knowledge to create simple straight-forward solutions for other beginners like yourself who can often be overwhelmed by some of the more complex solutions and frameworks common in the marketplace.RS
-
Who can best help my programmer and I come up with an actual completion date for our website?
Planning software projects — especially estimating timelines — is a consistent challenge for developers. When I ran an agency, I constantly struggled with my team's ability to hit deadlines until I figured out how to plan more effectively. I've written up my approach here: http://lengstorf.com/effective-project-planning/ The short version is: 1. Make every task a yes/no question. If there's room for interpretation, it's not clear enough. 2. Keep the goals visible and track progress in a central location (somewhere you can both see). 3. Break tasks into single-day efforts whenever possible. So instead of "build home page", it's "A) style navigation; B) create opt-in; C) add testimonials section; etc." — the goal is to create momentum with a daily deadline that can absolutely be completed. It takes a little more effort up front, but it pays dividends in the long run. I used this strategy with my team to decrease our average turnaround times by nearly half, and my consulting clients have used this strategy to similar effect. I'd be happy to help you create a concrete plan using these techniques. Schedule a call or send me a message and we'll get started. Good luck!JL
-
Programming language for web platform?
NOT Wordpress! Facebook uses PHP among other languages, if that tells you anything. Every programmer will be bias toward what they like and what they are used to coding with. The bigger question for you is, have you completed your due diligence? Is there a real need for another crowd funding platform? Why would yours be so different that it would stand out among the others? Who is you target market? What is your unique selling proposition? How big is your potential market? Should you go vertical or horizontal? You may have already answered these and the two dozen other questions every entrepreneur must ask before they waste valuable time and money to become another business start up statistic. Assuming you have a strong grasp of where you are heading and a solid strategic blueprint to be able to predict your growth, the last thing I will leave you with is this. The programing language is not nearly as important as your database structure and IT infrastructure for the purpose of scale. Not to say the language is not important - all three components work together. Spend time on the other two and work backwards. If you would like to discuss this further at no charge, use the link below. I provide a free 30 minute consultation to first time callers. https://clarity.fm/kevinmccarthy/FreeConsult Best regards, Kevin McCarthy www.kevinmccarthy.comKM
the startups.com platform
Copyright © 2025 Startups.com. All rights reserved.