
Tamamlandı
İlan edilme:
Teslimde ödenir
I need a lightweight AI model that can flag deepfakes in both still photos and the individual frames of a video. The goal is moderate, reliable accuracy—good enough to separate obvious fakes from genuine content without the heavy-duty infrastructure a research-grade solution would demand. I just want clean, well-commented code that someone with basic ML/DL familiarity can pick up and run on a CPU. Deliverables • Trained model file and all training scripts • Inference script or notebook that accepts an image or video file and returns a deepfake probability score plus a simple real/fake label • Brief README explaining setup, model architecture, and how to retrain or fine-tune on new data • A short report (a page or two) summarizing achieved accuracy, dataset used, and suggested next steps for further improvement If public datasets are required, please source ones that are freely licensed and reference them in the report. Keep the solution straightforward—clear code, minimal external dependencies, and results that demonstrate solid, good-accuracy detection without an oversized model.
Proje No: 40035999
6 teklifler
Uzaktan proje
Son aktiviteden bu yana geçen zaman 3 ay önce
Bütçenizi ve zaman çerçevenizi belirleyin
Çalışmanız için ödeme alın
Teklifinizin ana hatlarını belirleyin
Kaydolmak ve işlere teklif vermek ücretsizdir

Hey there! I can build you a lightweight, CPU-friendly deepfake detector that handles both images and video frames. I’ll stick with a compact CNN/MobileNet architecture, so you get solid accuracy without needing a fancy GPU or huge servers. I’m new to Freelancer, but I know my way around AI and ML. Since this is my first project here, I’m all-in — you’ll get high-quality work, clean code, and regular updates from me. I want this project to kickstart my reputation, so you can count on extra effort, attention to detail, and on-time delivery. Here’s what you’ll get: - A trained, lightweight deepfake detection model - Complete training scripts — clear, modular, and well-commented - An inference script or notebook that gives you both a deepfake probability and a simple real/fake label - A README with setup instructions, architecture details, and steps for retraining - A short report (1–2 pages) explaining the dataset, accuracy, and possible improvements - Minimal dependencies — just PyTorch or TensorFlow Lite, and OpenCV Why pick me? - I’ve got experience building optimized models for CPU-only systems - I know datasets like FaceForensics++, Celeb-DF, and DFDC inside out - My code is clean and beginner-friendly - This is my first project here, so you can bet I’ll make it a top priority - I want to prove myself, so you’ll get the best value for your budget I can start right away and make sure everything’s clear, simple, and works as promised. Hope to hear from you soon!
₹700 INR 7 gün içinde
0,0
0,0
6 freelancer bu proje için ortalama ₹950 INR teklif veriyor

I hold a Bachelor’s degree in Artificial Intelligence, and my work focuses on building practical, lightweight computer-vision systems that run efficiently on standard CPUs. I’ve delivered several end-to-end CV solutions involving dataset reconstruction, custom model design, and clean inference pipelines, all with clear documentation and reproducible training steps. I’m comfortable restructuring disorganised datasets, training compact PyTorch models, and producing simple, reliable detection scripts that anyone can run or extend. My approach prioritises clarity, minimal dependencies, and a fully transparent workflow from preprocessing through training to final evaluation. I can start immediately and deliver a polished, well-documented solution that meets your accuracy expectations and is easy to maintain going forward. Looking forward to working with you.
₹1.500 INR 7 gün içinde
2,1
2,1

Hi Siddhant, I understand you need a lightweight AI model to detect deepfakes in photos and video frames with moderate accuracy. With extensive experience in developing efficient ML models and simplifying complex concepts, I am well-suited for this task. I have successfully completed similar projects and can deliver a user-friendly model along with detailed documentation. In addition, I can provide a brief portfolio showcasing my expertise in AI model development. An insightful strategy I recommend is leveraging transfer learning to enhance model accuracy without heavy computational requirements. Let's discuss how we can get started on this project. I'm available at your convenience. Best regards, Zaheer Mahomed
₹1.000 INR 14 gün içinde
0,0
0,0

I will develop a lightweight deepfake detection model capable of analysing both images and video frames with reliable, moderate accuracy while remaining fully CPU-friendly. Using efficient CNN/transformer-based architectures and publicly available datasets, I will provide clean, well-commented training and inference scripts, along with a simple probability-based real/fake output. The final solution will include the trained model, a clear README, and a short accuracy report, ensuring an easy-to-understand and easily retrainable workflow.
₹600 INR 7 gün içinde
0,0
0,0

I will build a lightweight, CPU-optimized deepfake detection model with clean, well-structured code. You’ll receive the trained model, full training scripts, an easy inference tool for images/videos, a clear README, and a concise report. I’ll use free, reliable datasets and ensure the system is accurate, simple to run, and easy to retrain or extend.
₹1.050 INR 7 gün içinde
0,0
0,0

I’m an engineer experienced in building lightweight AI models that run efficiently on CPU while still delivering solid deepfake-detection accuracy. I’ll deliver a clean, well-documented codebase including training scripts, inference tools for both images and video frames, a trained model, and a clear report on performance and datasets used. My specialty is turning complex ML workflows into reproducible, easy-to-maintain systems — exactly what you need for a reliable deepfake-flagging tool without research-lab overhead.
₹850 INR 7 gün içinde
0,0
0,0

Pune, India
Ödeme yöntemi onaylandı
Ara 4, 2025 tarihinden bu yana üye
$10-50 USD
₹750-1250 INR / saat
₹1500-12500 INR
₹750-1250 INR / saat
$250-750 USD
₹600-1500 INR
₹12500-37500 INR
$30-250 USD
₹12500-37500 INR
$10-60 USD
$1500-3000 USD
₹750-1250 INR / saat
$750-1500 USD
₹12500-37500 INR
₹750-1250 INR / saat
₹1500-12500 INR
$250-750 USD
$30-93 USD
₹1500-12500 INR
₹12500-37500 INR