Congratulations on choosing to participate in the Virtual Internship Program on Generative AI with Open Weaver! This 4-week program is designed to be an interactive & practical internship and will help you gain industry-ready skills through project-based learning. The internship will consist of 3 Bootcamps (1 per week) , a few coding exercises, a project, and a final assessment.
WEEK 3 - GENERATIVE AI
Today, our focus will be on how DeepFake Detection Engine identifies manipulated or synthetic media content using machine learning algorithms and computer vision techniques to detect anomalies in facial and body movements, and other visual artifacts. Through today’s Bootcamp and this week’s exercises, we will learn how to apply Computer Vision techniques, specifically MTCNN and Inception-ResNet models, for the purpose of Building a DeepFake Detection Engine by using the popular Facenet_pytorch framework.
Learning Objectives
After completing this course you will:
- Have a good working knowledge of the Fundamentals of Computer Vision.
- Familiarize with MTCNN and Inception-ResNet models for DeepFake Detection.
- Have a fully functional DeepFake Detector prototype that you can customize and fine-tune the model to enhance its performance.
10-Min Tutorial
The DeepFake Detector is engineered using cutting-edge computer vision algorithms and state-of-the-art deep learning frameworks. The system is specifically designed to detect and flag manipulated or synthetic media content, such as deepfakes, by analyzing their visual attributes. By feeding your own data into the detector, it delivers a comprehensive report of identified deepfakes with remarkable precision.
Watch this tutorial on building your own DeepFake Detection Engine & learn how to train the model, and showcase the power of identifying and flagging anomalies in facial and body movements, as well as detecting a multitude of other visual artifacts. Revisit the concepts discussed during the live bootcamp session in this 10-min tutorial video. If you would like to watch the recording of the entire bootcamp please click HERE.
Practical Exercise
Click the below button to access the DeepFake Detector kandi kit. This kit has all the required dependencies and resources you need to build your application.
Click on the 1-Click Installer button on the kandi kit page to install the DeepFake Detector kit. On installing and running this kit, you will have a working model that you can customize and use in your project.
Final Project
Congratulations on reaching the final stage of your internship! Please take some time to carefully complete the intriguing Final Assessment & Project Submission . Upon successful completion, you will be awarded your highly anticipated Internship Completion Certificate!
It is mandatory for you to complete your weekly Coding Exercises in order to receive your Internship Completion Certificate.
Below is a sample coding exercise that will help you advance in your journey in DeepFake Detector. To get started, use the relevant keywords to search for simple code snippets in the search bar on kandi.
Sample Exercise 1 - Resize image using OpenCV: Image resizing refers to the scaling of images. It helps in reducing the number of pixels from an image and that has several advantages e.g. It can reduce the time of training of a neural network as the more the number of pixels in an image more is the number of input nodes that in turn increases the complexity of the model.
Support
Reach out to us by clicking on the reply button below for any help you may need with this course. You may also use the chat feature for support. To access the reply and chat feature, please sign-in to the the Community.
We hope you enjoyed using kandi! Continue your learning journey with kandi 