Machine-Learning Advanced Premium

Computer Vision AI Development Virtual Internship

In this advanced virtual internship, students will learn to build and deploy state-of-the-art computer vision models for image and video analysis. They will gain hands-on experience with object detection, image classification, and semantic segmentation, and learn how to optimize and deploy these models in real-world applications. By the end of the internship, students will have a strong portfolio of computer vision projects and be well-prepared for careers in AI and machine learning.

weeks
7 tasks
0 enrolled
Sign In to Purchase - $49
Track price: $49.00

Track Overview

This track provides hands-on experience and real-world projects to build your skills.

Tasks & Milestones

Explore Computer Vision Datasets

Advanced

In this task, students will investigate popular computer vision datasets, such as COCO, ImageNet, and Pascal VOC, and understand their characteristics, strengths, and limitations.

8 hours

Implement a YOLO Object Detector

Advanced

In this task, students will build and train a YOLO (You Only Look Once) object detection model using the PyTorch framework.

20 hours

Deploy an Object Detector in a Web Application

Advanced

In this task, students will integrate their object detection model into a web application, allowing users to upload images and view the detected objects.

25 hours

Build a CNN-based Image Classifier

Advanced

In this task, students will design and train a convolutional neural network (CNN) for image classification using the TensorFlow framework.

18 hours

Deploy an Image Classifier in a Mobile App

Advanced

In this task, students will integrate their image classification model into a mobile application, allowing users to classify images on their devices.

22 hours

Implement a U-Net Semantic Segmentation Model

Advanced

In this task, students will build and train a U-Net semantic segmentation model using the PyTorch framework.

20 hours

Deploy a Semantic Segmentation Model in a Computer Vision Pipeline

Advanced

In this task, students will integrate their semantic segmentation model into a larger computer vision pipeline, demonstrating its use in a real-world application.

25 hours

Prerequisites

  • • Proficiency in Python programming
  • • Familiarity with machine learning concepts and algorithms
  • • Experience with deep learning frameworks like TensorFlow or PyTorch

Certificate

Certificate of Completion

Earn a certificate upon successful completion