Computer Vision with DL
Image classification, detection, segmentation with modern architectures.
- Home
- Computer Vision with DL
Vision• intermediate
Computer Vision with DL
Image classification, detection, segmentation with modern architectures.
4.3(41 reviews)
78 students
Last updated 2024-01-20
Dr. Maria Santos
Computer Vision Researcher
0:00 / 0:00
Computer Vision with DL - Preview
What you'll learn
Master modern CNN architectures (ResNet, EfficientNet, Vision Transformers)
Implement object detection with YOLO and R-CNN
Build image segmentation models with U-Net
Apply transfer learning and fine-tuning
Deploy computer vision models to production
Course content
3 sections • 51 minutes
1
Classification
From AlexNet to ViT.
16 min
2
Object Detection
YOLO, Faster R-CNN.
18 min
3
Segmentation
U-Net and variants.
17 min
Requirements
- Python programming experience
- Understanding of deep learning basics
- Familiarity with PyTorch or TensorFlow
- Basic knowledge of image processing
About this course
This course covers the latest advances in computer vision with deep learning. You'll work with real image datasets and build production-ready vision models.
$199$299
33% OFF
One-time payment • Lifetime access
4.5 hours of video content
20 downloadable resources
Certificate of completion
Lifetime access
Pre-trained models included
Real-world image datasets
30-day guarantee
Full refund if you're not satisfied
Course Info
English
51 hours total
3 lessons
Certificate of completion