UDUdemy
Computer Vision with PyTorch: Deep Learning for Images
Intermediate 20 hours English Completion Certificate Certificate
About this course
This course covers computer vision from CNN fundamentals through modern production techniques: custom CNN architectures, transfer learning with ResNet and EfficientNet, object detection with YOLOv8, and semantic segmentation with U-Net.
The final section covers deploying vision models as REST APIs with FastAPI and Docker — bridging the gap between training a model and shipping it as a production service.
What you'll learn
Build CNNs from scratch and understand convolution, pooling, and feature maps
Apply transfer learning with ResNet, EfficientNet, and pretrained backbones
Implement object detection with YOLOv8 for real-time applications
Apply semantic segmentation with U-Net for pixel-level classification
Deploy vision models as REST APIs using FastAPI and Docker
This course includes
20h
On-demand video
Yes
Certificate
Yes
Mobile access
English
Language
Comparison · LBS
Compare alternatives for Computer Vision with PyTorch: Deep Learning for Images
Same topic, different options. We surface the trade-offs others hide so you can pick the course that actually fits your time, budget, and goals.
UDUdemy4.7(6,000)
Computer Vision with PyTorch: Deep Learning for Images
- Price
- PaidOne-time purchase, sales ~$15
- Duration
- 20 hrs
- Level
- Intermediate
- Certificate
- Completion Certificate
MOMIT OpenCourseWare4.9(15,000)
Linear Algebra (18.06)
- Price
- FreeCompletely free, openly licensed — no certificate
- Duration
- 34 hrs
- Level
- Intermediate
- Certificate
SOStanford Online4.9(9,000)
CS231n: Deep Learning for Computer Vision
- Price
- FreeFree lecture materials; some versions paid
- Duration
- 50 hrs
- Level
- Advanced
- Certificate
SOStanford Online4.9(7,000)
CS224n: Natural Language Processing with Deep Learning
- Price
- FreeFree lecture materials; some versions paid
- Duration
- 50 hrs
- Level
- Advanced
- Certificate
Prices & availability can change — confirm on the provider's site. We're not affiliated with any single provider.
Instructor
AN
Andrei Neagoie / Daniel Bourke
Udemy instructor
75K+ learners8 courses4.7 instructor rating
Taught by Udemy computer vision instructors with industry experience building vision systems for production applications.
Requirements
- Python proficiency; basic PyTorch or neural network knowledge recommended
Who this course is for
- ML engineers who want computer vision specialization
- Software developers building vision-based products
- Data scientists transitioning from tabular data to image data
About this provider
UD
Udemy
The world's largest online learning marketplace. 65M+ students, 210,000+ courses.
Frequently asked questions
Primarily images — video processing is covered briefly but is not the main focus.
YOLOv8 from Ultralytics — the current standard for real-time object detection.