Training: Deep Learning for Computer Vision
Level
AdvancedDuration
40h / 5 daysDate
Individually arrangedPrice
Individually arrangedTraining: Deep Learning for Computer Vision
Computer Vision (CV) is the field of science that defines how machines interpret the meaning of images and videos. CV algorithms analyze specific criteria in images and videos and then apply these interpretations to predictive or decision-making tasks.
What will you learn?
- How to prepare image data for machine learning using OpenCV and preprocessing techniques
- How to design and train Convolutional Neural Networks (CNNs) for image classification in TensorFlow/Keras
- How to build and evaluate object detection models, including SSD detectors
- How to improve model quality through tuning, transfer learning, and data augmentation
Who is this training for?
Designers and professionals working with images and video who want to leverage machine learning to make their work easier-
Individuals who want to deepen their knowledge of advanced topics related to image and video processing
Training Program
-
Introduction
- What is an image?
- OpenCV
- Classical image processing
- Theory of Convolutional Neural Networks (CNNs)
-
Dataset Processing
- Loading and reviewing images
- Building datasets
- Preprocessing
- Preparing for modeling
-
Image Classification
- Convolutional layers
- Designing CNNs in
tf.keras - Modeling
- Qualitative model analysis
- Model tuning
-
Object Detection
- Types of detectors
- Designing an SSD detector
- Detector modeling
- Quality analysis
-
Transfer Learning
- Comparing models
-
Advanced Object Detection
- Extensions
- Low-level CNN construction
- Model parameter analysis
- Data augmentation
