Welcome to the "Course on Computer Vision"! This course is designed to introduce you to the fundamentals of computer vision, covering key concepts, techniques, and applications.
- Understand the basic concepts of machine learning.
- Create and train a neural network in Python with pytorch.
- Apply machine learning algorithms to real-world data.
- Convolutional Neural Networks (CNNs)
- Filter an image for a particular feature (convolution)
- Detect that feature within the filtered image (ReLU)
- Condense the image to enhance the features (maximum pooling)
- Data Augmentation
- Test Time Augmentation
- Ensemble Learning
- Transfer Learning
- Collaborate with a team to solve machine learning problems.
- Ensure that git is installed on your machine. Download Git.
- Basic programming knowledge (Python recommended) Download Python.
- Familiarity with Jupyter Notebooks.
- Clone the repository.
git clone https://github.com/CogitoNTNU/course-on-computer-vision.git- Install juptyer notebook
pip install ipykernel -U --userBeyond the core content, the course provides additional insights into:
- Basic programming knowledge (Python recommended).
- Google Colab account for running the notebook.
Follow the parts in order, completing tasks and exercises as you go. Experiment with the code cells to reinforce your learning. Refer to the "Extras" section for additional tools and techniques beyond the course scope. Happy learning!
This course was created by Brage Kvamme, Kristoffer Nohr Olaisen, and Sverre Nystad. Using our combined experiences out in industry, programming, and machine learning, we have crafted this course to help you understand and work with Computer Vision.
 Brage Kvamme |
 Kristoffer Nohr Olainsen |
 Sverre Nystad |