Description
Computer Vision & Deep Learning is a written, self-paced course in six modules. You learn how convolutional neural networks (CNNs) work by building one from scratch; use transfer learning with ResNet, EfficientNet and Vision Transformers; cover object detection with YOLO, Faster R-CNN and DETR; image segmentation with U-Net and Mask R-CNN; real-time video processing with OpenCV; and deploying vision models with ONNX and TensorRT.
It is a written educational course with code exercises, not a certification, and it does not promise a job outcome. It assumes basic Python and some familiarity with machine learning. Training larger models may need a GPU, which you can access through free or paid cloud notebooks. Use images and data you have the right to use, and consider privacy when working with images of people.
What you will be able to do
- Explain how convolution, pooling and activation layers work
- Build and train a small CNN from scratch
- Fine-tune a pretrained model for your own image classes
- Run object detection and segmentation models and interpret their outputs
- Process video with OpenCV and export a model to ONNX for deployment
Educational content only. No income, revenue or earnings results are promised or implied. This course does not award a certification, licence or professional credential.
