Topics: The following topics are covered in this module:
- The Right Task for the Job
- Implementing Computer Vision Models with Python APIs
- Data Manipulation for Computer Vision Models
Objectives
By the end of this module, students will be able to:
- Select appropriate models for specific computer vision tasks.
- Implement Python APIs for computer vision model development.
- Evaluate a dataset’s suitability for training a computer vision model.
- Manipulate datasets using Python for vision model training.
- Discuss different architectures’ suitability for different computer vision tasks.
Watch
Video: Understanding Computer Vision Tasks (5:20)
Topics
Click on the links and read the materials within.
- The Right Task for the Job
- Implementing Computer Vision Models with Python APIs
- Data Manipulation for Computer Vision Models
Practice and Apply
Object Detection Exercise
You now have a better understanding of how to select the right models for different tasks, implement them using powerful APIs, and evaluate their performance on datasets. Most importantly, you have learned how to manipulate and prepare your image data to give your models the best chance of success. The next step? An object detection exercise!
Let’s head back to our Jupyter Notebooks to continue: https://github.com/PracticumAI/computer_vision
Using the same resource requests as in module 1, complete notebook 02_boxes_of_fruit.ipynb, which will introduce you to object detection.
