From the course: Deep Learning and Computer Vision: Object Detection with PyTorch
Join today to access over 24,900 courses taught by industry experts.
Using GitHub Codespaces for computer vision tasks - PyTorch Tutorial
From the course: Deep Learning and Computer Vision: Object Detection with PyTorch
Using GitHub Codespaces for computer vision tasks
- [Instructor] In this video, we will be using the wheat detection data set from Kaggle to train a custom object detection model for a computer vision task. This data set contains images of wheat heads annotated with bounding boxes. We will fine tune a pre-trained object detection model to recognize and locate wheat heads in these images. The wheat detection data set from Kaggle contains over 3000 images of wheat heads, each annotated with bonding boxes. We will be loading the data set and preparing it for training in PyTorch using GitHub Codespaces. Let's jump to the codespace environment. This code is for loading the wheat detection data set. First, we will be importing the important libraries like Pandas, torchvision, et cetera, and then reading the CSV file containing the dataset annotations used for training. Here we have created a custom dataset class to load the wheat detection dataset and thus prepare the images along with their bounding box annotations for training. Now we…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.