From the course: AWS Certified Machine Learning Engineer Associate (MLA-C01) Cert Prep

Unlock this course with a free trial

Join today to access over 25,300 courses taught by industry experts.

Object detection

Object detection

From the course: AWS Certified Machine Learning Engineer Associate (MLA-C01) Cert Prep

Start my 1-month free trial Buy for my team

Object detection

“

- [Instructor] Hello guys, and welcome again. So, in today's lesson we are going to talk about the object detection algorithm, which is used to detect objects in a given image. So, the object detection algorithm is a supervised learning algorithm by nature, so you need to supply both the features and the target as your input. It could identify instances of objects within an image with a confidence score and a rectangular bounding box. So, the bounding box is used to indicate the exact position of the object or an estimate of the position of the object. It uses a single-shot multibox detector which is the SSD framework, and it supports VGG and ResNet. So for the training format of the object detection algorithm, you could supply the input as Apache MXNet RecordIO format which is different from the RecordIO protobuf that we know, or you could supply an image format and in an image format you should specify train, validation, train annotation and validation annotation channels and the…

Contents