Train SSD MOBILENET

In this video, we will see how we can train SSD-MOBILENET model for your own custom object detection. For this video, we have used images for apples and banana and we have trained a model for this. Training has been performed on Ubuntu machine and then we have used #jetson #xavier to run that model.

Watch other custom training videos :

Watch all Nvidia Jetson Inference videos: https://www.youtube.com/watch?v=XTjh8Km7coM&list=PLWw98q-Xe7iF6gMaE7Yv8ATbe0z78O9yG

Clone the repository: https://github.com/mailrocketsystems/jetson-train

In this video, we will see how we can train SSD-MOBILENET model for your own custom object detection. For this video, we have used images for apples and banana and we have trained a model for this. Training has been performed on Ubuntu machine and then we have used #jetson #xavier to run that model.

If you want to train your own model, follow the steps mentioned in the repository and you will be able to train your model very easily.

Introduction : (0:00)
Understanding training project: (0:36)
Prepare dataset: (3:14)
Annotation : (5:58)
Create labels file : (9:51)
Training your dragon : (10:27)
Training graph : (13:30)
Using the best dragon : (14:50)
Extracting ONNX file on Jetson : (15:55)
Extracting engine file on Jetson : (17:35)
Inferencing : (19:03)

Contact: mailrocketsystems@gmail.com

source