How to detect more objects with SSD-Mobilenet?

Hi,

I am very new to this and sorry if I am asking something extremely stupid.

So I was following this tutorial

and got a model for detecting fruits.

I thought it would also detect the default object like person, cow in this list

But it only detects fruits.

So are there ways to add more detectable object on top of a model?

Thanks

Hi,

Suppose you have run the retraining process.
When preparing the database with the below command:

$ python3 open_images_downloader.py --class-names "Apple,Orange,Banana,Strawberry,Grape,Pear,Pineapple,Watermelon" --data=data/fruit

It only downloads the fruit category (Apple, Orange, Banana, Strawberry, Grape, Pear, Pineapple, Watermelon).
To train it with more classes, please expand the database with --class-names.

Thanks.

Thank you for your response!

What I want to ask is if it is possible to combine this fruit model and the default model that comes with ssdv2 which can already detect 90 objects, making it detect 100 or more objects.

Thanks.

Hi,

It’s possible.
You will need to merge the database first and retrain a model with all the classes together.

Thanks.

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.