OlafenwaMoses / ImageAI

A python library built to empower developers to build applications and systems with self-contained Computer Vision capabilities
https://www.genxr.co/#products
MIT License
8.59k stars 2.19k forks source link

What models will be available for custom object detection once PyTorch is used? #638

Open Zordiac opened 3 years ago

Zordiac commented 3 years ago

Hello everyone,

I was wondering which model will be available for custom object detection once the switch to PyTorch is completed. Will it still be Yolov3 using the DarkNet backend, or will you be using torchvisions models like Faster R-CNN or RetinaNet?

Thanks in advance!

OthmaneJaz commented 3 years ago

Interesting question, I'm looking forward to know what models the new ImageAI version based on PyTorch will provide.