search

DLR-RM / AugmentedAutoencoder

Official Code: Implicit 3D Orientation Learning for 6D Object Detection from RGB Images
MIT License
338 stars 97 forks source link

[question] How to evaluate the model with object detector? #52

Closed kshpv closed 4 years ago

kshpv commented 4 years ago
  1. I trained Autoencoder for my 3d model
  2. I trained keras-retinanet for detecting my object. How can I evaluate the whole system to get 6DOF of the object in a single RGB image? Thank you!
MartinSmeyer commented 4 years ago

Hi Alexey, simply adapt aae_retina_image_pose.py to input your image: https://github.com/DLR-RM/AugmentedAutoencoder#multi-object-rgb-based-6d-object-detection-from-a-webcam-stream I will push a script for single image processing soon.