Getting empty training inages.

DLR-RM / AugmentedAutoencoder

Official Code: Implicit 3D Orientation Learning for 6D Object Detection from RGB Images

MIT License

338 stars 97 forks source link

Closed capslocknanda closed 4 years ago

capslocknanda commented 4 years ago

training_images_9999

Describe the bug getting black empty training images

System Info Describe the characteristic of your environment:

Additional context Add any other context about the problem here.

MartinSmeyer commented 4 years ago

Hi, try to change the VERTEX_SCALE parameter in your train config to 1000.

capslocknanda commented 4 years ago

My training image is looking like this. The model surface is not straight. Can you help me with this? should I increase the ANTIALIASING?

training_images_3199

MartinSmeyer commented 4 years ago

Hi, seems like your object has a weird size. Reduce either the Vertex Scale to 100 or try to reduce your rendering distance.

capslocknanda commented 4 years ago

thank you for the information.