You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, I am trying to train OneFormer on the custom dataset and I was able to start the training. But, I have a few questions regarding choosing the right settings. Currently I resued ADE20k config file after editing the number of classes, iterations, and batch size.
What does DETECTIONS_PER_IMAGE do and how to choose the right value?
How to choose the right crop size? and will it impact the training or prediction time?
I have 20k labeled images and I am training on 4 NVIDIA A100 40GB GPUs with batch size 4, what is the minimum number of iterations required to get good results?
The text was updated successfully, but these errors were encountered:
Hi @rono221, thanks for your interest in our work. To answer your questions:
DETECTIONS_PER_IMAGE is the top k queries considered from the total number of queries during the inference stage for the final instance segmentation predictions. Usually, it's fine to set it equal to NUM_QUERIES.
The right crop size depends on your use case. If, during the inference, you want to input high-resolution or low-resolution images, it's beneficial to train with a comparable resolution. The crop size is only used during training, so training with a larger resolution will take more time.
It depends on the number of classes in your dataset as well, but since the size is similar to ADE20K, I would recommend training for 160k iterations to establish a baseline.
Hi, I am trying to train OneFormer on the custom dataset and I was able to start the training. But, I have a few questions regarding choosing the right settings. Currently I resued ADE20k config file after editing the number of classes, iterations, and batch size.
The text was updated successfully, but these errors were encountered: