Mask R-CNN Training Jupyter Notebook Model Quality and Multiple GPU changes

Accelerated Computing Intelligent Video Analytics TAO Toolkit
7

According to the log, there is OOM when you train with two 1080 cards.
Suggest trying:

  1. reduce the bs: try train_batch_size: 1
  2. or train a smaller network. Note that please set width/height to multiples of 64.
    For example, set image_size: “(640, 1024)”
  3. if possible, try other cards, for example, v100