Thank you for your amazing work.
I trained and tested light-weight model on my own dataset. However, I found GPU memory usage in testing is much higher than that in training(2.7GB with bs 2 vs 8.8GB with bs 1). I trained model with single GPU and tested it using test_ins.py
Could you kindly help me to solve this issue?
Thank you for your amazing work. I trained and tested light-weight model on my own dataset. However, I found GPU memory usage in testing is much higher than that in training(2.7GB with bs 2 vs 8.8GB with bs 1). I trained model with single GPU and tested it using test_ins.py Could you kindly help me to solve this issue?