search

JudasDie / SOTS

Single object tracking and segmentation.
484 stars 76 forks source link

[CSTrack] Trained on 640 with batch_size=8 or 10? #17

Closed Junhojuno closed 2 years ago

Junhojuno commented 3 years ago

Now, I keep trying to train a CSTrack model. I set the batch_size=2,4,6,8 and input_size=640 but, I can't train it because of CUDA out of memory error. only a setting(batch_size=1 and input_size=640) operated well... (mainly, CUDA out of error, my computer is set to 2060 super * 2, and used to train on only 1 GPU)

I don't know exactly what is wrong..

I think the CSTrack model is trained on 2080TI with batch_size=8 or 10 and input_size=640.

is it right..?!

H11zang commented 3 years ago

I trained CSTrack on 2080 Ti with batch_size = 8 or 10 and input_size = (1088,608). If you train CSTrack on 1 GPU (2060 memory is 6G）, you can only set the batch_size = 2,4 with the input_size = (1088,608), alternatively reduce the input_size to (640,480) or smaller.

Junhojuno commented 3 years ago

thanks a lot! It should be considered more.