search

HsinYingLee / OPN

46 stars 13 forks source link

Finetuning scheme #9

Open shubhamjha97 opened 5 years ago

shubhamjha97 commented 5 years ago

How do you finetune on the action recognition datasets? The datasets contain videos. Do you randomly extract frames from the videos? What is the size of the frames that you use?

HsinYingLee commented 5 years ago

Yes, I randomly select one frame each time. The frame size is 224. The initial learning rate is 0.01, I drop the learning rate by 0.1 when the validation loss does not decrease anymore.