Thans for your great work! Now I'm modifying source code to train my own novel dataset and I want to use 20/30 shot training in fintuning phase, but function train has a parameter 'repea_time', it is decided by the foumula repeat_time = 13 - shot_num, so if I use shot 20 or 30, the repeat_time is negative, this will cause no foward and backward process in train function. How should I change the 'repeat_time' parameter and why did you use the formula repeat_time = 13 - shot_num to calculate it?
Hoping your answer and thanks very much!
You can change repeat_time to 2 or 3. The reason why we use this formula is that in the past experiment we hope the lower the shot, the more disturbances to avoid overfitting.
Thans for your great work! Now I'm modifying source code to train my own novel dataset and I want to use 20/30 shot training in fintuning phase, but function
train
has a parameter 'repea_time', it is decided by the foumularepeat_time = 13 - shot_num
, so if I use shot 20 or 30, the repeat_time is negative, this will cause no foward and backward process in train function. How should I change the 'repeat_time' parameter and why did you use the formularepeat_time = 13 - shot_num
to calculate it? Hoping your answer and thanks very much!