memory_size，memory_per_class about pycil HOT 5 CLOSED

If the number of pictures in the second increment is much smaller than that in the first increment, how should I set these two parameters

from pycil.

When fixed memory is set to false, memory size is used, which means that we keep memory size images for all the old classes, which means that for each of the k old categories, we keep memory size/k(floor) images.

On the contrary, when fixed memory is set to true, memory_per_class will be used, which means that we will keep memory_per_class images for each category. In other words, its memory size increases with the number of categories.

from pycil.

In most cases, to be fair, when training cifar100 and imagenet100, we set memory size to 2000, and when training imagenet1000, we set memory size to 20000.

from pycil.

When fixed memory is set to false, memory size is used, which means that we keep memory size images for all the old classes, which means that for each of the k old categories, we keep memory size/k(floor) images.

On the contrary, when fixed memory is set to true, memory_per_class will be used, which means that we will keep memory_per_class images for each category. In other words, its memory size increases with the number of categories.

I probably understand. Thank you for your explanation

from pycil.

Thanks for your interests. 😊

from pycil.