jshtok
commented
4 years ago Hi Duynn,
The set of samples is selected once and for all epochs in loader.py \ PyramidAnchorIterator.balance_classes().
Regards, Joseph
On Mon, Mar 9, 2020 at 10:08 AM duynn912 notifications@github.com wrote:
Hi @jshtok https://github.com/jshtok,
According to a training issue, I found that you mentioned RepMet used 200 samples in per class for the first 101 classes of ImageNetLOC and 20 classes of PASCAL and there is a parameter in config.py to control them. Is it right? My problem here is that these 200 samples are fixed images chosen from the total images of ImageNetLOC and PASCAL for each class in each epoch or 200 samples are picked up randomly from the total images in each epoch?
Hope to hear your answer soon! Best regards, Duynn
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/jshtok/RepMet/issues/26?email_source=notifications&email_token=ACOBU6XCO5ZVHQHZ4HMLUR3RGSPWNA5CNFSM4LEDFTGKYY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4ITPMKTA, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACOBU6VPKOKDS5RIOVTVKOLRGSPWNANCNFSM4LEDFTGA .
Hi @jshtok,
According to a training issue, I found that you mentioned RepMet used 200 samples in per class for the first 101 classes of ImageNetLOC and 20 classes of PASCAL and there is a parameter in config.py to control them. Is it right? My problem here is that these 200 samples are fixed images chosen from the total images of ImageNetLOC and PASCAL for each class in each epoch or 200 samples are picked up randomly from the total images in each epoch?
Hope to hear your answer soon! Best regards, Duynn