search

dyabel / detpro

Apache License 2.0
171 stars 26 forks source link

Having issues reproducing DetPro #36

Open Con6924 opened 1 year ago

Con6924 commented 1 year ago

Hi! Thanks for your great work! Following your code and instructions, I'm trying to reproduce the Mask-RCNN results on LVIS. Using the same experiment setting provided in the code on 8 * V100 GPUs, the evaluation results of detpro_20e_ens.py are 11.7/26.7/32.8/26.5 (AP_r/AP_c/AP_f/AP). I also tried to replace the learned prompts fg_bg_5_10_end_ens.pth with your provided iou_neg5_ens.pth, but the performances are similar - 13.4/26.4/32.7/26.6. I wonder if there should be any modification in the current code in order to reproduce the given results. Besides, is there any difference between the mentioned two learned prompts above? Thanks for your kindful reply in advance!

Fangyi-Chen commented 1 year ago

Any follow-up under this thread?