Zhongyi Shui

Dear all, Thanks for the awesome work. I use the config file 'p2p_r50_fpns4_1x_fl_sl1_coco.py' to train P2PNet with the center annotations. But only 50.25 mAP is achieved. What should I do...

import os import SimpleITK as sitk import numpy as np data = np.load("ct/trn00022.npz") ct_data = data["ct"] ct = sitk.GetImageFromArray(ct_data) ct = sitk.Cast(ct, sitk.sitkInt16) ct.SetSpacing((0.8, 0.8, 0.8)) orientation = [1, 0,...

Memory Usage Continuously Increases During Pretraining Until Process is Killed

1


How about the performance of directly generating the (bit encoded) panoptic mask conditioned on an image?