search

gaviotas / AMN

Official PyTorch implementation of "Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds", CVPR2022
39 stars 2 forks source link

the segmentation #6

Closed woqiaow closed 1 year ago

woqiaow commented 2 years ago

Hello, I trained the segmentation network according to the link to deeplabv2 you gave me, using The train_aug.txt (10582) pseudo mask trained the segmentation network, and then verified with val.txt (1449), the result was only 0.03. Among the 21 classes, only the background is recognized, and the results of other classes are 0. Do I need to use a pseudo mask when verifying?

gaviotas commented 1 year ago

Sorry for the late reply.

Please check the following two things.

1) The pseudo-masks were generated correctly (please check the mIoU of the pseudo-mask with train.txt) 2) Please check the pre-trained model for the segmentation network. (e.g., ImageNet pre-trained model or MS-COCO pre-trained model)

Thanks.

woqiaow commented 1 year ago

That's OK. Thank you very much!