Semantic_Human_Matting icon indicating copy to clipboard operation
Semantic_Human_Matting copied to clipboard

Published 20 hours ago • verified publisher icon lizhengwei1992

random_scale_and_creat_patch

Open wwq66 opened this issue 5 years ago • 4 comments

Why should randomly scale and create path of input images? I do not understand why create pathes with randomly selecting areas in the image.

wwq66 avatar Aug 06 '19 13:08 wwq66

When I run ./test_camera.sh (--without_gpu), this error occurred: AttributeError: Can't get attribute 'RD_FPNnet' on <module 'model.T_Net' from '/Users/jasonxin/Documents/dlworkspace/Semantic_Human_Matting/model/T_Net.py'> My torch version is 1.0.0.

Jason-xin avatar Aug 08 '19 04:08 Jason-xin

When I run ./test_camera.sh (--without_gpu), this error occurred: AttributeError: Can't get attribute 'RD_FPNnet' on <module 'model.T_Net' from '/Users/jasonxin/Documents/dlworkspace/Semantic_Human_Matting/model/T_Net.py'> My torch version is 1.0.0.

Suggest that run the code with pytorch 0.4.0 or you will get mistakes.

wwq66 avatar Aug 12 '19 07:08 wwq66

When I run ./test_camera.sh (--without_gpu), this error occurred: AttributeError: Can't get attribute 'RD_FPNnet' on <module 'model.T_Net' from '/Users/jasonxin/Documents/dlworkspace/Semantic_Human_Matting/model/T_Net.py'> My torch version is 1.0.0.

Suggest that run the code with pytorch 0.4.0 or you will get mistakes.

@cqww I have changed it to the pytorch 0.4.0, but the same errors...

Jason-xin avatar Aug 12 '19 08:08 Jason-xin

Why should randomly scale and create path of input images? I do not understand why create pathes with randomly selecting areas in the image.

This is a data augmentation technique for improving the generalization-ability of the model.

xiankgx avatar Aug 29 '19 23:08 xiankgx