pix2pixHD icon indicating copy to clipboard operation
pix2pixHD copied to clipboard

Published 20 hours ago • verified publisher icon NVIDIA

Bad results when testing

Open ShaniGam opened this issue 5 years ago • 6 comments

I train the model on 2975 images from the cityscapes dataset with the following command: python train.py --name label2city_512p_feat_cityscapes --instance_feat The outputs I get during the training seem fine: epoch054_160500_synthesized_image epoch055_161000_synthesized_image

But when I test the model (on images from the training set) I get:

aachen_000004_000019_gtFine_labelIds_synthesized_image aachen_000010_000019_gtFine_labelIds_synthesized_image

Does anyone has an idea of why it happens?

ShaniGam avatar Nov 05 '19 07:11 ShaniGam

overfitting

cszer avatar Jan 28 '20 16:01 cszer

Did you solve the problem? I also meet with this problem during testing.

wang-zm18 avatar Oct 04 '20 09:10 wang-zm18

can we add a validation set to prevent overfitting in pix2pixHD model? I haven't seen anyone done this before.

yxwang1794 avatar Jan 20 '21 02:01 yxwang1794

overfitting

I don't think it's because overfitting. He says that he is "Testing the model with images from the training set". If it is overfitting. It shouldn't work with any other images but with images the model was trained with should work.

I'm having this same issue, with no good outcome yet.

edd2110-jac avatar Jul 13 '21 18:07 edd2110-jac

I'm having this same issue, How did you fix it? @ShaniGam @wang-zm18 @cszer @yxwang1794 @edd2110-jac

songyn95 avatar Jun 17 '22 06:06 songyn95