Trained with custom dataset model results

I prepared custom dataset that 7000 images has only floor class and added to ade20k dataset. Now i have dataset with 28000 images. I changed floor annotations color with #040404 in my dataset, because floor class had that color in ADE20K dataset. So my floor annotation looks like this;
(#040404 color is very close to black. If you look carefully you will see the floor annotation)

and original images;

It seems everything normal my dataset. Then i changed start_epoch and num_epoch values in config yaml file,
`num_epoch: 23
start_epoch: 20
epoch_iters: 5000` .
Training process done with successfully and i have encoder and decoder model that names are encoder_epoch_23.pth, decoder_epoch_23.pth. Everything is seems normal here as well

I got results using theses models but result was not as expected.
I got this result when i download model from here [decoder_epoch_20.pth](http://sceneparsing.csail.mit.edu/model/pytorch/ade20k-resnet50dilated-ppm_deepsup/decoder_epoch_20.pth)

And i got this result when using i trained model;


Results seem to be getting worse. What could i be doing wrong?