AdaptSegNet

AdaptSegNet copied to clipboard

Dear author, I was using this code for my project and I found the discriminator loss is further divided by 2. I am not very clear with GAN and could...

Muming-Zhao

The image after transformation using the mean of imagenet gives darker image. Is this right?  

soans1994

hello author, Did you use the the mirror and scale augmentaions in the dataloader. There are arguments in the dataloader function, but have not been used ? thank you

soans1994

error when loading the pretrained model

1

when I load the pretrained model which is downloaded from http://vllab.ucmerced.edu/ytsai/CVPR18/DeepLab_resnet_pretrained_init-f81d91e8.pth then `torch.load()` will report an error ``` Traceback (most recent call last): File "", line 1, in File "/data1/xxx/software/anaconda3/envs/torch18/lib/python3.8/site-packages/torch/serialization.py",...

TomSheng21

Thank you to share your amazing code! I try to use deeper segmentation network. But after changing the segmentation backbone network, the adversarial loss diverges only after a few steps....

seongwn

Hello i want to train model faster. Could i decrease the NUM_STEPS to 25000? what are the effects of decreasing the NUM_STEPS ? I will be very grateful if you...

farahnazmalekzadeh

License

1

Thank you, @wasidennis! Could you add a license in your repo that better reflects your desire to make this software free only for academic purpose, please? Best,

allansp84

About the training of AdaptSegNet(GTA5 -> Cityscapes) and usage of Synscpaes

1

Thanks for your fantastic sharing code! I have 2 questions about your code: 1. Recently I tried to train your code AdaptSegNet(GTA5 -> Cityscpaes multi ResNet) via PyTorch 1.4. The...

LinfengYuan1997

adv_loss keep increasing during training?

2

I just set lambda-adv-target1 as 0.00 and lambda-adv-target2 as 0. 001 to train the single-level model. All parameters are the same as those set by the author. But I find...

VE-yyq

when I removed the discriminator I found the results GTA5->Cityscapes degraded by 1% only

1

Hi, First, thanks for your paper and your contribution and making you work available to everyone to benefit from it. I trained the network (GTA5->Cityscapes vanilla gan) without backpropagating the...

MoHassoubah