Wuyang

Hi @AliLotfi92, Thanks for your interest in our work! We use `model.eval()` because we want to keep the BN statistics learned in the pretrained checkpoint (e.g. from ImageNet) remain intact...

@AliLotfi92 The `fc_new` is learning features from the new domain. It is randomly initialized, instead of having a pretrained checkpoint to load from.

We used public released deeplabv3+ implementation [here](https://github.com/kazuto1011/deeplab-pytorch/blob/master/libs/models/deeplabv3plus.py). Github repo for pspnet and segnet are [here](https://github.com/meetshah1995/pytorch-semseg). I think different networks have the different capabilities of feature learning on different datasets, like...

1. For light-weight models (UNet, ICNet) we used `learning_rate = 1e-4`. For other models we used `learning_rate = 2e-5`. Details about batch size and input size can be found in...

Hi @thomasverelst! Thank you very much for your interest in our work! In our paper, we report the mIoU on the test set, not the validation set.

Hi @oshindutta, Thanks for your interest in our work! The "four GPU hours" is verified multiple times, so it is valid. Possible reasons might be on other hardware sides: the...

> @chenxiaoyu523 Yes. In the speed experiments, we use the low-scale labels for the fast inference speed, which is mentioned in our paper. Hi @ycszen! Did you mean you used...

Looking forward to the code release! Thank you!

I don't think it is because of the over-fitting. I found one line missing in the Pre-Trained LSTM.ipynb when loading the wordsList: `wordsList = [word.decode('UTF-8') for word in wordsList] #Encode...