Hsuan

yes, just like @lijia-xing mentioned. You could change following line in `train.py` ``` restore_var = [v for v in tf.global_variables() if 'conv6' not in v.name] ```

Hey AmeetR If you run through the history issues, you will found that we have discussed this problem several times. Since this repository just convert the pre-trained weight from caffe...

@eris231, I'll fix this bug, thank you.

Hey @amiltonwong , Sorry, there isn't enough time for me to release the training part now. But I have provided the training code of `PSPNet` and `ICNet` in other repos,...

Hi @simon1727 , Thank you for your quick reply. I have checked the split file is correct. And I just found the problem! Please refer to this issue here: https://stackoverflow.com/questions/4813061/non-alphanumeric-list-order-from-os-listdir...

Hi, I'm sorry for your inconvenience, this repository works only with FlyingChairs and FlyingThings now. If you are trying to train on Sintel or Kitti, there are several things to...

Thank you @B-Paweekorn and @zengy5 for pointing out that links are invalid, here is the new link to the trained ResNet101 model: [google drive](https://drive.google.com/file/d/1ydCdS9zE6LejbJwPW888K82GyBOla4oT/view?usp=drive_link)