Jin-Hwa Kim
Jin-Hwa Kim
I checked and confirmed it is able to unzip from this link: https://drive.google.com/file/d/1BmcxeY1kXzMZv54d4wMtl7HGc8Cs9zgO/view If you persist, I will recheck with this link.
I confirmed that the download link has no issue. Unzipping and reading `train.hdf5` works fine, as above screenshot.
@jaesuny do you have access to this?
My mistake. You're right for ResNet32. I would be grateful if the checkpoint is available for reproduction.
Incorrect Docker image link. Please redirect to [https://hub.docker.com/r/minyelee/dok2qa](https://hub.docker.com/r/minyelee/dok2qa).
Regrettably, the link is no longer accessible, and I cannot perform maintenance due to the loss of the materials. :(
The argument of `resume` should be the number of iterations you trained and the file name should be changed accordingly in my understanding. Please refer to https://github.com/jwyang/graph-rcnn.pytorch/blob/master/lib/scene_parser/rcnn/utils/checkpoint.py#L54 .
@jgyy4775 Sorry but could you elaborate your question?
I think `args.mode` is not used and deprecated. Could you confirm this, @jwyang ?
Presumably, the same license for KolektorSDD2?