Jensen-Su

Confused about the shape of relative position encoding

4

The following code generates a position embedding of shape ` (C, K, K)`, where `C=self.group_planes*2, K=self.kernel_size`: https://github.com/csrhddlam/axial-deeplab/blob/fe1d0523faa7b3068ee59ab13f222a46c511d0aa/lib/models/axialnet.py#L64 It seems that each position in the `(K, K)` window owns a position...

OSError: [Errno 4] Interrupted system call

1

Err... error jumps out: ```python Traceback (most recent call last): File "train_multi_task.py", line 200, in experiment(config) File "train_multi_task.py", line 88, in experiment data_list.append(iter_.next()) File "/usr/local/lib/python2.7/dist-packages/torch/utils/data/dataloader.py", line 267, in __next__ idx,...

As a quick reproduction, I simply added the following class to file `model_multi_task.py`: ```python class AlexnetNoFc(nn.Module): def __init__(self): super(AlexnetNoFc, self).__init__() alexnet = models.alexnet(pretrained=True) self.features = alexnet.features self.classifier = nn.Sequential() for...

request for the paper

1

Seems to be an interesting work. Could you please send me ([email protected]) a copy of the paper please? Thanks a million!