Closed 1201amit closed 3 years ago
I have the same problem. @bowenc0221 Can you provide a .pth pre-trained model of ResNet52 for cityscapes panoptic segmentation? Thanks!
The issue is that panoptic-deeplab (this workspace) and detectron2 Panoptic-DeepLab have different key values in model parameters and given weights follow detectron2 keys. Best way is to create a model using detectron2 Panoptic-DeepLab.
@suyuzhang
The .pkl
file for ResNet52 is converted from this code: https://github.com/facebookresearch/detectron2/blob/master/tools/convert-torchvision-to-d2.py
The model
field is the corresponding .pth
weights with some key conversion.
I am getting runtime error("Invalid magic number; corrupt file?") while loading pickle weights.