detectron2: Error on run demo.py for Panoptic-DeepLab

Hello,

I tested the projet “Panoptic-DeepLab” by using demo.py (changed “import add_panoptic_deeplab_config, setting config” ) but I got error like below. ------------------------ log ---------------------------------------------------------------------- sem_seg_head.predictor.{bias, weight} 0%| | 0/1 [00:00<?, ?it/s] Traceback (most recent call last): File “demopan.py”, line 92, in <module> predictions, visualized_output = demo.run_on_image(img) File “/home/appuser/detectron2/demo/predictor.py”, line 48, in run_on_image predictions = self.predictor(image) File “/home/appuser/detectron2/detectron2/engine/defaults.py”, line 217, in call predictions = self.model([inputs])[0] File “/home/appuser/.local/lib/python3.6/site-packages/torch/nn/modules/module.py”, line 550, in call result = self.forward(*input, **kwargs) File “/home/appuser/detectron2/projects/Panoptic-DeepLab/panoptic_deeplab/panoptic_seg.py”, line 104, in forward sem_seg_results, sem_seg_losses = self.sem_seg_head(features, targets, weights) File “/home/appuser/.local/lib/python3.6/site-packages/torch/nn/modules/module.py”, line 550, in call result = self.forward(*input, **kwargs) File “/home/appuser/detectron2/projects/Panoptic-DeepLab/panoptic_deeplab/panoptic_seg.py”, line 301, in forward y = self.layers(features) File “/home/appuser/detectron2/projects/Panoptic-DeepLab/panoptic_deeplab/panoptic_seg.py”, line 312, in layers y = super().layers(features) File “/home/appuser/detectron2/projects/DeepLab/deeplab/semantic_seg.py”, line 221, in layers proj_x = self.decoder[f]“project_conv” File “/home/appuser/.local/lib/python3.6/site-packages/torch/nn/modules/module.py”, line 550, in call result = self.forward(*input, **kwargs) File “/home/appuser/detectron2/detectron2/layers/aspp.py”, line 114, in forward “Input size: {} pool_kernel_size: {}”.format(size, self.pool_kernel_size) ValueError: pool_kernel_size must be divisible by the shape of inputs. Input size: torch.Size([64, 114]) pool_kernel_size: (32, 64) …