You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am trying to code custom DatasetMapper as provided in the tutorial of detectron2. This mapper is responsible for normalizing the bounding box coordinate for my custom dataset. I am not sure where exactly detectron2 does normalization, if it does so. If you can point out this as well, it would be nice. Currently, I am writing my piece of code for this.
<Traceback (most recent call last):
File "/home/jovyan/.local/lib/python3.8/site-packages/detectron2/engine/train_loop.py", line 134, in train
self.run_step()
File "/home/jovyan/.local/lib/python3.8/site-packages/detectron2/engine/train_loop.py", line 222, in run_step
data = next(self._data_loader_iter)
File "/home/jovyan/.local/lib/python3.8/site-packages/detectron2/data/common.py", line 180, in __iter__
w, h = d["width"], d["height"]
KeyError: 'width'
[02/27 13:52:49 d2.engine.hooks]: Total training time: 0:00:00 (0:00:00 on hooks)
[02/27 13:52:49 d2.utils.events]: iter: 1 lr: N/A max_mem: 199M
Traceback (most recent call last):
File "main.py", line 85, in <module>
launch(
File "/home/jovyan/.local/lib/python3.8/site-packages/detectron2/engine/launch.py", line 62, in launch
main_func(*args)
File "main.py", line 80, in main
return trainer.train()
File "/home/jovyan/thesis_s2577712/DeFRCN_voc_format/thesis-pascal_voc_format/defrcn/engine/defaults.py", line 387, in train
super().train(self.start_iter, self.max_iter)
File "/home/jovyan/.local/lib/python3.8/site-packages/detectron2/engine/train_loop.py", line 134, in train
self.run_step()
File "/home/jovyan/.local/lib/python3.8/site-packages/detectron2/engine/train_loop.py", line 222, in run_step
data = next(self._data_loader_iter)
File "/home/jovyan/.local/lib/python3.8/site-packages/detectron2/data/common.py", line 180, in __iter__
w, h = d["width"], d["height"]
KeyError: 'width'>
Instructions To Reproduce the Issue:
I am trying to code custom DatasetMapper as provided in the tutorial of detectron2. This mapper is responsible for normalizing the bounding box coordinate for my custom dataset. I am not sure where exactly detectron2 does normalization, if it does so. If you can point out this as well, it would be nice. Currently, I am writing my piece of code for this.
Environment:
The text was updated successfully, but these errors were encountered: