errors when training pointsup

[yejr0229]

when I use this scrip "python train_net.py --config-file configs/mask_rcnn_R_50_FPN_3x_point_sup_point_aug_coco.yaml --num-gpus 2" to train pointsup,I use 2 3090gpus,then I encountered this error,I use '1.8.0+cu111'

[github-actions]

You've chosen to report an unexpected problem or bug. Unless you already know the root cause of it, please include details about it by filling the issue template.
The following information is missing: "Instructions To Reproduce the Issue and Full Logs"; "Your Environment";

[yejr0229]

there is the whole error:

Traceback (most recent call last):
File "train_net.py", line 115, in
args=(args,),
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/detectron2/engine/launch.py", line 79, in launch
daemon=False,
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 230, in spawn
return start_processes(fn, args, nprocs, join, daemon, start_method='spawn')
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 188, in start_processes
while not context.join():
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 150, in join
raise ProcessRaisedException(msg, error_index, failed_process.pid)
torch.multiprocessing.spawn.ProcessRaisedException:

-- Process 1 terminated with the following error:
Traceback (most recent call last):
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/torch/multiprocessing/spawn.py", line 59, in _wrap
fn(i, *args)
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/detectron2/engine/launch.py", line 126, in _distributed_worker
main_func(*args)
File "/home/usr/detectron2/projects/PointSup/train_net.py", line 103, in main
return trainer.train()
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/detectron2/engine/defaults.py", line 484, in train
super().train(self.start_iter, self.max_iter)
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/detectron2/engine/train_loop.py", line 149, in train
self.run_step()
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/detectron2/engine/defaults.py", line 494, in run_step
self._trainer.run_step()
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/detectron2/engine/train_loop.py", line 267, in run_step
data = next(self._data_loader_iter)
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/detectron2/data/common.py", line 234, in iter
for d in self.dataset:
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 517, in next
data = self._next_data()
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1199, in _next_data
return self._process_data(data)
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1225, in _process_data
data.reraise()
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/torch/_utils.py", line 429, in reraise
raise self.exc_type(msg)
TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 202, in _worker_loop
data = fetcher.fetch(index)
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 28, in fetch
data.append(next(self.dataset_iter))
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/detectron2/data/common.py", line 201, in iter
yield self.dataset[idx]
File "/home/usr/miniconda3/envs/detectron2/lib/python3.7/site-packages/detectron2/data/common.py", line 90, in getitem
data = self._map_func(self._dataset[cur_idx])
File "/home/usr/detectron2/projects/PointSup/point_sup/dataset_mapper.py", line 115, in call
for obj in dataset_dict.pop("annotations")
File "/home/usr/detectron2/projects/PointSup/point_sup/dataset_mapper.py", line 116, in
if obj.get("iscrowd", 0) == 0
File "/home/usr/detectron2/projects/PointSup/point_sup/detection_utils.py", line 86, in transform_instance_annotations
annotation, transforms, image_size, keypoint_hflip_indices
TypeError: transform_instance_annotations() takes 3 positional arguments but 4 were given

[yejr0229]

I use this scrip "python train_net.py --config-file configs/mask_rcnn_R_50_FPN_3x_point_sup_point_aug_coco.yaml --num-gpus 2" to train pointsup,I use 2 3090gpus,then I encountered this error,I use '1.8.0+cu111'

[zqy1]

I'm having the same problem.

[Khola-naseem]

I resolved this issue by passing keypoint_hflip_indices as a keyword argument line 85 in point_sup/detection_utils.py file
Replace this
annotation = base_transform_instance_annotations(annotation, transforms, image_size, keypoint_hflip_indices)
with this:
annotation = base_transform_instance_annotations( annotation, transforms, image_size, keypoint_hflip_indices=keypoint_hflip_indices)