An error when training with free-anchor

[jiaminglei-lei]

when trained a model with the config: hv_pointpillars_fpn_sbn-all_free-anchor_4x8_2x_nus-3d.py, encountered an error.

Traceback (most recent call last):
File "/home/.../.pycharm_helpers/pydev/pydevd.py", line 1477, in _exec
pydev_imports.execfile(file, globals, locals) # execute the script
File "/home/.../.pycharm_helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "/home/.../mmdetection3d/tools/train.py", line 226, in
main()
File "/home/.../mmdetection3d/tools/train.py", line 222, in main
meta=meta)
File "/home/.../mmdetection3d/mmdet3d/apis/train.py", line 35, in train_model
meta=meta)
File "/home/.../anaconda3/envs/open-mmlab/lib/python3.6/site-packages/mmdet/apis/train.py", line 170, in train_detector
runner.run(data_loaders, cfg.workflow)
File "/home/.../anaconda3/envs/open-mmlab/lib/python3.6/site-packages/mmcv/runner/epoch_based_runner.py", line 127, in run
python-BaseException
epoch_runner(data_loaders[i], **kwargs)
File "/home/.../anaconda3/envs/open-mmlab/lib/python3.6/site-packages/mmcv/runner/epoch_based_runner.py", line 50, in train
self.run_iter(data_batch, train_mode=True, **kwargs)
File "/home/.../anaconda3/envs/open-mmlab/lib/python3.6/site-packages/mmcv/runner/epoch_based_runner.py", line 30, in run_iter
**kwargs)
File "/home/.../anaconda3/envs/open-mmlab/lib/python3.6/site-packages/mmcv/parallel/data_parallel.py", line 67, in train_step
return self.module.train_step(*inputs[0], **kwargs[0])
File "/home/.../anaconda3/envs/open-mmlab/lib/python3.6/site-packages/mmdet/models/detectors/base.py", line 237, in train_step
losses = self(**data)
File "/home/..../anaconda3/envs/open-mmlab/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/home/.../anaconda3/envs/open-mmlab/lib/python3.6/site-packages/mmcv/runner/fp16_utils.py", line 98, in new_func
return old_func(*args, **kwargs)
File "/home/.../mmdetection3d/mmdet3d/models/detectors/base.py", line 59, in forward
return self.forward_train(**kwargs)
File "/home/.../mmdetection3d/mmdet3d/models/detectors/mvx_two_stage.py", line 279, in forward_train
gt_bboxes_ignore)
File "/home/.../mmdetection3d/mmdet3d/models/detectors/mvx_two_stage.py", line 316, in forward_pts_train
*loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
File "/home/.../anaconda3/envs/open-mmlab/lib/python3.6/site-packages/mmcv/runner/fp16_utils.py", line 186, in new_func
return old_func(*args, **kwargs)
File "/home/.../mmdetection3d/mmdet3d/models/dense_heads/free_anchor3d_head.py", line 212, in loss
bbox_preds_tmp, matched_object_targets_tmp
RuntimeError: Output 0 of UnbindBackward is a view and is being modified inplace. This view is the output of a function that returns multiple views. Such functions do not allow the output views to be modified inplace. You should replace the inplace operation by an out-of-place one.

In other models like pointpillar with anchor_3d_head, this problem will not happen.
Have any idea to solve this problem?

[ZCMax]

Have you made any modifications in your code free_anchor3d_head.py?

[jiaminglei-lei]

no.

[jiaminglei-lei]

I added a clone() in this if block, and it works.
FROM

mmdetection3d/mmdet3d/models/dense_heads/free_anchor3d_head.py

Lines 206 to 209 in 9c7270d

	if self.diff_rad_by_sin:
	bbox_preds_[matched], matched_object_targets = \
	self.add_sin_difference(
	bbox_preds_[matched], matched_object_targets)

TO

And replace all bbox_preds_ with bbox_preds_clone.
I am testing the performance, checking whether it will hurt the accuracy.

Updata:
with batch_size=3, other config keep unchange, I got the mAP=0.4433 and NDS=0.5515.

[clw5180]

jiaminglei-lei

老哥牛批