UserWarning: This overload of nonzero is deprecated

[Abonnen]

🐛 Bug

$venv\lib\site-packages\torchvision\ops\boxes.py:101: UserWarning: This overload of nonzero is deprecated:
	nonzero()
Consider using one of the following signatures instead:
	nonzero(*, bool as_tuple) (Triggered internally at  ..\torch\csrc\utils\python_arg_parser.cpp:766.)
  keep = keep.nonzero().squeeze(1)

similar issue #2154

To Reproduce

Steps to reproduce the behavior:

official example of faster-rcnn

the error occurs in line 129

>>> import torch
>>> import torchvision
>>> from torchvision.models.detection import FasterRCNN
>>> from torchvision.models.detection.rpn import AnchorGenerator
>>> # load a pre-trained model for classification and return
>>> # only the features
>>> backbone = torchvision.models.mobilenet_v2(pretrained=True).features
>>> # FasterRCNN needs to know the number of
>>> # output channels in a backbone. For mobilenet_v2, it's 1280
>>> # so we need to add it here
>>> backbone.out_channels = 1280
>>>
>>> # let's make the RPN generate 5 x 3 anchors per spatial
>>> # location, with 5 different sizes and 3 different aspect
>>> # ratios. We have a Tuple[Tuple[int]] because each feature
>>> # map could potentially have different sizes and
>>> # aspect ratios
>>> anchor_generator = AnchorGenerator(sizes=((32, 64, 128, 256, 512),),
>>>                                    aspect_ratios=((0.5, 1.0, 2.0),))
>>>
>>> # let's define what are the feature maps that we will
>>> # use to perform the region of interest cropping, as well as
>>> # the size of the crop after rescaling.
>>> # if your backbone returns a Tensor, featmap_names is expected to
>>> # be ['0']. More generally, the backbone should return an
>>> # OrderedDict[Tensor], and in featmap_names you can choose which
>>> # feature maps to use.
>>> roi_pooler = torchvision.ops.MultiScaleRoIAlign(featmap_names=['0'],
>>>                                                 output_size=7,
>>>                                                 sampling_ratio=2)
>>>
>>> # put the pieces together inside a FasterRCNN model
>>> model = FasterRCNN(backbone,
>>>                    num_classes=2,
>>>                    rpn_anchor_generator=anchor_generator,
>>>                    box_roi_pool=roi_pooler)
>>> model.eval()
>>> x = [torch.rand(3, 300, 400), torch.rand(3, 500, 400)]
>>> predictions = model(x)

Expected behavior

It is obviously a bug. The expected behavior is to get predictions.

Environment

PyTorch version: 1.6.0
Is debug build: False
CUDA used to build PyTorch: 10.2
ROCM used to build PyTorch: N/A

OS: Microsoft Windows 10 
GCC version: (x86_64-posix-seh-rev0, Built by MinGW-W64 project) 8.1.0
Clang version: Could not collect
CMake version: Could not collect

Python version: 3.6 (64-bit runtime)
Is CUDA available: True
CUDA runtime version: 10.0.130
GPU models and configuration: Could not collect
Nvidia driver version: Could not collect
cuDNN version: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v10.0\bin\cudnn64_7.dll
HIP runtime version: N/A
MIOpen runtime version: N/A

Versions of relevant libraries:
[pip3] numpy==1.19.2
[pip3] torch==1.6.0
[pip3] torchvision==0.7.0
[conda] Could not collect

Additional context

I have fixed the bug by making a minor change:

• modify torchvision.ops.box.py remove_small_boxes()

keep = keep.nonzero(as_tuple=False).squeeze(1)

• modify torchvision.models.detection.roi_heads.py postprocess_detections()

inds = torch.nonzero(scores > self.score_thresh, as_tuple=False).squeeze(1)

I am not sure whether my solution would cause side effects, but at least it can fix this bug.

[fmassa]

Hi,

Thanks for re-raising this issue. I've sent a PR trying to fix this in #2705