Detectron2: Error decoding masks when training Mask R-CNN

[minhduc0711]

Instructions To Reproduce the Issue:

1. what changes you made (git diff) or what code you wrote

register_coco_instances("corn", {}, "annos.json", ".")

My annotation file looks like this:

"annotations": [
        {
            "id": 2159120,
            "image_id": 2159100,
            "category_id": 2159121,
            "segmentation": {
                "counts": [
                    492904,
                    18,
                    3015,
                    18,
                    .....],
                "size": [
                    3033,
                    2275
                  ]
            },
            "area": 0,
            "bbox": [
                162,
                1502,
                229,
                123
            ],
            "iscrowd": 0
       },
       .....
]

1. what exact command you run:
   I use the same training code in the Getting Started notebook.
2. what you observed (including the full logs):

Traceback (most recent call last):
  File "/usr/local/lib/python3.6/dist-packages/detectron2/engine/train_loop.py", line 132, in train
    self.run_step()
  File "/usr/local/lib/python3.6/dist-packages/detectron2/engine/train_loop.py", line 208, in run_step
    data = next(self._data_loader_iter)
  File "/usr/local/lib/python3.6/dist-packages/detectron2/data/common.py", line 109, in __iter__
    for d in self.dataset:
  File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 345, in __next__
    data = self._next_data()
  File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 856, in _next_data
    return self._process_data(data)
  File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/dataloader.py", line 881, in _process_data
    data.reraise()
  File "/usr/local/lib/python3.6/dist-packages/torch/_utils.py", line 394, in reraise
    raise self.exc_type(msg)
TypeError: Caught TypeError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
    data = fetcher.fetch(index)
  File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/usr/local/lib/python3.6/dist-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/usr/local/lib/python3.6/dist-packages/detectron2/data/common.py", line 39, in __getitem__
    data = self._map_func(self._dataset[cur_idx])
  File "/usr/local/lib/python3.6/dist-packages/detectron2/utils/serialize.py", line 23, in __call__
    return self._obj(*args, **kwargs)
  File "/usr/local/lib/python3.6/dist-packages/detectron2/data/dataset_mapper.py", line 128, in __call__
    for obj in dataset_dict.pop("annotations")
  File "/usr/local/lib/python3.6/dist-packages/detectron2/data/dataset_mapper.py", line 129, in <listcomp>
    if obj.get("iscrowd", 0) == 0
  File "/usr/local/lib/python3.6/dist-packages/detectron2/data/detection_utils.py", line 180, in transform_instance_annotations
    mask = mask_util.decode(segm)
  File "/usr/local/lib/python3.6/dist-packages/pycocotools/mask.py", line 91, in decode
    return _mask.decode([rleObjs])[:,:,0]
  File "pycocotools/_mask.pyx", line 146, in pycocotools._mask.decode
  File "pycocotools/_mask.pyx", line 128, in pycocotools._mask._frString
TypeError: Expected bytes, got list

Expected behavior:

The annotations show up when using the visualizer, but there's the above error when training

Environment:

---

sys.platform linux
Python 3.6.9 (default, Nov 7 2019, 10:44:02) [GCC 8.3.0]
numpy 1.17.5
detectron2 0.1 @/usr/local/lib/python3.6/dist-packages/detectron2
detectron2 compiler GCC 7.3
detectron2 CUDA compiler 10.0
detectron2 arch flags sm_35, sm_37, sm_50, sm_52, sm_60, sm_61, sm_70, sm_75
DETECTRON2_ENV_MODULE
PyTorch 1.4.0+cu100 @/usr/local/lib/python3.6/dist-packages/torch
PyTorch debug build False
CUDA available True
GPU 0 Tesla P100-PCIE-16GB
CUDA_HOME /usr/local/cuda
NVCC Cuda compilation tools, release 10.0, V10.0.130
Pillow 6.2.2
torchvision 0.5.0+cu100 @/usr/local/lib/python3.6/dist-packages/torchvision
torchvision arch flags sm_35, sm_50, sm_60, sm_70, sm_75
cv2 4.1.2

---

PyTorch built with:

• GCC 7.3
• Intel(R) Math Kernel Library Version 2019.0.4 Product Build 20190411 for Intel(R) 64 architecture applications
• Intel(R) MKL-DNN v0.21.1 (Git Hash 7d2fd500bc78936d1d648ca713b901012f470dbc)
• OpenMP 201511 (a.k.a. OpenMP 4.5)
• NNPACK is enabled
• CUDA Runtime 10.0
• NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37
• CuDNN 7.6.3
• Magma 2.5.1
• Build settings: BLAS=MKL, BUILD_NAMEDTENSOR=OFF, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -fopenmp -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -O2 -fPIC -Wno-narrowing -Wall -Wextra -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Wno-stringop-overflow, DISABLE_NUMA=1, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF,

[ppwwyyxx]

Please follow the documentation https://detectron2.readthedocs.io/tutorials/datasets.html and use

╰─$ pycocotools.mask.encode(np.asarray(mask.astype("uint8"), order="F"))                                  
Out[9]: {'size': [30, 30], 'counts': b'Tl0'}

to produce masks at the correct format.

[minhduc0711]

@ppwwyyxx what is mask.astype("uint8") supposed to be? Is it the list of numbers in the counts attribute?

[minhduc0711]

Have you seen my annotations yet? I am not trying to convert binary masks since I've already got RLE I think.

"segmentation": {
                "counts": [
                    492904,
                    18,
                    3015,
                    18,
                    .....],
                "size": [
                    3033,
                    2275
                  ]
            },

I just don't know how to convert this big list of numbers to the byte string that you got above.

[ppwwyyxx]

what is mask.astype("uint8") supposed to be

mask is supposed to be the segmentation mask.

am not trying to convert binary masks since I've already got RLE I think.

Then you need to figure out how to convert "your RLE", whatever it means, into the RLE format pycocotools.mask.encode produces. This is not related to detectron2.

[minhduc0711]

Turns out what I have is uncompressed RLE format. To compress it:

pycocotools.mask.frPyObjects(rle, rle['size'][0], rle['size'][1])

where rle is the uncompressed RLE dict