Issue with Instance and Panoptic labels using Panoptic deeplab model

[similalwani]

Instructions To Reproduce the Issue:

Modified the colab notebook tutorial from detectron2 in the following way to create panoptic labels using panoptic deeplab model under the directory detectron2/projects for a custom dataset. When I used the Panoptic FPN model from the model zoo, it gives me correct labels but when I use the panoptic deeplab model (link in the code below), there are 2 issues:

1. For 3 out of 10 images, the code below gives a key error for 'instances'.
2. The panoptic labels obtained have the 'pred' tuple values as 8000, 2000, etc and the segments_info is null when it shouldn't be so. (refer this: https://detectron2.readthedocs.io/en/latest/tutorials/models.html#model-output-format)

Changes I made to reproduce issue:

        cfg = get_cfg()
        from detectron2.projects.panoptic_deeplab import add_panoptic_deeplab_config  
        add_panoptic_deeplab_config(cfg)
        # add project-specific config (e.g., TensorMask) here if you're not running a model in detectron2's core library
        cfg.merge_from_file("detectron2/projects/Panoptic-DeepLab/configs/Cityscapes-PanopticSegmentation/panoptic_deeplab_R_52_os16_mg124_poly_90k_bs32_crop_512_1024.yaml")
        cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5  # set threshold for this model
        # Find a model from detectron2's model zoo. You can use the https://dl.fbaipublicfiles... url as well
        cfg.MODEL.WEIGHTS = 'Desktop/detectron2/model_final_bd324a.pkl'
        predictor = DefaultPredictor(cfg)

Environment:

Pasting the output of the following command:

wget -nc -nv https://github.com/facebookresearch/detectron2/raw/main/detectron2/utils/collect_env.py && python collect_env.py

sys.platform                     linux
Python                           3.8.18 (default, Sep 11 2023, 13:40:15) [GCC 11.2.0]
numpy                            1.24.3
detectron2                       0.6 @Desktop/detectron2/detectron2
Compiler                         GCC 9.4
CUDA compiler                    CUDA 12.3
detectron2 arch flags            Desktop/detectron2/detectron2/_C.cpython-38-x86_64-linux-gnu.so; cannot find cuobjdump
DETECTRON2_ENV_MODULE            <not set>
PyTorch                          2.2.0+cu118 @/tools/miniconda3/envs/panoptic/lib/python3.8/site-packages/torch
PyTorch debug build              False
torch._C._GLIBCXX_USE_CXX11_ABI  False
GPU available                    Yes
GPU 0,1,2,3                      NVIDIA H100 PCIe (arch=9.0)
Driver version                   535.86.05
CUDA_HOME                        /tools/miniconda3/envs/panoptic
Pillow                           10.2.0
torchvision                      0.17.0+cu118 @/tools/miniconda3/envs/panoptic/lib/python3.8/site-packages/torchvision
torchvision arch flags           /tools/miniconda3/envs/panoptic/lib/python3.8/site-packages/torchvision/_C.so; cannot find cuobjdump
fvcore                           0.1.5.post20221221
iopath                           0.1.9
cv2                              4.6.0
-------------------------------  ----------------------------------------------------------------------------------------------------
PyTorch built with:
  - GCC 9.3
  - C++ Version: 201703
  - Intel(R) oneAPI Math Kernel Library Version 2022.2-Product Build 20220804 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v3.3.2 (Git Hash 2dc95a2ad0841e29db8b22fbccaf3e5da7992b01)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX512
  - CUDA Runtime 11.8
  - NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_90,code=sm_90
  - CuDNN 8.7
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.8, CUDNN_VERSION=8.7.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=pedantic -Wno-error=old-style-cast -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=2.2.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF,

Please help solve this!

[Programmer-RD-AI]

Hi,
For the given issues check the following..

1. Keyerror : 'image_id'; while evaluation of Custom Dataset with CocoEvaluator() #2431
2. If segments_info is None, all pixel values in pred must be ≥ -1. Pixels with value -1 are assigned void labels. Otherwise, the category id of each pixel is obtained by category_id = pixel // metadata.label_divisor.

and when merging from file add cfg.set_new_allowed(True)

Thank you...