Not all items detected in picture (just not a big part)

Expected results

I have a list of 250 trained images, like this, (average each image size 1000px X 3000px with ~ 300 polygons in each)

but when I'm trying to check the trained model, only part of the evaluation image successfully masked. What I'm doing wrong?

Actual results

This is the image after prediction:

Not all stones detected.

Detailed steps to reproduce

Trainer configuration:

cfg = get_cfg() cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")) cfg.DATASETS.TRAIN = ("balloon_train",) cfg.DATASETS.TEST = () cfg.DATALOADER.NUM_WORKERS = 2 cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml") cfg.SOLVER.IMS_PER_BATCH = 2 cfg.SOLVER.BASE_LR = 0.01 # pick a good LR cfg.SOLVER.WARMUP_ITERS = 300 cfg.SOLVER.CHECKPOINT_PERIOD = 300 cfg.SOLVER.MAX_ITER = 10000
cfg.SOLVER.STEPS = (1000,) cfg.SOLVER.GAMMA = 0.005 cfg.MODEL.ROI_HEADS.POSITIVE_FRACTION = 0.7 cfg.MODEL.ROI_HEADS.IOU_THRESHOLDS = [0.5] cfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE = 32
cfg.MODEL.ROI_HEADS.NUM_CLASSES = 1 cfg.TEST.EVAL_PERIOD = 300



### System information

sys.platform            linux
Python                  3.6.9 (default, Oct  8 2020, 12:12:24) [GCC 8.4.0]
numpy                   1.18.5
detectron2              0.2.1 @/usr/local/lib/python3.6/dist-packages/detectron2
Compiler                GCC 7.3
CUDA compiler           CUDA 10.1
detectron2 arch flags   sm_35, sm_37, sm_50, sm_52, sm_60, sm_61, sm_70, sm_75
DETECTRON2_ENV_MODULE   <not set>
PyTorch                 1.6.0+cu101 @/usr/local/lib/python3.6/dist-packages/torch
PyTorch debug build     False
GPU available           True
GPU 0                   Tesla T4
CUDA_HOME               /usr/local/cuda
Pillow                  8.0.1
torchvision             0.7.0+cu101 @/usr/local/lib/python3.6/dist-packages/torchvision
torchvision arch flags  sm_35, sm_50, sm_60, sm_70, sm_75
fvcore                  0.1.2.post20201030
cv2                     4.1.2
----------------------  ---------------------------------------------------------------
PyTorch built with:
  - GCC 7.3
  - C++ Version: 201402
  - Intel(R) Math Kernel Library Version 2019.0.5 Product Build 20190808 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v1.5.0 (Git Hash e2ac1fac44c5078ca927cb9b90e1b3066a0b2ed0)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 10.1
  - 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_70,code=sm_70;-gencode;arch=compute_75,code=sm_75
  - CuDNN 7.6.3
  - Magma 2.5.2
  - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -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-unused-local-typedefs -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 -Werror=format -Wno-stringop-overflow, 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,

facebookresearch / Detectron