AttributeError: Cannot find field 'gt_masks' in the given Instances!

[stoic-signs]

If you do not know the root cause of the problem, please post according to this template:

Instructions To Reproduce the Issue:

Check https://stackoverflow.com/help/minimal-reproducible-example for how to ask good questions.
Simplify the steps to reproduce the issue using suggestions from the above link, and provide them below:

1. Full runnable code or full changes you made:
   Here's my model config, based on the mask rcnn config provided, with the mask heads removed:

model = L(GeneralizedRCNN)(
    backbone=L(FPN)(
        bottom_up=L(ResNet)(
            stem=L(BasicStem)(in_channels=3, out_channels=64, norm="FrozenBN"),
            stages=L(ResNet.make_default_stages)(
                depth=50,
                stride_in_1x1=True,
                norm="FrozenBN",
            ),
            out_features=["res2", "res3", "res4", "res5"],
        ),
        in_features="${.bottom_up.out_features}",
        out_channels=256,
        top_block=L(LastLevelMaxPool)(),
    ),
    proposal_generator=L(RPN)(
        in_features=["p2", "p3", "p4", "p5", "p6"],
        head=L(StandardRPNHead)(in_channels=256, num_anchors=3),
        anchor_generator=L(DefaultAnchorGenerator)(
            sizes=[[32], [64], [128], [256], [512]],
            aspect_ratios=[0.5, 1.0, 2.0],
            strides=[4, 8, 16, 32, 64],
            offset=0.0,
        ),
        anchor_matcher=L(Matcher)(
            thresholds=[0.3, 0.7], labels=[0, -1, 1], allow_low_quality_matches=True
        ),
        box2box_transform=L(Box2BoxTransform)(weights=[1.0, 1.0, 1.0, 1.0]),
        batch_size_per_image=256,
        positive_fraction=0.5,
        pre_nms_topk=(2000, 1000),
        post_nms_topk=(1000, 1000),
        nms_thresh=0.7,
    ),
    roi_heads=L(StandardROIHeads)(
        num_classes=80,
        batch_size_per_image=512,
        positive_fraction=0.25,
        proposal_matcher=L(Matcher)(
            thresholds=[0.5], labels=[0, 1], allow_low_quality_matches=False
        ),
        box_in_features=["p2", "p3", "p4", "p5"],
        box_pooler=L(ROIPooler)(
            output_size=7,
            scales=(1.0 / 4, 1.0 / 8, 1.0 / 16, 1.0 / 32),
            sampling_ratio=0,
            pooler_type="ROIAlignV2",
        ),
        box_head=L(FastRCNNConvFCHead)(
            input_shape=ShapeSpec(channels=256, height=7, width=7),
            conv_dims=[],
            fc_dims=[1024, 1024],
        ),
        box_predictor=L(FastRCNNOutputLayers)(
            input_shape=ShapeSpec(channels=1024),
            test_score_thresh=0.05,
            box2box_transform=L(Box2BoxTransform)(weights=(10, 10, 5, 5)),
            num_classes="${..num_classes}",
        ),
    ),
    pixel_mean=constants.imagenet_bgr256_mean,
    pixel_std=constants.imagenet_bgr256_std,
    input_format="BGR",
)
model.pixel_mean = [123.675, 116.28, 103.53]
model.pixel_std = [58.395, 57.12, 57.375]
model.input_format = "RGB"

model.roi_heads.num_classes = len(model_classes)

train = model_zoo.get_config("common/train.py").train
train.amp.enabled = True
train.ddp.fp16_compression = True
train.init_checkpoint = "detectron2://COCO-Detection/faster_rcnn_R_50_FPN_3x/137849458/model_final_280758.pkl"
dataloader = model_zoo.get_config("common/data/coco.py").dataloader
dataloader.train.mapper.augmentations = [
	L(T.RandomFlip)(horizontal=True),  # flip first
	L(T.RandomApply)(tfm_or_aug=L(T.RandomBrightness)(intensity_min=0.5,intensity_max=1.5),prob=0.3),
	L(T.RandomApply)(tfm_or_aug=L(T.RandomCrop)(crop_type='relative_range',crop_size=[0.7,0.7]),prob=0.4),
	L(T.ResizeShortestEdge)(short_edge_length=min_edge_range, sample_style="range",max_size=max_size)
]
dataloader.train.mapper.image_format = "RGB"
# recompute boxes due to cropping
dataloader.train.mapper.recompute_boxes = True

dataloader.test.mapper.augmentations = [
	L(T.ResizeShortestEdge)(short_edge_length=min_edge_range[1], max_size=max_size),
]
dataloader.test.mapper.recompute_boxes = True

Here's the model output during runtime:

[05/03 14:14:25 detectron2]: Model:
GeneralizedRCNN(
  (backbone): FPN(
    (fpn_lateral2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
    (fpn_output2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (fpn_lateral3): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1))
    (fpn_output3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (fpn_lateral4): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))
    (fpn_output4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (fpn_lateral5): Conv2d(2048, 256, kernel_size=(1, 1), stride=(1, 1))
    (fpn_output5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (top_block): LastLevelMaxPool()
    (bottom_up): ResNet(
      (stem): BasicStem(
        (conv1): Conv2d(
          3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False
          (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
        )
      )
      (res2): Sequential(
        (0): BottleneckBlock(
          (shortcut): Conv2d(
            64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
          )
          (conv1): Conv2d(
            64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
          )
          (conv2): Conv2d(
            64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
          )
          (conv3): Conv2d(
            64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
          )
        )
        (1): BottleneckBlock(
          (conv1): Conv2d(
            256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
          )
          (conv2): Conv2d(
            64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
          )
          (conv3): Conv2d(
            64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
          )
        )
        (2): BottleneckBlock(
          (conv1): Conv2d(
            256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
          )
          (conv2): Conv2d(
            64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=64, eps=1e-05)
          )
          (conv3): Conv2d(
            64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
          )
        )
      )
      (res3): Sequential(
        (0): BottleneckBlock(
          (shortcut): Conv2d(
            256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
          )
          (conv1): Conv2d(
            256, 128, kernel_size=(1, 1), stride=(2, 2), bias=False
            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
          )
          (conv2): Conv2d(
            128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
          )
          (conv3): Conv2d(
            128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
          )
        )
        (1): BottleneckBlock(
          (conv1): Conv2d(
            512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
          )
          (conv2): Conv2d(
            128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
          )
          (conv3): Conv2d(
            128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
          )
        )
        (2): BottleneckBlock(
          (conv1): Conv2d(
            512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
          )
          (conv2): Conv2d(
            128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
          )
          (conv3): Conv2d(
            128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
          )
        )
        (3): BottleneckBlock(
          (conv1): Conv2d(
            512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
          )
          (conv2): Conv2d(
            128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=128, eps=1e-05)
          )
          (conv3): Conv2d(
            128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
          )
        )
      )
      (res4): Sequential(
        (0): BottleneckBlock(
          (shortcut): Conv2d(
            512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False
            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
          )
          (conv1): Conv2d(
            512, 256, kernel_size=(1, 1), stride=(2, 2), bias=False
            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
          )
          (conv2): Conv2d(
            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
          )
          (conv3): Conv2d(
            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
          )
        )
        (1): BottleneckBlock(
          (conv1): Conv2d(
            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
          )
          (conv2): Conv2d(
            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
          )
          (conv3): Conv2d(
            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
          )
        )
        (2): BottleneckBlock(
          (conv1): Conv2d(
            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
          )
          (conv2): Conv2d(
            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
          )
          (conv3): Conv2d(
            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
          )
        )
        (3): BottleneckBlock(
          (conv1): Conv2d(
            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
          )
          (conv2): Conv2d(
            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
          )
          (conv3): Conv2d(
            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
          )
        )
        (4): BottleneckBlock(
          (conv1): Conv2d(
            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
          )
          (conv2): Conv2d(
            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
          )
          (conv3): Conv2d(
            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
          )
        )
        (5): BottleneckBlock(
          (conv1): Conv2d(
            1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
          )
          (conv2): Conv2d(
            256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=256, eps=1e-05)
          )
          (conv3): Conv2d(
            256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=1024, eps=1e-05)
          )
        )
      )
      (res5): Sequential(
        (0): BottleneckBlock(
          (shortcut): Conv2d(
            1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False
            (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
          )
          (conv1): Conv2d(
            1024, 512, kernel_size=(1, 1), stride=(2, 2), bias=False
            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
          )
          (conv2): Conv2d(
            512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
          )
          (conv3): Conv2d(
            512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
          )
        )
        (1): BottleneckBlock(
          (conv1): Conv2d(
            2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
          )
          (conv2): Conv2d(
            512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
          )
          (conv3): Conv2d(
            512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
          )
        )
        (2): BottleneckBlock(
          (conv1): Conv2d(
            2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
          )
          (conv2): Conv2d(
            512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=512, eps=1e-05)
          )
          (conv3): Conv2d(
            512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False
            (norm): FrozenBatchNorm2d(num_features=2048, eps=1e-05)
          )
        )
      )
    )
  )
  (proposal_generator): RPN(
    (rpn_head): StandardRPNHead(
      (conv): Conv2d(
        256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)
        (activation): ReLU()
      )
      (objectness_logits): Conv2d(256, 3, kernel_size=(1, 1), stride=(1, 1))
      (anchor_deltas): Conv2d(256, 12, kernel_size=(1, 1), stride=(1, 1))
    )
    (anchor_generator): DefaultAnchorGenerator(
      (cell_anchors): BufferList()
    )
  )
  (roi_heads): StandardROIHeads(
    (box_pooler): ROIPooler(
      (level_poolers): ModuleList(
        (0): ROIAlign(output_size=(7, 7), spatial_scale=0.25, sampling_ratio=0, aligned=True)
        (1): ROIAlign(output_size=(7, 7), spatial_scale=0.125, sampling_ratio=0, aligned=True)
        (2): ROIAlign(output_size=(7, 7), spatial_scale=0.0625, sampling_ratio=0, aligned=True)
        (3): ROIAlign(output_size=(7, 7), spatial_scale=0.03125, sampling_ratio=0, aligned=True)
      )
    )
    (box_head): FastRCNNConvFCHead(
      (flatten): Flatten(start_dim=1, end_dim=-1)
      (fc1): Linear(in_features=12544, out_features=1024, bias=True)
      (fc_relu1): ReLU()
      (fc2): Linear(in_features=1024, out_features=1024, bias=True)
      (fc_relu2): ReLU()
    )
    (box_predictor): FastRCNNOutputLayers(
      (cls_score): Linear(in_features=1024, out_features=8, bias=True)
      (bbox_pred): Linear(in_features=1024, out_features=28, bias=True)
    )
  )
)

2. What exact command you run:

python lazyconfig_train_net.py --config-file config.py

3. Full logs or other relevant observations:

Traceback (most recent call last):
  File "/home/ubuntu/Trainer/detectron2/detectron2/engine/train_loop.py", line 149, in train
    self.run_step()
  File "/home/ubuntu/Trainer/detectron2/detectron2/engine/train_loop.py", line 404, in run_step
    data = next(self._data_loader_iter)
  File "/home/ubuntu/Trainer/detectron2/detectron2/data/common.py", line 234, in __iter__
    for d in self.dataset:
  File "/home/ubuntu/miniconda3/envs/detectron/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 517, in __next__
    data = self._next_data()
  File "/home/ubuntu/miniconda3/envs/detectron/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1199, in _next_data
    return self._process_data(data)
  File "/home/ubuntu/miniconda3/envs/detectron/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1225, in _process_data
    data.reraise()
  File "/home/ubuntu/miniconda3/envs/detectron/lib/python3.8/site-packages/torch/_utils.py", line 429, in reraise
    raise self.exc_type(msg)
AttributeError: Caught AttributeError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/home/ubuntu/miniconda3/envs/detectron/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 202, in _worker_loop
    data = fetcher.fetch(index)
  File "/home/ubuntu/miniconda3/envs/detectron/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 28, in fetch
    data.append(next(self.dataset_iter))
  File "/home/ubuntu/Trainer/detectron2/detectron2/data/common.py", line 201, in __iter__
    yield self.dataset[idx]
  File "/home/ubuntu/Trainer/detectron2/detectron2/data/common.py", line 90, in __getitem__
    data = self._map_func(self._dataset[cur_idx])
  File "/home/ubuntu/Trainer/detectron2/detectron2/utils/serialize.py", line 26, in __call__
    return self._obj(*args, **kwargs)
  File "/home/ubuntu/Trainer/detectron2/detectron2/data/dataset_mapper.py", line 189, in __call__
    self._transform_annotations(dataset_dict, transforms, image_shape)
  File "/home/ubuntu/Trainer/detectron2/detectron2/data/dataset_mapper.py", line 141, in _transform_annotations
    instances.gt_boxes = instances.gt_masks.get_bounding_boxes()
  File "/home/ubuntu/Trainer/detectron2/detectron2/structures/instances.py", line 68, in __getattr__
    raise AttributeError("Cannot find field '{}' in the given Instances!".format(name))
AttributeError: Cannot find field 'gt_masks' in the given Instances!

Expected behavior:

The model should start training without issue. I referred to #485 , but I'm using a detection model with bbox annotations.
Not sure what is going on. The model weights from "detectron2://COCO-Detection/faster_rcnn_R_50_FPN_3x/137849458/model_final_280758.pkl" load fine, too.
A sample of my dataset:

{'file_name': '1713252303077.jpg', 'image_id': 71, 'height': 3000, 'width': 4000, 'annotations': [{'bbox': [61, 820, 3982, 2080], 'bbox_mode': <BoxMode.XYXY_ABS: 0>, 'category_id': 3}]}

Environment:

The detectron2 is locally built from a fork without any changes.

----------------------  -------------------------------------------------------------------------------------------
sys.platform            linux
Python                  3.8.19 (default, Mar 20 2024, 19:58:24) [GCC 11.2.0]
numpy                   1.24.4
detectron2              0.6 @/home/ubuntu/Trainer/detectron2/detectron2
Compiler                GCC 11.4
CUDA compiler           not available
DETECTRON2_ENV_MODULE   <not set>
PyTorch                 1.8.2+cu102 @/home/ubuntu/miniconda3/envs/detectron/lib/python3.8/site-packages/torch
PyTorch debug build     False
GPU available           Yes
GPU 0                   Tesla T4 (arch=7.5)
Driver version          535.171.04
CUDA_HOME               None - invalid!
Pillow                  10.3.0
torchvision             0.9.2+cu102 @/home/ubuntu/miniconda3/envs/detectron/lib/python3.8/site-packages/torchvision
torchvision arch flags  /home/ubuntu/miniconda3/envs/detectron/lib/python3.8/site-packages/torchvision/_C.so
fvcore                  0.1.5.post20221221
iopath                  0.1.9
cv2                     4.9.0
----------------------  -------------------------------------------------------------------------------------------
PyTorch built with:
  - GCC 7.3
  - C++ Version: 201402
  - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v1.7.0 (Git Hash 7aed236906b1f7a05c0917e5257a1af05e9ff683)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 10.2
  - 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
  - CuDNN 7.6.5
  - Magma 2.5.2
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=10.2, CUDNN_VERSION=7.6.5, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -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-psabi -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, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.8.2, 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=ON, USE_NNPACK=ON, USE_OPENMP=ON,

[stoic-signs]

Okay, looks like I found the issue: recompute_boxes requires gt_masks to get tighter bounding boxes when cropping.
I removed that and it seems to work fine now.
Follow-up question: when using the ResizeShortestEdge augmentation, I assume the bounding boxes are automatically scaled. Is this true? And is there any way to use cropping and recomputing bboxes when gt_mask isn't available?

[function2-llx]

when using the ResizeShortestEdge augmentation, I assume the bounding boxes are automatically scaled. Is this true?

This seems to be true, annotations are applied with the same set of transforms:

detectron2/detectron2/data/dataset_mapper.py

Lines 124 to 130 in 2a420ed

	annos = [
	utils.transform_instance_annotations(
	obj, transforms, image_shape, keypoint_hflip_indices=self.keypoint_hflip_indices
	)
	for obj in dataset_dict.pop("annotations")
	if obj.get("iscrowd", 0) == 0
	]

And is there any way to use cropping and recomputing bboxes when gt_mask isn't available?

So, I think annotations should also be automatically transformed in these cases.

[ExtReMLapin]

As for future people meeting this issue.

I don't get this error with default trained but as soon as I use my aug trainer

class AugTrainer(DefaultTrainer):
        @classmethod
        def build_train_loader(cls, cfg):
            mapper = DatasetMapper(
                cfg,
                is_train=True,
                use_instance_mask=True,
                recompute_boxes=True,
                augmentations=[
                    T.ResizeShortestEdge(
                        short_edge_length=cfg.INPUT.MIN_SIZE_TRAIN, 
                        max_size=cfg.INPUT.MAX_SIZE_TRAIN,
                        sample_style=cfg.INPUT.MIN_SIZE_TRAIN_SAMPLING,
                    ),
                T.RandomApply(T.RandomFlip(vertical=True, horizontal=False), prob=0.5),
                T.RandomApply(T.RandomFlip(vertical=False, horizontal=True), prob=0.5),
                T.RandomRotation([0, 360]),
                T.RandomApply(T.RandomContrast(0.3, 1.4), prob=0.7),
                T.RandomApply(T.RandomBrightness(0.3, 1.4), prob=0.7),
                T.RandomApply(T.RandomLighting(scale=0.5), prob=0.5),
                ],
            )
            return build_detection_train_loader(cfg, mapper=mapper)

        @classmethod
        def build_evaluator(cls, cfg, dataset_name, output_folder=None):
            if output_folder is None:
                output_folder = os.path.join(cfg.OUTPUT_DIR, "inference")
            return COCOEvaluator(dataset_name, output_dir=output_folder)

WIth cfg.DATALOADER.FILTER_EMPTY_ANNOTATIONS = False it errors as soon as it tries to train on a background image