RuntimeError: Expected object of scalar type Byte but got scalar type Bool

使用mmdet的时候遇到问题：RuntimeError: Expected object of scalar type Byte but got scalar type Bool for argument #2 'other' in call to _th_and

2021-05-20 23:14:34,287 - INFO - Distributed training: False
loading annotations into memory...
Done (t=1.78s)
creating index...
index created!
2021-05-20 23:15:02,674 - INFO - Start running, host: sipl@sipl-Z590-UD, work_dir: /home/sipl/4T/ReDet-master/tools/work_dirs/ReDet_re50_refpn_1x_dota1_ms
2021-05-20 23:15:02,674 - INFO - workflow: [('train', 1)], max: 12 epochs
Traceback (most recent call last):
  File "/home/sipl/4T/ReDet-master/tools/train.py", line 97, in <module>
    main()
  File "/home/sipl/4T/ReDet-master/tools/train.py", line 93, in main
    logger=logger)
  File "/home/sipl/4T/ReDet-master/mmdet/apis/train.py", line 61, in train_detector
    _non_dist_train(model, dataset, cfg, validate=validate)
  File "/home/sipl/4T/ReDet-master/mmdet/apis/train.py", line 197, in _non_dist_train
    runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
  File "/home/sipl/anaconda3/envs/redet/lib/python3.7/site-packages/mmcv/runner/runner.py", line 358, in run
    epoch_runner(data_loaders[i], **kwargs)
  File "/home/sipl/anaconda3/envs/redet/lib/python3.7/site-packages/mmcv/runner/runner.py", line 264, in train
    self.model, data_batch, train_mode=True, **kwargs)
  File "/home/sipl/4T/ReDet-master/mmdet/apis/train.py", line 39, in batch_processor
    losses = model(**data)
  File "/home/sipl/anaconda3/envs/redet/lib/python3.7/site-packages/torch/nn/modules/module.py", line 541, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/sipl/anaconda3/envs/redet/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py", line 150, in forward
    return self.module(*inputs[0], **kwargs[0])
  File "/home/sipl/anaconda3/envs/redet/lib/python3.7/site-packages/torch/nn/modules/module.py", line 541, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/sipl/4T/ReDet-master/mmdet/models/detectors/base_new.py", line 95, in forward
    return self.forward_train(img, img_meta, **kwargs)
  File "/home/sipl/4T/ReDet-master/mmdet/models/detectors/ReDet.py", line 143, in forward_train
    *rpn_loss_inputs, gt_bboxes_ignore=gt_bboxes_ignore)
  File "/home/sipl/4T/ReDet-master/mmdet/models/anchor_heads/rpn_head.py", line 51, in loss
    gt_bboxes_ignore=gt_bboxes_ignore)
  File "/home/sipl/4T/ReDet-master/mmdet/models/anchor_heads/anchor_head.py", line 177, in loss
    sampling=self.sampling)
  File "/home/sipl/4T/ReDet-master/mmdet/core/anchor/anchor_target.py", line 63, in anchor_target
    unmap_outputs=unmap_outputs)
  File "/home/sipl/4T/ReDet-master/mmdet/core/utils/misc.py", line 24, in multi_apply
    return tuple(map(list, zip(*map_results)))
  File "/home/sipl/4T/ReDet-master/mmdet/core/anchor/anchor_target.py", line 108, in anchor_target_single
    cfg.allowed_border)
  File "/home/sipl/4T/ReDet-master/mmdet/core/anchor/anchor_target.py", line 173, in anchor_inside_flags
    (flat_anchors[:, 2] < img_w + allowed_border) & \
RuntimeError: Expected object of scalar type Byte but got scalar type Bool for argument #2 'other' in call to _th_and

解决方法：

打开上述anchor_target.py文件，然后修改下面几行为：

def anchor_inside_flags(flat_anchors, valid_flags, img_shape,
                        allowed_border=0):
    img_h, img_w = img_shape[:2]
    if allowed_border >= 0:
        inside_flags = valid_flags & \
            (flat_anchors[:, 0] >= -allowed_border).type(torch.uint8) & \
            (flat_anchors[:, 1] >= -allowed_border).type(torch.uint8) & \
            (flat_anchors[:, 2] < img_w + allowed_border).type(torch.uint8) & \
            (flat_anchors[:, 3] < img_h + allowed_border).type(torch.uint8)
    else:
        inside_flags = valid_flags
    return inside_flags