当我运行cascade_mask_rcnn_r50_fpn_1x_coco时出现does not match the type of data currently contained in the container

在自己的数据集中
运行代码：

```
python -u tools/train.py -c configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.yml --use_vdl=true --vdl_log_dir=vdl_dir/scalar --eval
```

报错信息：

```
File "tools/train.py", line 173, in main
    run(FLAGS, cfg)
  File "tools/train.py", line 127, in run
    trainer.train(FLAGS.eval)
  File "/home/f523/chx/projectChx/PaddleDetection-release-2.4/ppdet/engine/trainer.py", line 512, in train
    self._eval_with_loader(self._eval_loader)
  File "/home/f523/chx/projectChx/PaddleDetection-release-2.4/ppdet/engine/trainer.py", line 535, in _eval_with_loader
    outs = self.model(data)
  File "/home/f523/miniconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/dygraph/layers.py", line 930, in __call__
    return self._dygraph_call_func(*inputs, **kwargs)
  File "/home/f523/miniconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/dygraph/layers.py", line 915, in _dygraph_call_func
    outputs = self.forward(*inputs, **kwargs)
  File "/home/f523/chx/projectChx/PaddleDetection-release-2.4/ppdet/modeling/architectures/meta_arch.py", line 75, in forward
    outs.append(self.get_pred())
  File "/home/f523/chx/projectChx/PaddleDetection-release-2.4/ppdet/modeling/architectures/cascade_rcnn.py", line 137, in get_pred
    bbox_pred, bbox_num, mask_pred = self._forward()
  File "/home/f523/chx/projectChx/PaddleDetection-release-2.4/ppdet/modeling/architectures/cascade_rcnn.py", line 119, in _forward
    mask_out = self.mask_head(body_feats, bbox, bbox_num, self.inputs)
  File "/home/f523/miniconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/dygraph/layers.py", line 930, in __call__
    return self._dygraph_call_func(*inputs, **kwargs)
  File "/home/f523/miniconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/dygraph/layers.py", line 915, in _dygraph_call_func
    outputs = self.forward(*inputs, **kwargs)
  File "/home/f523/chx/projectChx/PaddleDetection-release-2.4/ppdet/modeling/heads/mask_head.py", line 249, in forward
    return self.forward_test(body_feats, rois, rois_num, im_scale,
  File "/home/f523/chx/projectChx/PaddleDetection-release-2.4/ppdet/modeling/heads/mask_head.py", line 216, in forward_test
    rois_feat = self.roi_extractor(body_feats, bbox, rois_num)
  File "/home/f523/chx/projectChx/PaddleDetection-release-2.4/ppdet/modeling/heads/roi_extractor.py", line 90, in __call__
    rois_dist, restore_index, rois_num_dist = ops.distribute_fpn_proposals(
  File "/home/f523/chx/projectChx/PaddleDetection-release-2.4/ppdet/modeling/ops.py", line 301, in distribute_fpn_proposals
    helper.append_op(
  File "/home/f523/miniconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/layer_helper.py", line 44, in append_op
    return self.main_program.current_block().append_op(*args, **kwargs)
  File "/home/f523/miniconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/framework.py", line 3599, in append_op
    _dygraph_tracer().trace_op(type,
  File "/home/f523/miniconda3/envs/paddle/lib/python3.8/site-packages/paddle/fluid/dygraph/tracer.py", line 307, in trace_op
    self.trace(type, inputs, outputs, attrs,
ValueError: (InvalidArgument) The type of data we are trying to retrieve does not match the type of data currently contained in the container.
  [Hint: Expected dtype() == paddle::experimental::CppTypeToDataType<T>::Type(), but received dtype():7 != paddle::experimental::CppTypeToDataType<T>::Type():5.] (at /paddle/paddle/phi/co
re/dense_tensor.cc:137)
  [operator < distribute_fpn_proposals > error]
```
运行版本情况：
paddleDetection：2.4
paddlepaddle：2.3.2
我打印出来了mask_head的输入信息，感觉没什么不同，不明白这是什么错，该如何解决

PaddlePaddle/PaddleDetection

内容风险标识

评论 (1)

PaddlePaddle/PaddleDetection .gitee-modal { width: 500px !important; }

内容风险标识