Expected object of type torch.cuda.FloatTensor but found type torch.cuda.DoubleTensor for argument #2 'other'

[qiangruoyu]

I want to use my datasets . so I save my data to a pickle file (train.pkl) According to example Provided by https://github.com/open-mmlab/mmdetection。 But I meet one error , I try my best to solve the problem and It still doesn't work. Please give me some advice.

2018-11-03 21:57:09,580 - INFO - workflow: [('train', 1)], max: 5 epochs
Traceback (most recent call last):
File "tools/train.py", line 81, in
main()
File "tools/train.py", line 77, in main
logger=logger)
File "/home/dezheng/.local/lib/python3.6/site-packages/mmdet-0.5.2+86e25e4-py3.6.egg/mmdet/apis/train.py", line 59, in train_detector
_non_dist_train(model, dataset, cfg, validate=validate)
File "/home/dezheng/.local/lib/python3.6/site-packages/mmdet-0.5.2+86e25e4-py3.6.egg/mmdet/apis/train.py", line 117, in _non_dist_train
runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
File "/home/dezheng/anaconda3/lib/python3.6/site-packages/mmcv/runner/runner.py", line 349, in run
epoch_runner(data_loaders[i], **kwargs)
File "/home/dezheng/anaconda3/lib/python3.6/site-packages/mmcv/runner/runner.py", line 255, in train
self.model, data_batch, train_mode=True, **kwargs)
File "/home/dezheng/.local/lib/python3.6/site-packages/mmdet-0.5.2+86e25e4-py3.6.egg/mmdet/apis/train.py", line 37, in batch_processor
losses = model(**data)
File "/home/dezheng/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/dezheng/anaconda3/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 121, in forward
return self.module(*inputs[0], **kwargs[0])
File "/home/dezheng/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/dezheng/.local/lib/python3.6/site-packages/mmdet-0.5.2+86e25e4-py3.6.egg/mmdet/models/detectors/base.py", line 79, in forward
return self.forward_train(img, img_meta, **kwargs)
File "/home/dezheng/.local/lib/python3.6/site-packages/mmdet-0.5.2+86e25e4-py3.6.egg/mmdet/models/detectors/two_stage.py", line 95, in forward_train
rpn_losses = self.rpn_head.loss(*rpn_loss_inputs)
File "/home/dezheng/.local/lib/python3.6/site-packages/mmdet-0.5.2+86e25e4-py3.6.egg/mmdet/models/rpn_heads/rpn_head.py", line 159, in loss
self.target_means, self.target_stds, cfg)
File "/home/dezheng/.local/lib/python3.6/site-packages/mmdet-0.5.2+86e25e4-py3.6.egg/mmdet/core/anchor/anchor_target.py", line 41, in anchor_target
img_metas, means_replicas, stds_replicas, cfg_replicas)
File "/home/dezheng/.local/lib/python3.6/site-packages/mmdet-0.5.2+86e25e4-py3.6.egg/mmdet/core/utils/misc.py", line 24, in multi_apply
return tuple(map(list, zip(*map_results)))
File "/home/dezheng/.local/lib/python3.6/site-packages/mmdet-0.5.2+86e25e4-py3.6.egg/mmdet/core/anchor/anchor_target.py", line 83, in anchor_target_single
_, sampling_result = assign_and_sample(anchors, gt_bboxes, None, None, cfg)
File "/home/dezheng/.local/lib/python3.6/site-packages/mmdet-0.5.2+86e25e4-py3.6.egg/mmdet/core/bbox/sampling.py", line 30, in assign_and_sample
gt_labels)
File "/home/dezheng/.local/lib/python3.6/site-packages/mmdet-0.5.2+86e25e4-py3.6.egg/mmdet/core/bbox/assignment.py", line 66, in assign
overlaps = bbox_overlaps(bboxes, gt_bboxes)
File "/home/dezheng/.local/lib/python3.6/site-packages/mmdet-0.5.2+86e25e4-py3.6.egg/mmdet/core/bbox/geometry.py", line 50, in bbox_overlaps
lt = torch.max(bboxes1[:, None, :2], bboxes2[:, :2]) # [rows, cols, 2]
RuntimeError: Expected object of type torch.cuda.FloatTensor but found type torch.cuda.DoubleTensor for argument #2 'other'

[haoran1062]

print bboxes.dtype, if dtype is 'float64', change it to 'float32' maybe work