pickle save gpu tensor，在本地没有gpu的情况下load出错。

error:

RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.
解决办法：

保存pkl文件前，将数据device设置为cpu。

outputs = {'point': pc,
           'gt': bbox,
           'pred': pre_bbox}

改为

outputs = {'point': pc.cpu(),
           'gt': bbox.cpu(),
           'pred': pre_bbox.cpu()}