xinzhuma / monodle

Delving into Localization Errors for Monocular 3D Object Detection, CVPR'2021

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

resume会报错,已解决

DuZzzs opened this issue · comments

commit: e86bae4, resume报错如下:

File "/monodle/tools/train_val.py", line 87, in <module>
    main()
  File "/monodle/tools/train_val.py", line 75, in main
    trainer.train()
  File "/monodle/lib/helpers/trainer_helper.py", line 72, in train
    self.train_one_epoch()
  File "/monodle/lib/helpers/trainer_helper.py", line 106, in train_one_epoch
    self.optimizer.step()
  File "/env/miniconda3/envs/monodle/lib/python3.6/site-packages/torch/optim/adam.py", line 93, in step
    exp_avg.mul_(beta1).add_(1 - beta1, grad)
RuntimeError: expected backend CPU and dtype Float but got backend CUDA and dtype Float
Exception ignored in: <bound method tqdm.__del__ of <tqdm.std.tqdm object at 0x7f904072d780>>

解决办法:

# self.epoch = load_checkpoint(model=self.model,
self.epoch = load_checkpoint(model=self.model.to(self.device),
                                         optimizer=self.optimizer,
                                         filename=cfg['resume_model'],
                                         map_location=self.device,
                                         logger=self.logger)

Thanks! I will update it.