Version restriction

[Song-Jingyu]

Hi,

Thanks for the wonderful work. As I am working to set up this work I found this project has a very strict limit on versions. Since the compiled .so files are provided by the authors I was not able to change the version to suit my hardware (especially the CUDA version). The provided file has a version constraint of using CUDA 10.2 and pytorch 1.9, which requires that the GPU is older than sm_70. However, in the paper it is mentioned RTX 2080Ti is used. Since it is sm_75, I was wondering if the authors could give any suggestion on how to run this project on a more recent GPU, or point out if I was missing anything to run unidistill on my GPU (sm_80). Thanks!

[Song-Jingyu]

Can you also share the version of pytorch-lightning? I am getting an error that seems to be related to that. Thanks!

Traceback (most recent call last):
  File "unidistill/exps/multisensor_fusion/nuscenes/BEVFusion/BEVFusion_nuscenes_centerhead_lidar_exp.py", line 35, in <module>
    run_cli(Exp, "BEVFusion_nuscenes_centerhead_lidar_exp")
  File "/home/jingyuso/kd_project/test/CVPR2023-UniDistill/unidistill/exps/base_cli.py", line 59, in run_cli
    trainer.fit(model, model.train_dataloader, model.val_dataloader)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py", line 444, in fit
    results = self.accelerator_backend.train()
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/accelerators/ddp_accelerator.py", line 148, in train
    results = self.ddp_train(process_idx=self.task_idx, model=model)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/accelerators/ddp_accelerator.py", line 282, in ddp_train
    results = self.train_or_test()
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/accelerators/accelerator.py", line 74, in train_or_test
    results = self.trainer.train()
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py", line 493, in train
    self.train_loop.run_training_epoch()
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/trainer/training_loop.py", line 561, in run_training_epoch
    batch_output = self.run_training_batch(batch, batch_idx, dataloader_idx)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/trainer/training_loop.py", line 728, in run_training_batch
    self.optimizer_step(optimizer, opt_idx, batch_idx, train_step_and_backward_closure)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/trainer/training_loop.py", line 470, in optimizer_step
    optimizer, batch_idx, opt_idx, train_step_and_backward_closure
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/accelerators/accelerator.py", line 130, in optimizer_step
    using_lbfgs=is_lbfgs
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/core/lightning.py", line 1270, in optimizer_step
    optimizer.step(closure=optimizer_closure)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/torch/optim/lr_scheduler.py", line 65, in wrapper
    return wrapped(*args, **kwargs)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/torch/optim/optimizer.py", line 88, in wrapper
    return func(*args, **kwargs)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/torch/autograd/grad_mode.py", line 28, in decorate_context
    return func(*args, **kwargs)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/torch/optim/adamw.py", line 65, in step
    loss = closure()
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/trainer/training_loop.py", line 723, in train_step_and_backward_closure
    self.trainer.hiddens
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/trainer/training_loop.py", line 813, in training_step_and_backward
    result = self.training_step(split_batch, batch_idx, opt_idx, hiddens)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/trainer/training_loop.py", line 320, in training_step
    training_step_output = self.trainer.accelerator_backend.training_step(args)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/accelerators/ddp_accelerator.py", line 158, in training_step
    output = self.trainer.model(*args)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/overrides/data_parallel.py", line 176, in forward
    output = self.module.training_step(*inputs[0], **kwargs[0])
TypeError: training_step() takes 2 positional arguments but 3 were given

[Song-Jingyu]

Can you also share the version of pytorch-lightning? I am getting an error that seems to be related to that. Thanks!

Traceback (most recent call last):
  File "unidistill/exps/multisensor_fusion/nuscenes/BEVFusion/BEVFusion_nuscenes_centerhead_lidar_exp.py", line 35, in <module>
    run_cli(Exp, "BEVFusion_nuscenes_centerhead_lidar_exp")
  File "/home/jingyuso/kd_project/test/CVPR2023-UniDistill/unidistill/exps/base_cli.py", line 59, in run_cli
    trainer.fit(model, model.train_dataloader, model.val_dataloader)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py", line 444, in fit
    results = self.accelerator_backend.train()
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/accelerators/ddp_accelerator.py", line 148, in train
    results = self.ddp_train(process_idx=self.task_idx, model=model)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/accelerators/ddp_accelerator.py", line 282, in ddp_train
    results = self.train_or_test()
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/accelerators/accelerator.py", line 74, in train_or_test
    results = self.trainer.train()
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py", line 493, in train
    self.train_loop.run_training_epoch()
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/trainer/training_loop.py", line 561, in run_training_epoch
    batch_output = self.run_training_batch(batch, batch_idx, dataloader_idx)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/trainer/training_loop.py", line 728, in run_training_batch
    self.optimizer_step(optimizer, opt_idx, batch_idx, train_step_and_backward_closure)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/trainer/training_loop.py", line 470, in optimizer_step
    optimizer, batch_idx, opt_idx, train_step_and_backward_closure
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/accelerators/accelerator.py", line 130, in optimizer_step
    using_lbfgs=is_lbfgs
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/core/lightning.py", line 1270, in optimizer_step
    optimizer.step(closure=optimizer_closure)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/torch/optim/lr_scheduler.py", line 65, in wrapper
    return wrapped(*args, **kwargs)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/torch/optim/optimizer.py", line 88, in wrapper
    return func(*args, **kwargs)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/torch/autograd/grad_mode.py", line 28, in decorate_context
    return func(*args, **kwargs)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/torch/optim/adamw.py", line 65, in step
    loss = closure()
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/trainer/training_loop.py", line 723, in train_step_and_backward_closure
    self.trainer.hiddens
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/trainer/training_loop.py", line 813, in training_step_and_backward
    result = self.training_step(split_batch, batch_idx, opt_idx, hiddens)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/trainer/training_loop.py", line 320, in training_step
    training_step_output = self.trainer.accelerator_backend.training_step(args)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/accelerators/ddp_accelerator.py", line 158, in training_step
    output = self.trainer.model(*args)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/jingyuso/miniconda3/envs/unidistill_test/lib/python3.6/site-packages/pytorch_lightning/overrides/data_parallel.py", line 176, in forward
    output = self.module.training_step(*inputs[0], **kwargs[0])
TypeError: training_step() takes 2 positional arguments but 3 were given

solved by using newer version of pytorch-lightning (for instance 1.5)

[smalltoyfox]

Hello, do you know how. pkl is generated in the data processing section

[Puiching-Memory]

@Song-Jingyu The source code is located at here
I have provided a linux version of python3.8, please compile your own if you need more

voxel_pooling_ext.cpython-38-x86_64-linux-gnu.zip