Skip to main content

Kimsehun725's group workspace

Timestamps visible
2022-10-11 05:44:23
GPU available: True (cuda), used: True
2022-10-11 05:44:23
TPU available: False, using: 0 TPU cores
2022-10-11 05:44:23
IPU available: False, using: 0 IPUs
2022-10-11 05:44:23
HPU available: False, using: 0 HPUs
2022-10-11 05:44:23
wandb: logging graph, to disable use `wandb.watch(log_graph=False)`
2022-10-11 05:44:33
Initializing distributed: GLOBAL_RANK: 0, MEMBER: 1/4
2022-10-11 05:44:33
----------------------------------------------------------------------------------------------------
2022-10-11 05:44:33
distributed_backend=nccl
2022-10-11 05:44:33
All distributed processes registered. Starting with 4 processes
2022-10-11 05:44:33
----------------------------------------------------------------------------------------------------
2022-10-11 05:44:43
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0,1,2,3]
2022-10-11 05:44:43
  | Name                   | Type             | Params
2022-10-11 05:44:43
------------------------------------------------------------
2022-10-11 05:44:43
0 | conv_stack             | ConvStack        | 1.6 M
2022-10-11 05:44:43
1 | z_linear               | Sequential       | 524 K
2022-10-11 05:44:43
2 | self_attention_block   | ConformerEncoder | 2.6 M
2022-10-11 05:44:43
3 | frame_tab_output_layer | Sequential       | 81.9 K
2022-10-11 05:44:43
4 | softmax_by_string      | Softmax          | 0
2022-10-11 05:44:43
------------------------------------------------------------
2022-10-11 05:44:43
4.8 M     Trainable params
2022-10-11 05:44:43
0         Non-trainable params
2022-10-11 05:44:43
4.8 M     Total params
2022-10-11 05:44:43
19.117    Total estimated model params size (MB)
2022-10-11 05:44:48
Sanity Checking DataLoader 0:   0%|                                                                                                                                                                    | 0/1 [00:00<?, ?it/s]
2022-10-11 05:44:51
Traceback (most recent call last):
2022-10-11 05:44:51
  File "src/train.py", line 63, in <module>
2022-10-11 05:44:51
    main(kwargs)
2022-10-11 05:44:51
  File "src/train.py", line 23, in main
2022-10-11 05:44:51
    step3(kwargs)
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/src/step3.py", line 191, in step3
2022-10-11 05:44:51
    train(kwargs, use_pretrained_model, pretrained_time, pretrained_epoch, now, test_num, train_data_list,
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/src/step3.py", line 145, in train
2022-10-11 05:44:51
    trainer.fit(model, train_dataloaders=train_loader,
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 696, in fit
2022-10-11 05:44:51
    self._call_and_handle_interrupt(
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 648, in _call_and_handle_interrupt
2022-10-11 05:44:51
    return self.strategy.launcher.launch(trainer_fn, *args, trainer=self, **kwargs)
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/pytorch_lightning/strategies/launchers/subprocess_script.py", line 93, in launch
2022-10-11 05:44:51
    return function(*args, **kwargs)
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 735, in _fit_impl
2022-10-11 05:44:51
    results = self._run(model, ckpt_path=self.ckpt_path)
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1166, in _run
2022-10-11 05:44:51
    results = self._run_stage()
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1252, in _run_stage
2022-10-11 05:44:51
    return self._run_train()
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1274, in _run_train
2022-10-11 05:44:51
    self._run_sanity_check()
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1343, in _run_sanity_check
2022-10-11 05:44:51
    val_loop.run()
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/pytorch_lightning/loops/loop.py", line 200, in run
2022-10-11 05:44:51
    self.advance(*args, **kwargs)
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/pytorch_lightning/loops/dataloader/evaluation_loop.py", line 155, in advance
2022-10-11 05:44:51
    dl_outputs = self.epoch_loop.run(self._data_fetcher, dl_max_batches, kwargs)
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/pytorch_lightning/loops/loop.py", line 200, in run
2022-10-11 05:44:51
    self.advance(*args, **kwargs)
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/pytorch_lightning/loops/epoch/evaluation_epoch_loop.py", line 143, in advance
2022-10-11 05:44:51
    output = self._evaluation_step(**kwargs)
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/pytorch_lightning/loops/epoch/evaluation_epoch_loop.py", line 240, in _evaluation_step
2022-10-11 05:44:51
    output = self.trainer._call_strategy_hook(hook_name, *kwargs.values())
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1704, in _call_strategy_hook
2022-10-11 05:44:51
    output = fn(*args, **kwargs)
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/pytorch_lightning/strategies/ddp.py", line 358, in validation_step
2022-10-11 05:44:51
    return self.model(*args, **kwargs)
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
2022-10-11 05:44:51
    return forward_call(*input, **kwargs)
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/torch/nn/parallel/distributed.py", line 1008, in forward
2022-10-11 05:44:51
    output = self._run_ddp_forward(*inputs, **kwargs)
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/torch/nn/parallel/distributed.py", line 969, in _run_ddp_forward
2022-10-11 05:44:51
    return module_to_run(*inputs[0], **kwargs[0])
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
2022-10-11 05:44:51
    return forward_call(*input, **kwargs)
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/venv/lib/python3.8/site-packages/pytorch_lightning/overrides/base.py", line 90, in forward
2022-10-11 05:44:51
    return self.module.validation_step(*inputs, **kwargs)
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/src/models.py", line 647, in validation_step
2022-10-11 05:44:51
    y_hat, mu, logvar = self.forward(x1, x2, ilens)
2022-10-11 05:44:51
  File "/data/group1/z44543r/vae_separation/src/models.py", line 635, in forward
2022-10-11 05:44:51
    return y_hat, mu, logvar
2022-10-11 05:44:51
NameError: name 'mu' is not defined