EEGProject

[ZhaoShanBiounite]

0622 16:26:57.738000 7904 .venv\Lib\site-packages\torch\utils\flop_counter.py:29] triton not found; flop counting will not work for triton kernels
Seed set to 97
subjects:['sub-01']
./data\Image_feature\DirectT\ViT-bigG-14_test.pt
ViT-bigG-14
inpating_data.DirectT
init test_dataset success
subjects:['sub-01']
./data\Image_feature\DirectT\ViT-bigG-14_train.pt
ViT-bigG-14
inpating_data.DirectT
init train_dataset success
train num: 8270,val num: 200, test num: 200
init brain
{}
eeg_backbone.EEGProject
GPU available: True (cuda), used: True
TPU available: False, using: 0 TPU cores
💡 Tip: For seamless cloud logging and experiment tracking, try installing litlogger to enable LitLogger, which logs metrics and artifacts automatically to the Lightning Experiments platform.
exp\intra-subject_EEGProject_ViT-bigG-14\sub-01/seed97
C:\Users\zjy\Documents\code.venv\Lib\site-packages\pytorch_lightning\trainer\connectors\checkpoint_connector.py:190: .fit(ckpt_path="last") is set, but there is no last checkpoint available. No checkpoint will be loaded. HINT: Set ModelCheckpoint(..., save_last=True).
You are using a CUDA device ('NVIDIA GeForce RTX 4090 D') that has Tensor Cores. To properly utilize them, you should set torch.set_float32_matmul_precision('medium' | 'high') which will trade-off precision for performance. For more details, read https://pytorch.org/docs/stable/generated/torch.set_float32_matmul_precision.html#torch.set_float32_matmul_precision
LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0]
┏━━━┳━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━┳━━━━━━━┳━━━━━━━┓
┃ ┃ Name ┃ Type ┃ Params ┃ Mode ┃ FLOPs ┃
┡━━━╇━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━╇━━━━━━━╇━━━━━━━┩
│ 0 │ brain │ EEGProject │ 6.0 M │ train │ 0 │
│ 1 │ criterion │ ClipLoss │ 0 │ train │ 0 │
└───┴───────────┴────────────┴────────┴───────┴───────┘
Trainable params: 6.0 M
Non-trainable params: 0
Total params: 6.0 M
Total estimated model params size (MB): 24.069
Modules in train mode: 11
Modules in eval mode: 0
Total FLOPs: 0
C:\Users\zjy\Documents\code.venv\Lib\site-packages\pytorch_lightning\utilities_pytree.py:21: isinstance(treespec, LeafSpec) is deprecated, use
isinstance(treespec, TreeSpec) and treespec.is_leaf() instead.
C:\Users\zjy\Documents\code.venv\Lib\site-packages\pytorch_lightning\trainer\connectors\data_connector.py:434: The 'val_dataloader' does not have many
workers which may be a bottleneck. Consider increasing the value of the num_workers argumenttonum_workers=19in theDataLoader` to improve
performance.
Traceback (most recent call last):
File "c:\Users\zjy\Documents\code\src\retrieval\train_process.py", line 416, in
run_experiment(parse_args())
~~~~~~~~~~~~~~^^^^^^^^^^^^^^
File "c:\Users\zjy\Documents\code\src\retrieval\train_process.py", line 411, in run_experiment
result = main(config, yaml)
File "c:\Users\zjy\Documents\code\src\retrieval\train_process.py", line 346, in main
trainer.fit(pl_model, train_dataloaders=train_loader, val_dataloaders=val_loader, ckpt_path=ckpt_path)
~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\zjy\Documents\code.venv\Lib\site-packages\pytorch_lightning\trainer\trainer.py", line 584, in fit
call._call_and_handle_interrupt(
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
self,
^^^^^
...<6 lines>...
weights_only,
^^^^^^^^^^^^^
)
^
File "C:\Users\zjy\Documents\code.venv\Lib\site-packages\pytorch_lightning\trainer\call.py", line 49, in _call_and_handle_interrupt
return trainer_fn(*args, **kwargs)
File "C:\Users\zjy\Documents\code.venv\Lib\site-packages\pytorch_lightning\trainer\trainer.py", line 630, in _fit_impl
self._run(model, ckpt_path=ckpt_path, weights_only=weights_only)
~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\zjy\Documents\code.venv\Lib\site-packages\pytorch_lightning\trainer\trainer.py", line 1079, in _run
results = self._run_stage()
File "C:\Users\zjy\Documents\code.venv\Lib\site-packages\pytorch_lightning\trainer\trainer.py", line 1121, in _run_stage
self._run_sanity_check()
~~~~~~~~~~~~~~~~~~~~~~^^
File "C:\Users\zjy\Documents\code.venv\Lib\site-packages\pytorch_lightning\trainer\trainer.py", line 1150, in _run_sanity_check
val_loop.run()
~~~~~~~~~~~~^^
File "C:\Users\zjy\Documents\code.venv\Lib\site-packages\pytorch_lightning\loops\utilities.py", line 179, in _decorator
return loop_run(self, *args, **kwargs)
File "C:\Users\zjy\Documents\code.venv\Lib\site-packages\pytorch_lightning\loops\evaluation_loop.py", line 146, in run
self._evaluation_step(batch, batch_idx, dataloader_idx, dataloader_iter)
~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\zjy\Documents\code.venv\Lib\site-packages\pytorch_lightning\loops\evaluation_loop.py", line 441, in _evaluation_step
output = call._call_strategy_hook(trainer, hook_name, *step_args)
File "C:\Users\zjy\Documents\code.venv\Lib\site-packages\pytorch_lightning\trainer\call.py", line 329, in _call_strategy_hook
output = fn(*args, **kwargs)
File "C:\Users\zjy\Documents\code.venv\Lib\site-packages\pytorch_lightning\strategies\strategy.py", line 412, in validation_step
return self.lightning_module.validation_step(*args, **kwargs)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
File "c:\Users\zjy\Documents\code\src\retrieval\train_process.py", line 193, in validation_step
eeg_z, img_z, loss = self(batch)
~~~~^^^^^^^
File "C:\Users\zjy\Documents\code.venv\Lib\site-packages\torch\nn\modules\module.py", line 1778, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
File "C:\Users\zjy\Documents\code.venv\Lib\site-packages\torch\nn\modules\module.py", line 1789, in _call_impl
return forward_call(*args, **kwargs)
File "c:\Users\zjy\Documents\code\src\retrieval\train_process.py", line 86, in forward
eeg_z = self.brain(eeg)
File "C:\Users\zjy\Documents\code.venv\Lib\site-packages\torch\nn\modules\module.py", line 1778, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
File "C:\Users\zjy\Documents\code.venv\Lib\site-packages\torch\nn\modules\module.py", line 1789, in _call_impl
return forward_call(*args, **kwargs)
File "c:\Users\zjy\Documents\code\src\retrieval\eeg_backbone.py", line 38, in forward
x = x.view(x.shape[0], self.input_dim)
RuntimeError: shape '[200, 3417]' is invalid for input of size 41004000