ValueError in training CFLOW

[aparico]

Describe the bug

I'm getting this error in training CFLOW on a custom dataset. I tried PatchCore and FastFlow but I don't get the same error.

Traceback (most recent call last):█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 27/27 [00:47<00:00,  1.30s/it]
  File "/foo/anomalib/tools/train.py", line 71, in <module>
    train()
  File "/foo/anomalib/tools/train.py", line 60, in train
    trainer.fit(model=model, datamodule=datamodule)
  File "/home/anaconda3/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 770, in fit
    self._call_and_handle_interrupt(
  File "/home/anaconda3/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 723, in _call_and_handle_interrupt
    return trainer_fn(*args, **kwargs)
  File "/home/anaconda3/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 811, in _fit_impl
    results = self._run(model, ckpt_path=self.ckpt_path)
  File "/home/anaconda3/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1236, in _run
    results = self._run_stage()
  File "/home/anaconda3/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1323, in _run_stage
    return self._run_train()
  File "/home/anaconda3/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1353, in _run_train
    self.fit_loop.run()
  File "/home/anaconda3/lib/python3.9/site-packages/pytorch_lightning/loops/base.py", line 204, in run
    self.advance(*args, **kwargs)
  File "/home/anaconda3/lib/python3.9/site-packages/pytorch_lightning/loops/fit_loop.py", line 266, in advance
    self._outputs = self.epoch_loop.run(self._data_fetcher)
  File "/home/anaconda3/lib/python3.9/site-packages/pytorch_lightning/loops/base.py", line 205, in run
    self.on_advance_end()
  File "/home/anaconda3/lib/python3.9/site-packages/pytorch_lightning/loops/epoch/training_epoch_loop.py", line 255, in on_advance_end
    self._run_validation()
  File "/home/anaconda3/lib/python3.9/site-packages/pytorch_lightning/loops/epoch/training_epoch_loop.py", line 311, in _run_validation
    self.val_loop.run()
  File "/home/anaconda3/lib/python3.9/site-packages/pytorch_lightning/loops/base.py", line 211, in run
    output = self.on_run_end()
  File "/home/anaconda3/lib/python3.9/site-packages/pytorch_lightning/loops/dataloader/evaluation_loop.py", line 183, in on_run_end
    self._evaluation_epoch_end(self._outputs)
  File "/home/anaconda3/lib/python3.9/site-packages/pytorch_lightning/loops/dataloader/evaluation_loop.py", line 310, in _evaluation_epoch_end
    self.trainer._call_lightning_module_hook("validation_epoch_end", output_or_outputs)
  File "/home/anaconda3/lib/python3.9/site-packages/pytorch_lightning/trainer/trainer.py", line 1595, in _call_lightning_module_hook
    output = fn(*args, **kwargs)
  File "/foo/anomalib/anomalib/models/components/base/anomaly_module.py", line 120, in validation_epoch_end
    self._compute_adaptive_threshold(outputs)
  File "/foo/anomalib/anomalib/models/components/base/anomaly_module.py", line 136, in _compute_adaptive_threshold
    self._collect_outputs(self.image_threshold, self.pixel_threshold, outputs)
  File "/foo/anomalib/anomalib/models/components/base/anomaly_module.py", line 153, in _collect_outputs
    pixel_metric.update(output["anomaly_maps"], output["mask"].int())
  File "/home/anaconda3/lib/python3.9/site-packages/torchmetrics/metric.py", line 383, in wrapped_func
    update(*args, **kwargs)
  File "/home/anaconda3/lib/python3.9/site-packages/torchmetrics/classification/precision_recall_curve.py", line 110, in update
    preds, target, num_classes, pos_label = _precision_recall_curve_update(
  File "/home/anaconda3/lib/python3.9/site-packages/torchmetrics/functional/classification/precision_recall_curve.py", line 119, in _precision_recall_curve_update
    raise ValueError("preds and target must have same number of dimensions, or one additional dimension for preds")
ValueError: preds and target must have same number of dimensions, or one additional dimension for preds

To Reproduce

Steps to reproduce the behavior:

I ran this command: python tools/train.py --config anomalib/models/cflow/config.yaml

But I added AUPRO as a metric in the config and I'm running on a custom dataset

Hardware and Software Configuration

• OS: Ubuntu 18.04.2
• NVIDIA Driver Version 418.67
• CUDA Version 10.1
• CUDNN Version 7.5.0

[aparico]

I tried with the MVTech dataset and I'm still getting the same error

[samet-akcay]

@aparico, we have just created a fix for CFlow in PR #589. Can you check if you still have this issue after this fix?

[aparico]

@samet-akcay It worked successfully! Thanks!

[AbdelsalamHaa]

I'm getting the same error during validation but for Ganomaly

Traceback (most recent call last):
  File "C:\Users\itope\anomalib\tools\train.py", line 79, in <module>
    train(args)
  File "C:\Users\itope\anomalib\tools\train.py", line 64, in train
    trainer.fit(model=model, datamodule=datamodule)
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\pytorch_lightning\trainer\trainer.py", line 608, in fit
    call._call_and_handle_interrupt(
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\pytorch_lightning\trainer\call.py", line 38, in _call_and_handle_interrupt
    return trainer_fn(*args, **kwargs)
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\pytorch_lightning\trainer\trainer.py", line 650, in _fit_impl
    self._run(model, ckpt_path=self.ckpt_path)
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\pytorch_lightning\trainer\trainer.py", line 1112, in _run
    results = self._run_stage()
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\pytorch_lightning\trainer\trainer.py", line 1191, in _run_stage
    self._run_train()
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\pytorch_lightning\trainer\trainer.py", line 1214, in _run_train
    self.fit_loop.run()
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\pytorch_lightning\loops\loop.py", line 199, in run
    self.advance(*args, **kwargs)
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\pytorch_lightning\loops\fit_loop.py", line 267, in advance
    self._outputs = self.epoch_loop.run(self._data_fetcher)
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\pytorch_lightning\loops\loop.py", line 200, in run
    self.on_advance_end()
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\pytorch_lightning\loops\epoch\training_epoch_loop.py", line 250, in on_advance_end
    self._run_validation()
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\pytorch_lightning\loops\epoch\training_epoch_loop.py", line 308, in _run_validation
    self.val_loop.run()
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\pytorch_lightning\loops\loop.py", line 206, in run
    output = self.on_run_end()
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\pytorch_lightning\loops\dataloader\evaluation_loop.py", line 180, in on_run_end
    self._evaluation_epoch_end(self._outputs)
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\pytorch_lightning\loops\dataloader\evaluation_loop.py", line 288, in _evaluation_epoch_end
    self.trainer._call_lightning_module_hook(hook_name, output_or_outputs)
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\pytorch_lightning\trainer\trainer.py", line 1356, in _call_lightning_module_hook
    output = fn(*args, **kwargs)
  File "C:\Users\itope\anomalib\src\anomalib\models\ganomaly\lightning_model.py", line 165, in validation_epoch_end
    super().validation_epoch_end(outputs)
  File "C:\Users\itope\anomalib\src\anomalib\models\components\base\anomaly_module.py", line 146, in validation_epoch_end
    self._collect_outputs(self.image_metrics, self.pixel_metrics, outputs)
  File "C:\Users\itope\anomalib\src\anomalib\models\components\base\anomaly_module.py", line 179, in _collect_outputs
    image_metric.update(output["pred_scores"], output["label"].int())
  File "C:\Users\itope\anomalib\src\anomalib\utils\metrics\collection.py", line 26, in update
    super().update(*args, **kwargs)
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\torchmetrics\collections.py", line 191, in update
    m.update(*args, **m_kwargs)
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\torchmetrics\metric.py", line 395, in wrapped_func
    update(*args, **kwargs)
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\torchmetrics\classification\stat_scores.py", line 706, in update
    tp, fp, tn, fn = _stat_scores_update(
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\torchmetrics\functional\classification\stat_scores.py", line 954, in _stat_scores_update
    preds, target, _ = _input_format_classification(
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\torchmetrics\utilities\checks.py", line 412, in _input_format_classification
    case = _check_classification_inputs(
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\torchmetrics\utilities\checks.py", line 270, in _check_classification_inputs
    _basic_input_validation(preds, target, threshold, multiclass, ignore_index)
  File "C:\Users\itope\anaconda3\envs\anomalib_env\lib\site-packages\torchmetrics\utilities\checks.py", line 61, in _basic_input_validation
    raise ValueError("The `preds` and `target` should have the same first dimension.")
ValueError: The `preds` and `target` should have the same first dimension.
Epoch 1: : 173it [08:47,  3.05s/it, loss=5.56, train_loss_step=9.420, train_loss_epoch=7.030]