cannot training with papaya databases
Closed this issue · 5 comments
Hello... Is the system not adapted to train with the papaya database?
Training on papaya works.
Please provide an error message, otherwise it is hard to help.
Are you able to train a model on the avocado data?
Best regards,
Leon Varga
Hello... Yes, I have already trained the models using the avocado, kiwi and kaki data.
The error message that appears when using the papaya data is as follows:
File "/home/yjimenez/PycharmProjects/deephs_fruit-master/classification/train.py", line 423, in
main(hparams)
File "/home/yjimenez/PycharmProjects/deephs_fruit-master/classification/train.py", line 399, in main
trainer.fit(model)
File "/home/yjimenez/Imaging_Processing/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 696, in fit
self._call_and_handle_interrupt(
File "/home/yjimenez/Imaging_Processing/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 648, in _call_and_handle_interrupt
return self.strategy.launcher.launch(trainer_fn, *args, trainer=self, **kwargs)
File "/home/yjimenez/Imaging_Processing/lib/python3.10/site-packages/pytorch_lightning/strategies/launchers/subprocess_script.py", line 93, in launch
return function(*args, **kwargs)
File "/home/yjimenez/Imaging_Processing/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 735, in _fit_impl
results = self._run(model, ckpt_path=self.ckpt_path)
File "/home/yjimenez/Imaging_Processing/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1105, in _run
self._call_setup_hook() # allow user to setup lightning_module in accelerator environment
File "/home/yjimenez/Imaging_Processing/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1449, in _call_setup_hook
self._call_lightning_module_hook("setup", stage=fn)
File "/home/yjimenez/Imaging_Processing/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1550, in _call_lightning_module_hook
output = fn(*args, **kwargs)
File "/home/yjimenez/PycharmProjects/deephs_fruit-master/classification/train.py", line 60, in setup
get_records(self.hparams['fruit'],
File "/home/yjimenez/PycharmProjects/deephs_fruit-master/core/datasets/hyperspectral_dataset.py", line 222, in get_records
assert len(records) > 0
AssertionError
wandb: Waiting for W&B process to finish... (failed 1).
wandb:
wandb: You can sync this run to the cloud by running:
wandb: wandb sync /tmp/wandb/offline-run-20230918_213420-2u51jakx
wandb: Find logs at: /tmp/wandb/offline-run-20230918_213420-2u51jakx/log
Line
File "/home/yjimenez/PycharmProjects/deephs_fruit-master/core/datasets/hyperspectral_dataset.py", line 222, in get_records assert len(records) > 0
indicates that it cannot find the hyperspectral recordings.
Can you please validate whether the data_path directory contains the extracted papaya-zip?
You were right, the public repository was not fully up-to-date.
With the commit 42e032b the training for papayas should be possbile.
Best regards,
Leon
Thank you so much!