Solo on 10x genomics scRNA data #67
Comments
|
Hi there Another user just had this error has well.I'll be trying to track it down today. Best, |
|
Hi there It seems like the most recent version of scvi-tools broke this. Please rollback to I'll be pinning these in the requirements.txt shortly |
|
Thanks! I tried to roll back, but I do get an error:
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi,
I am trying to run solo on the 10x genomics data. This is the command I used:
solo -d /projects/lihc_hiseq/active/SingleCell/processedDATA/12_M491_PBMC_CTC_cDNArep/outs/filtered_feature_bc_matrix -j model_json.json -o 12_M491_outputThe model_json.json is the default you have suggested.
This is the error I get:
Cuda is not available, switching to cpu running! Min cell depth: 500.0, Max cell depth: 68659.0 INFO No batch_key inputted, assuming all cells are same batch INFO No label_key inputted, assuming all cells have same label INFO Using data from adata.X INFO Computing library size prior per batch INFO Successfully registered anndata object containing 7333 cells, 32738 vars, 1 batches, 1 labels, and 0 proteins. Also registered 0 extra categorical covariates and 0 extra continuous covariates. INFO Please do not further modify adata until model is trained. GPU available: False, used: False TPU available: False, using: 0 TPU cores IPU available: False, using: 0 IPUs /home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/tqdm/std.py:538: TqdmWarning: clamping frac to range [0, 1] colour=colour) Epoch 1/2000: -0%| | -1/2000 [00:00<?, ?it/s]/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/pytorch_lightning/trainer/connectors/logger_connector/result.py:398: LightningDeprecationWarning: One of the returned values {'reconstruction_loss_sum', 'kl_global', 'kl_local_sum', 'n_obs'} has agrad_fn. We will detach it automatically but this behaviour will change in v1.6. Please detach it manually:return {'loss': ..., 'something': something.detach()}f"One of the returned values {set(extra.keys())} has agrad_fn. We will detach it automatically" Traceback (most recent call last): File "/home/paulyr2/miniconda/envs/solo/bin/solo", line 33, in <module> sys.exit(load_entry_point('solo-sc', 'console_scripts', 'solo')()) File "/home/paulyr2/solo/solo/solo.py", line 240, in main callbacks=scvi_callbacks, File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/scvi/model/base/_training_mixin.py", line 70, in train return runner() File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/scvi/model/base/_trainrunner.py", line 75, in __call__ self.trainer.fit(self.training_plan, train_dl, val_dl) File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/scvi/lightning/_trainer.py", line 131, in fit super().fit(*args, **kwargs) File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py", line 553, in fit self._run(model) File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py", line 918, in _run self._dispatch() File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py", line 986, in _dispatch self.accelerator.start_training(self) File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/pytorch_lightning/accelerators/accelerator.py", line 92, in start_training self.training_type_plugin.start_training(trainer) File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/pytorch_lightning/plugins/training_type/training_type_plugin.py", line 161, in start_training self._results = trainer.run_stage() File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py", line 996, in run_stage return self._run_train() File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/pytorch_lightning/trainer/trainer.py", line 1045, in _run_train self.fit_loop.run() File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/pytorch_lightning/loops/base.py", line 111, in run self.advance(*args, **kwargs) File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/pytorch_lightning/loops/fit_loop.py", line 200, in advance epoch_output = self.epoch_loop.run(train_dataloader) File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/pytorch_lightning/loops/base.py", line 118, in run output = self.on_run_end() File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/pytorch_lightning/loops/epoch/training_epoch_loop.py", line 235, in on_run_end self._on_train_epoch_end_hook(processed_outputs) File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/pytorch_lightning/loops/epoch/training_epoch_loop.py", line 275, in _on_train_epoch_end_hook trainer_hook(processed_epoch_output) File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/pytorch_lightning/trainer/callback_hook.py", line 109, in on_train_epoch_end callback.on_train_epoch_end(self, self.lightning_module) File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/pytorch_lightning/callbacks/early_stopping.py", line 170, in on_train_epoch_end self._run_early_stopping_check(trainer) File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/pytorch_lightning/callbacks/early_stopping.py", line 185, in _run_early_stopping_check logs File "/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/pytorch_lightning/callbacks/early_stopping.py", line 134, in _validate_condition_metric raise RuntimeError(error_msg) RuntimeError: Early stopping conditioned on metricreconstruction_loss_validationwhich is not available. Pass in or modify yourEarlyStoppingcallback to use any of the following:elbo_train,reconstruction_loss_train,kl_local_train,kl_global_train/home/paulyr2/miniconda/envs/solo/lib/python3.6/site-packages/tqdm/std.py:538: TqdmWarning: clamping frac to range [0, 1] Epoch 1/2000: -0%|Suggestions?
Thanks!
The text was updated successfully, but these errors were encountered: