OSError: [Errno 12] Cannot allocate memory

[danli349]

Is it possible to use 12 core cpu and 64GB RAM to run scv.tl.recover_dynamics(adata)?
scv.tl.recover_dynamics(adata)

recovering dynamics (using 1/12 cores)
0%
0/431 [00:00<?, ?gene/s]

---------------------------------------------------------------------------
OSError                                   Traceback (most recent call last)
<ipython-input-159-b72bbac5d528> in <module>
----> 1 scv.tl.recover_dynamics(adata)

~/miniconda3/lib/python3.8/site-packages/scvelo/tools/dynamical_model.py in recover_dynamics(data, var_names, n_top_genes, max_iter, assignment_mode, t_max, fit_time, fit_scaling, fit_steady_states, fit_connected_states, fit_basal_transcription, use_raw, load_pars, return_model, plot_results, steady_state_prior, add_key, copy, n_jobs, backend, **kwargs)
    499     conn = get_connectivities(adata) if fit_connected_states else None
    500 
--> 501     res = parallelize(
    502         _fit_recovery,
    503         var_names,

~/miniconda3/lib/python3.8/site-packages/scvelo/core/_parallelize.py in wrapper(*args, **kwargs)
    120         if pass_queue and show_progress_bar:
    121             pbar = None if tqdm is None else tqdm(total=col_len, unit=unit)
--> 122             queue = Manager().Queue()
    123             thread = Thread(target=update, args=(pbar, queue, len(collections)))
    124             thread.start()

~/miniconda3/lib/python3.8/multiprocessing/context.py in Manager(self)
     55         from .managers import SyncManager
     56         m = SyncManager(ctx=self.get_context())
---> 57         m.start()
     58         return m
     59 

~/miniconda3/lib/python3.8/multiprocessing/managers.py in start(self, initializer, initargs)
    577         ident = ':'.join(str(i) for i in self._process._identity)
    578         self._process.name = type(self).__name__  + '-' + ident
--> 579         self._process.start()
    580 
    581         # get address of server

~/miniconda3/lib/python3.8/multiprocessing/process.py in start(self)
    119                'daemonic processes are not allowed to have children'
    120         _cleanup()
--> 121         self._popen = self._Popen(self)
    122         self._sentinel = self._popen.sentinel
    123         # Avoid a refcycle if the target function holds an indirect

~/miniconda3/lib/python3.8/multiprocessing/context.py in _Popen(process_obj)
    275         def _Popen(process_obj):
    276             from .popen_fork import Popen
--> 277             return Popen(process_obj)
    278 
    279     class SpawnProcess(process.BaseProcess):

~/miniconda3/lib/python3.8/multiprocessing/popen_fork.py in __init__(self, process_obj)
     17         self.returncode = None
     18         self.finalizer = None
---> 19         self._launch(process_obj)
     20 
     21     def duplicate_for_child(self, fd):

~/miniconda3/lib/python3.8/multiprocessing/popen_fork.py in _launch(self, process_obj)
     68         parent_r, child_w = os.pipe()
     69         child_r, parent_w = os.pipe()
---> 70         self.pid = os.fork()
     71         if self.pid == 0:
     72             try:

OSError: [Errno 12] Cannot allocate memory

Thanks

[WeilerP]

This obviously depends on the size of your dataset. I suggest you reduce the number of jobs.