spikeinterface
spikeinterface copied to clipboard
SpikeInterface
Error when saving/caching with `resample`
Hi! I'm getting en error when trying to cache a down sampled recording but not on a recording that was only filtered/re-referenced.
When checking the number of samples of the down sampled recrodign with rec_resample.get_num_samples() I get the correct value of samples. However, when I use the rec_resample.get_traces method and check the dimensions I get 0 samples x N_channels.
Code I'm using
new_rate = 2500
rec_resample = pre.resample(rec_probe,
resample_rate = new_rate) # in Hz
rec_resample = rec_resample.save(format='binary',
folder="lfp/preprocessed",
n_jobs=32,
chunk_size=5000,
progress_bar=True)
ERROR
/home/neuroimaging/anaconda2/envs/si_openephys/lib/python3.9/site-packages/spikeinterface/core/job_tools.py:18: DeprecationWarning: invalid escape sequence \I
_shared_job_kwargs_doc = """**job_kwargs: keyword arguments for parallel processing:
---------------------------------------------------------------------------
_RemoteTraceback Traceback (most recent call last)
_RemoteTraceback:
"""
Traceback (most recent call last):
File "/home/neuroimaging/anaconda2/envs/si_openephys/lib/python3.9/concurrent/futures/process.py", line 243, in _process_worker
r = call_item.fn(*call_item.args, **call_item.kwargs)
File "/home/neuroimaging/anaconda2/envs/si_openephys/lib/python3.9/concurrent/futures/process.py", line 202, in _process_chunk
return [fn(*args) for args in chunk]
File "/home/neuroimaging/anaconda2/envs/si_openephys/lib/python3.9/concurrent/futures/process.py", line 202, in <listcomp>
return [fn(*args) for args in chunk]
File "/home/neuroimaging/anaconda2/envs/si_openephys/lib/python3.9/site-packages/spikeinterface/core/job_tools.py", line 337, in function_wrapper
return _func(segment_index, start_frame, end_frame, _worker_ctx)
File "/home/neuroimaging/anaconda2/envs/si_openephys/lib/python3.9/site-packages/spikeinterface/core/core_tools.py", line 218, in _write_binary_chunk
rec_memmap[start_frame:end_frame, :] = traces
ValueError: could not broadcast input array from shape (0,62) into shape (1677,62)
"""
The above exception was the direct cause of the following exception:
ValueError Traceback (most recent call last)
Input In [4], in <cell line: 13>()
3 rec_resample = pre.resample(rec_probe,
4 resample_rate = resample_rate) # in Hz
7 ###rec_cmr = st.common_reference(rec_resample,
8 ### reference='global',
9 ### operator='median')
10
11
12 #### used to make accessing data faster afterwards.
---> 13 rec_resample = rec_resample.save(format='binary',
14 folder="lfp/preprocessed",
15 n_jobs=32,
16 chunk_size=5000,
17 progress_bar=True)
File ~/anaconda2/envs/si_openephys/lib/python3.9/site-packages/spikeinterface/core/base.py:615, in BaseExtractor.save(self, **kwargs)
613 loaded_extractor = self.save_to_zarr(**kwargs)
614 else:
--> 615 loaded_extractor = self.save_to_folder(**kwargs)
616 return loaded_extractor
File ~/anaconda2/envs/si_openephys/lib/python3.9/site-packages/spikeinterface/core/base.py:694, in BaseExtractor.save_to_folder(self, name, folder, verbose, **save_kwargs)
691 self.save_metadata_to_folder(folder)
693 # save data (done the subclass)
--> 694 cached = self._save(folder=folder, verbose=verbose, **save_kwargs)
696 # copy properties/
697 self.copy_metadata(cached)
File ~/anaconda2/envs/si_openephys/lib/python3.9/site-packages/spikeinterface/core/baserecording.py:224, in BaseRecording._save(self, format, **save_kwargs)
221 dtype = self.get_dtype()
223 job_kwargs = {k: save_kwargs[k] for k in job_keys if k in save_kwargs}
--> 224 write_binary_recording(self, file_paths=file_paths, dtype=dtype, **job_kwargs)
226 from .binaryrecordingextractor import BinaryRecordingExtractor
227 cached = BinaryRecordingExtractor(file_paths=file_paths, sampling_frequency=self.get_sampling_frequency(),
228 num_chan=self.get_num_channels(), dtype=dtype,
229 t_starts=t_starts, channel_ids=self.get_channel_ids(), time_axis=0,
230 file_offset=0, gain_to_uV=self.get_channel_gains(),
231 offset_to_uV=self.get_channel_offsets())
File ~/anaconda2/envs/si_openephys/lib/python3.9/site-packages/spikeinterface/core/core_tools.py:285, in write_binary_recording(recording, file_paths, dtype, add_file_extension, verbose, byte_offset, auto_cast_uint, **job_kwargs)
282 init_args = (recording.to_dict(), rec_memmaps_dict, dtype, cast_unsigned)
283 executor = ChunkRecordingExecutor(recording, func, init_func, init_args, verbose=verbose,
284 job_name='write_binary_recording', **job_kwargs)
--> 285 executor.run()
File ~/anaconda2/envs/si_openephys/lib/python3.9/site-packages/spikeinterface/core/job_tools.py:312, in ChunkRecordingExecutor.run(self)
310 returns.append(res)
311 else:
--> 312 for res in results:
313 pass
315 return returns
File ~/anaconda2/envs/si_openephys/lib/python3.9/site-packages/tqdm/notebook.py:258, in tqdm_notebook.__iter__(self)
256 try:
257 it = super(tqdm_notebook, self).__iter__()
--> 258 for obj in it:
259 # return super(tqdm...) will not catch exception
260 yield obj
261 # NB: except ... [ as ...] breaks IPython async KeyboardInterrupt
File ~/anaconda2/envs/si_openephys/lib/python3.9/site-packages/tqdm/std.py:1195, in tqdm.__iter__(self)
1192 time = self._time
1194 try:
-> 1195 for obj in iterable:
1196 yield obj
1197 # Update and possibly print the progressbar.
1198 # Note: does not call self.update(1) for speed optimisation.
File ~/anaconda2/envs/si_openephys/lib/python3.9/concurrent/futures/process.py:559, in _chain_from_iterable_of_lists(iterable)
553 def _chain_from_iterable_of_lists(iterable):
554 """
555 Specialized implementation of itertools.chain.from_iterable.
556 Each item in *iterable* should be a list. This function is
557 careful not to keep references to yielded objects.
558 """
--> 559 for element in iterable:
560 element.reverse()
561 while element:
File ~/anaconda2/envs/si_openephys/lib/python3.9/concurrent/futures/_base.py:609, in Executor.map.<locals>.result_iterator()
606 while fs:
607 # Careful not to keep a reference to the popped future
608 if timeout is None:
--> 609 yield fs.pop().result()
610 else:
611 yield fs.pop().result(end_time - time.monotonic())
File ~/anaconda2/envs/si_openephys/lib/python3.9/concurrent/futures/_base.py:439, in Future.result(self, timeout)
437 raise CancelledError()
438 elif self._state == FINISHED:
--> 439 return self.__get_result()
441 self._condition.wait(timeout)
443 if self._state in [CANCELLED, CANCELLED_AND_NOTIFIED]:
File ~/anaconda2/envs/si_openephys/lib/python3.9/concurrent/futures/_base.py:391, in Future.__get_result(self)
389 if self._exception:
390 try:
--> 391 raise self._exception
392 finally:
393 # Break a reference cycle with the exception in self._exception
394 self = None
ValueError: could not broadcast input array from shape (0,62) into shape (1677,62)
Hi, this resample is quite new and well tested yet. Sorry for that. Could you try to run the same with n_jobs=1 and then send the error trace ?
Hi @samuelgarcia
No problem!
With n_jobs=1 I don't get any error. However, saving the binary file takes a long time, even with a significantly reduced recording (e.g. 100sec). Saving the whole file with n_jobs=1 crashes my jupyter notebook after ~1h.
Can you try this
rec_resample = rec_resample.save(format='binary',
folder="lfp/preprocessed",
n_jobs=1,
chunk_duration='1s',
progress_bar=False)
And copy us the trace ?
