2D classification outputs blank classes but with particles assigned & deep inference can not work

Hi,

I am using v4.2.0, and 2D classification outputs blank classes, but these classes has particles and resolution, it’s confusing. And sometimes, it displays weird result in the job overview interface.

what’s more, I can use deep picker train, it works well. BUT deep picker inference are always aborted when reading the original micrograph. (The imported movies are .eer format, it’s eer’s fault?)

if I link the micrograph input of inference with the curate exposures job, it outputs error:
Traceback (most recent call last):
File “cryosparc_master/cryosparc_compute/run.py”, line 96, in cryosparc_compute.run.main
File “cryosparc_master/cryosparc_compute/jobs/deep_picker/run_deep_picker.py”, line 535, in cryosparc_compute.jobs.deep_picker.run_deep_picker.run_deep_picker_inference
File “cryosparc_master/cryosparc_compute/jobs/deep_picker/deep_picker_utils.py”, line 874, in cryosparc_compute.jobs.deep_picker.deep_picker_utils.picker_extract_worker
File “cryosparc_master/cryosparc_compute/jobs/deep_picker/deep_picker_utils.py”, line 879, in cryosparc_compute.jobs.deep_picker.deep_picker_utils.picker_extract_worker
File “cryosparc_master/cryosparc_compute/jobs/deep_picker/deep_picker_utils.py”, line 791, in cryosparc_compute.jobs.deep_picker.deep_picker_utils.picker_extract_worker._do_picking
File “/home/spuser/Software/cryosparc/cryosparc_worker/cryosparc_compute/micrograph_plotutils.py”, line 52, in showarray
a = a.reshape(-1, a.shape[-2], a.shape[-1])
ValueError: cannot reshape array of size 0 into shape (0,1)

if I link the micrograph input of inference with the deep train job, it outputs error:
Traceback (most recent call last):
File “cryosparc_master/cryosparc_compute/run.py”, line 96, in cryosparc_compute.run.main
File “cryosparc_master/cryosparc_compute/jobs/deep_picker/run_deep_picker.py”, line 535, in cryosparc_compute.jobs.deep_picker.run_deep_picker.run_deep_picker_inference
File “cryosparc_master/cryosparc_compute/jobs/deep_picker/deep_picker_utils.py”, line 874, in cryosparc_compute.jobs.deep_picker.deep_picker_utils.picker_extract_worker
File “cryosparc_master/cryosparc_compute/jobs/deep_picker/deep_picker_utils.py”, line 879, in cryosparc_compute.jobs.deep_picker.deep_picker_utils.picker_extract_worker
File “cryosparc_master/cryosparc_compute/jobs/deep_picker/deep_picker_utils.py”, line 801, in cryosparc_compute.jobs.deep_picker.deep_picker_utils.picker_extract_worker._do_picking
File “cryosparc_master/cryosparc_compute/jobs/deep_picker/deep_picker_utils.py”, line 569, in cryosparc_compute.jobs.deep_picker.deep_picker_utils.get_dataset_from_particle_centers
ValueError: need more than 1 value to unpack

I’ve tried to use 64*64 shape of split micrographs in deep train and not using “show plots” feature in deep inference, it still can not work.

SOMEBODY HELPS ME! I appreciate any discussion here.

The weird result in the job overview interface:

A patch for v4.2.0

Were the results you posted obtained using multi-GPU classification jobs?
You may alternatively consider updating to CryoSPARC v4.2.1 and applying the 230427 patch (details).