topaz
topaz copied to clipboard
tbepler
Pipeline for particle picking in cryo-electron microscopy images using convolutional neural networks trained from positive and unlabeled examples. Also featuring micrograph and tomogram denoising with...
### Discussed in https://github.com/tbepler/topaz/discussions/172 Originally posted by **wuhucryoem** July 24, 2023 When I do a topaz training, it show me there haven't some file or directory, but don't show me...
Looks like the error I get is due to the MRC package that I have versus the one Topaz assumes there to be is incompatible. requirements.txt does not list the...
I follow the Quick start guide and get the predicted_particles_all.txt However, when I try to visualize the result and import libraries as the guide, here came the bug. It seems...
Hi, I just tested the singularity container and it the command 'topaz --version' works just fine. I did notice that the version in the container is still 0.2.4 instead of...
Here is the error message. Topaz Cross Validation: Traceback (most recent call last): File “cryosparc_worker/cryosparc_compute/run.py”, line 93, in cryosparc_compute.run.main File “/data/cryosparc/cryosparc_worker/cryosparc_compute/jobs/topaz/run_topaz.py”, line 794, in run_topaz_wrapper_cross_validation assert len(tables) > 0, “All...
Hi - just a minor thing but the --output flag is missing in the Topaz GUI for training of new denoise models (there is only a --save_prefix flag). It's easy...
Training on large datasets raises OOM error before training. Need some alternative such as storing in normal RAM or loading on-the-fly.
Samplers in topaz/utils/data/sampler.py need adjusting to keep track of individual sizes instead of group[0]'s only
Hi there, it looks like there's a bug with Topaz. The line where it is erroring is bad. It should be: pd.concat(groups_train, axis=0) Instead of pd.concat(groups_train, 0)
