search

tbepler / topaz

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 DNNs.
GNU General Public License v3.0
169 stars 63 forks source link

Installation problem and presence of Unet-3d-10a in v0.2.4 #54

Closed dgvjay closed 4 years ago

dgvjay commented 4 years ago

Hi Topaz creators and community.

I have just started using Topaz for cryoET and ran into an installation problem.

I installed Topaz into my conda environment and installation went well but after I activate my Topaz environment, it does not seem to recognize Topaz commands. A screenshot is attached. I guess something is wrong with my [conda?](url Topaz Installation problem )

Another question is regarding the presence of Unet-3d-10a in v0.2.4. I guess using the -m Unet-3d-10a should suffice or do we need to currently download this model from somewhere else?

Thanks for the software and your support.

Cheers,

tbepler commented 4 years ago

It looks like you still need to install Topaz into your conda environment. There are instructions here, but the gist of it is that you need to run 

conda install topaz -c tbepler -c pytorch

from within your Topaz environment.

All of the pretrained models, including unet-3d-10a, are bundled with the topaz package so they will be installed automatically.

dgvjay commented 4 years ago

Ohh, damn. I had a terrible brain-freeze. I created the topaz environment but did not install anything in it. Extremely sorry about that.

Thanks!

tbepler commented 4 years ago

No worries! I am going to close this issue since it sounds like the problem is resolved.