Oren Amsalem

I understand, but I used your conda envierment ```conda create -n neuronvisio_env neuronvisio -c mattions``` doesn't it suppose to install all the requirements? Thanks Michele.

Thanks, I tried importing pyqt ```(neuronvisio_env) oren.amsalem@bream ~ $ ipython ipython Python 2.7.13 | packaged by conda-forge | (default, May 2 2017, 12:48:11) Type "copyright", "credits" or "license" for more...

```conda create -n neuronvisio_env1 neuronvisio -c mattions Fetching package metadata ........... Solving package specifications: .......... Package plan for installation in environment /home/ls/users/oren.amsalem/anaconda2/envs/neuronvisio_env1: The following packages will be downloaded: package |...

Thanks @rwightman for the detailes, I am also intrested in the labels of the classes. I did try the code that you suggsetd: ```python model_id = 'timm/resnetrs350.tf_in1k' model = timm.create_model(f"hf_hub:{model_id}",...

Thanks @WenChentao, I actually did not know that the model also use probability maps. I'll get in the details of my pipeline, and maybe it will help. We use 2p...

Thanks @WenChentao do you have an example of those ` 'coordst0001.npy' and 'probt0001.npy' ` files so I can try to recreate them?

for the case where ref is first image or mean it can be added here, https://github.com/glichtner/pystackreg/blob/28d4c625e8542cddae8c3e8b9ad85dce0ef46147/pystackreg/pystackreg.py#L416 I'll create a pull request.

see here: https://github.com/glichtner/pystackreg/pull/17

Any updates? Thanks.

There is also nvtop here: https://github.com/Syllo/nvtop  which is written in C