User Tools

Site Tools


janni

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision Both sides next revision
janni [2020/09/28 16:29]
twagner [Changelog]
janni [2021/05/20 15:33]
twagner
Line 1: Line 1:
 ====== Just Another Noise 2 Noise Implementation (JANNI) ====== ====== Just Another Noise 2 Noise Implementation (JANNI) ======
  
-JANNI implements a neural network denoising tool described in NVIDIA's noise2noise paper: +JANNI implements a neural network denoising tool described in NVIDIA's noise2noise paper: [[https://arxiv.org/abs/1803.04189|Noise2Noise: Learning Image Restoration without Clean Data - arXiv]]
-[[https://arxiv.org/abs/1803.04189|Noise2Noise: Learning Image Restoration without Clean Data - arXiv]]+
  
 It can be trained on your data without the need of ground truth images. It supports MRC and TIFF format. It can be trained on your data without the need of ground truth images. It supports MRC and TIFF format.
  
-JANNI can be used a command line tool but also provides an simple interface to integrate into other programs (see [[janni_tutorial#developer_information|developer information]]). +JANNI can be used a command line tool but also provides an simple interface to integrate into other programs (see [[:janni_tutorial#developer_information|developer information]]). <note> 
-<note>+
   * **License**: MIT   * **License**: MIT
-  * **GitHub repository**: https://github.com/thorstenwagner/sphire-janni +  * **GitHub repository**: [[https://github.com/thorstenwagner/sphire-janni|https://github.com/thorstenwagner/sphire-janni]] 
-</note> +</note> This is an example where we applied JANNI:
-This is an example where we applied JANNI:+
  
-{{ ::results_denoising_trpc4.jpg?800 |}}+{{  :results_denoising_trpc4.jpg?800  }} 
 + 
 +<note important> The denoised micrographs are likely bad to use for further processing besides picking. </note>
  
-<note important> 
-The denoised micrographs are likely bad to use for further processing besides picking. 
-</note> 
 ==== Download ==== ==== Download ====
 +
 === JANNI === === JANNI ===
-Version: 0.2 
  
-Uploaded: 28September 2020+Version: 0.2.1 
 + 
 +Uploaded: 20May 2021
  
 [[https://pypi.org/project/janni/#files|DOWNLOAD]] [[https://pypi.org/project/janni/#files|DOWNLOAD]]
  
 === JANNI General Model === === JANNI General Model ===
 +
 Version: 20190703 (Trained on 1xFalcon 2, 3x Falcon 3, 7xK2 datasets from Arctica / Krios) Version: 20190703 (Trained on 1xFalcon 2, 3x Falcon 3, 7xK2 datasets from Arctica / Krios)
  
Line 34: Line 34:
  
 ==== Known Issues ==== ==== Known Issues ====
 +
 - <del>Issue 0 (Version 0.0.1): On some machines (maybe related to ubuntu 16.04) JANNI complains that imagecodecs module (module for tiff files) cannot be found. However, imagecodecs-lite is installed and the error also occurs if you try to denoise MRC. pip uninstall imagecodecs-lite helps.</del> - <del>Issue 0 (Version 0.0.1): On some machines (maybe related to ubuntu 16.04) JANNI complains that imagecodecs module (module for tiff files) cannot be found. However, imagecodecs-lite is installed and the error also occurs if you try to denoise MRC. pip uninstall imagecodecs-lite helps.</del>
  
 ==== Installation ==== ==== Installation ====
-The following instructions assume that pip and anaconda or miniconda are available.  
  
-1. In case you have a old JANNI environment installed, you might want to remove the old one with: +The following instructions assume that pip and anaconda or miniconda are available. 
 + 
 +1. In case you have a old JANNI environment installed, you might want to remove the old one with:
 <code> <code>
 +
 conda env remove --name janni conda env remove --name janni
 +
 </code> </code>
  
-2. After that, create a new virtual environment: +2. After that, create a new virtual environment: 
 <code> <code>
 conda create -n janni -c anaconda python=3.6 cudnn=7.1.2 libtiff wxPython=4.0.4 conda create -n janni -c anaconda python=3.6 cudnn=7.1.2 libtiff wxPython=4.0.4
 +
 </code> </code>
  
-3. Activate the environment: +3. Activate the environment: 
 <code> <code>
 source activate janni source activate janni
 +
 </code> </code>
  
-Now can install JANNI either for GPUs **or** for CPUs:+Now can install JANNI either for GPUs **or**  for CPUs
 + 
 +4a. **For GPU:**  Install JANNI form PyPi for a GPU machine:
  
-4a. **For GPU:** Install JANNI form PyPi for a GPU machine: 
 <code> <code>
 pip install janni[gpu] pip install janni[gpu]
 +
 </code> </code>
  
-4b. **For CPU:** Install JANNI form PyPi for a CPU machine:+4b. **For CPU:**  Install JANNI form PyPi for a CPU machine: 
 <code> <code>
 pip install janni[cpu] pip install janni[cpu]
 +
 </code> </code>
  
 ==== Getting started ==== ==== Getting started ====
-[[janni_tutorial|Here you can find a tutorial how to denoise your micrograghs with JANNI]]+ 
 +[[:janni_tutorial|Here you can find a tutorial how to denoise your micrograghs with JANNI]]
  
 ==== How to cite ==== ==== How to cite ====
Line 73: Line 86:
 You can cite JANNI using the Zenodo DOI: You can cite JANNI using the Zenodo DOI:
  
-<html> +<html> <a href="https://zenodo.org/badge/latestdoi/192689060"><img src="https://zenodo.org/badge/192689060.svg" alt="DOI"></a> </html>
-<a href="https://zenodo.org/badge/latestdoi/192689060"><img src="https://zenodo.org/badge/192689060.svg" alt="DOI"></a> +
-</html> +
  
 ==== Changelog ==== ==== Changelog ====
 +
 +**JANNI 0.2.1:**
 +
 +  * Because of an libary update, JANNI was not working anymore (No supported model).
 +
 **JANNI 0.2** **JANNI 0.2**
 +
   * Added support for binning. In case you recorded your movies in super resolution mode, but later want to apply JANNI to binned images, you need to bin your images during training. This now happens when 'bin.txt' file is available in the directory that contains the super resolution movies. The file 'bin.txt' simply contains the binning factor (like 2 for 2x binning).   * Added support for binning. In case you recorded your movies in super resolution mode, but later want to apply JANNI to binned images, you need to bin your images during training. This now happens when 'bin.txt' file is available in the directory that contains the super resolution movies. The file 'bin.txt' simply contains the binning factor (like 2 for 2x binning).
   * JANNI now allows to choose between two loss functions: mean squared error (mse) or mean absolute error (mae). The latter is the new default.   * JANNI now allows to choose between two loss functions: mean squared error (mse) or mean absolute error (mae). The latter is the new default.
  
 **JANNI 0.1.2** **JANNI 0.1.2**
 +
   * Fix installation procedure.   * Fix installation procedure.
  
 **JANNI 0.1.0** **JANNI 0.1.0**
 +
   * Add GUI   * Add GUI
   * API changes for crYOLO 1.5   * API changes for crYOLO 1.5
  
 **JANNI 0.0.5** **JANNI 0.0.5**
 +
   * Downgrade tensorflow and numpy again as it leads to long initialization times for some users.   * Downgrade tensorflow and numpy again as it leads to long initialization times for some users.
-  * +  * 
 **JANNI 0.0.4** **JANNI 0.0.4**
 +
   * Improved selection of validation data   * Improved selection of validation data
   * Add more data augmentation   * Add more data augmentation
   * Updated libraries (To Tensorflow 1.12.3 and numpy 1.15.4) to make it compatible with crYOLO   * Updated libraries (To Tensorflow 1.12.3 and numpy 1.15.4) to make it compatible with crYOLO
 +
 +
janni.txt · Last modified: 2021/05/31 14:45 by twagner