BisQue v1.0.1

Minor Release

This release is mostly comprised of bug fixes and uploading missing files. For further information on the changes we made for the Dockerfile, please check out the merged request below.

What's Changed

• Added BASE Dockerfile by @amilworks in #43

Run BisQue using Docker

Download

Ensure you have the latest release by first running the following pull command:

docker pull amilworks/bisque-module-dev:git

Run the BisQue Docker Container

To run the docker version of BisQue locally, start a bisque server on the host port 8080:

docker run --name bisque --rm -p 8080:8080 amilworks/bisque-module-dev:git

and point your browser at http://localhost:8080. You should see a BisQue homepage similar to the one on bisque.ece.ucsb.edu. If you do not see the homepage, check to make sure that port 8080 is not being used by another container or application and that you have correctly mapped the ports using -p 8080:8080, where -p is short for port.

Full Changelog: v1.0.0...v1.0.1

BisQue v1.0.0

BisQue2

We have moved to v1.0.0! This new release brings a new module backend that is powered by the powerful Argo Workflow Engine and a new storage backend that creates an iRODS user and a Minio S3 bucket for that user. We have also cleaned up our Dockerfile to make it easier to build and develop for BisQue.

Features

• Argo Workflows for running modules in BisQue
• iRODS as main storage backend
• Automatic iRODS user creation
• Minio S3 bucket for each user to facilitate hyperscale deep learning training
• Enabled OpenID
• Easier builds for BisQue developers with new Multi-stage Dockerfile

Run BisQue using Docker

Download

Ensure you have the latest release by first running the following pull command:

  docker pull amilworks/bisque-module-dev:git

Intro: BisQue Docker Container

Run the BisQue Docker Container

To run the docker version of BisQue locally, start a bisque server on the host port 8080:

docker run --name bisque --rm -p 8080:8080 amilworks/bisque-module-dev:git

and point your browser at http://localhost:8080. You should see a BisQue homepage similar to the one on bisque.ece.ucsb.edu. If you do not see the homepage, check to make sure that port 8080 is not being used by another container or application and that you have correctly mapped the ports using -p 8080:8080, where -p is short for port.

Full Changelog: v0.7...v1.0.0

BisQue v0.7

This release focused on deploying Two New Modules to the BisQue platform. The work was in conjunction with UC Riverside's Electrical and Computer Engineering Department. We also have updated the NPH prediction module.

We have also updated our documentation which is always an ever growing compilation of BisQue goodness. Fell free to file an issue if there are missing details, extra clarification needed, or an example you feel would be useful to the BisQue community.
Documentation Link: https://ucsb-vrl.github.io/bisqueUCSB/

New Modules

Cell Segmentation 2D

• This module implements watershed segmentation in 2D for cell segmentation of Arabidopsis thaliana. The module takes as input a TIFF image with a z-stack and outputs the segmented image in a TIFF z-stack, respectively.

Enhanced Reconstruction

• This module implements a latent space quantization model that generates an enhanced z-stack given a noisy input of Arabidopsis thaliana. For more details, take a look at the paper Deep Quantized Representation for Enhanced Reconstruction.
  Paper Link: https://vcg.ece.ucr.edu/sites/g/files/rcwecm2661/files/2020-05/ISBI2020_CellEnhancement.pdf

Updated Modules

NPH Prediction

• We have updated this module to output 7 classes and the trained model has been retrained with new data. This work is in conjunction with UC Irvine. There will be more updates to this module in the coming months so stay tuned!

BisQue v0.6.2

This release updates the codebase to reflect a better overall structure for build, test, and deployment pipelines.

Main Changes:

• Updated code structure
• Fixed broken dependencies
• Added Dockerfile for build state

BisQue v0.6

June 2020: BisQue v0.6

We are bringing a small list of updates for this version that include TWO new modules, an updated image converter to better handle TIFF files and various bug fixes. A full detailed list can be found below!

This release includes

• NPH Prediction Module
• CellECT 2.0 Module
• Updated Image Converter
• Minor bug fixes
• Code clean-up
• Removal of deprecated files
• UI Improvements