Official repository of DeepFLasH2 - a deep learning pipeline for segmentation of fluorescent labels in microscopy images.

The best of two worlds: Combining state of the art deep learning with a barrier free environment for life science researchers.

• End-to-end process for life science researchers
  • no coding skills required
  • free usage on Google Colab at no costs
  • easy deployment on own hardware
• Rigorously evaluated deep learning models
  • Model Library
  • easy integration new (pytorch) models
• Best practices model training
  • leveraging the fastai library
  • mixed precision training
  • learning rate finder and fit one cycle policy
  • advanced augementation
• Reliable prediction on new data
  • leveraging Bayesian Uncertainties

tbd

You can use deepflash2 by using Google Colab. You can run every page of the documentation as an interactive notebook - click "Open in Colab" at the top of any page to open it.

• Be sure to change the Colab runtime to "GPU" to have it run fast!
• Use Firefox or Google Chrome if you want to upload your images.

You can install deepflash2 on your own machines with conda (highly recommended):

conda install -c fastai -c pytorch -c matjesg deepflash2 

To install with pip, use

pip install deepflash2

If you install with pip, you should install PyTorch first by following the PyTorch installation instructions.

Docker images for deepflash2 are built on top of the latest pytorch image and fastai images. You must install Nvidia-Docker to enable gpu compatibility with these containers.

• CPU only

docker run -p 8888:8888 matjesg/deepflash

• With GPU support (Nvidia-Docker must be installed.) has an editable install of fastai and fastcore.

docker run --gpus all -p 8888:8888 matjesg/deepflash All docker containers are configured to start a jupyter server. deepflash2 notebooks are available in the deepflash2_notebooks folder.

For more information on how to run docker see docker orientation and setup and fastai docker.

We provide a model library with pretrained model weights. Visit our model library documentation for information on the datasets of the pretrained models.

If you don't have labelled training data available, you can use this instruction manual for creating segmentation maps. The ImagJ-Macro is available here.

A Deep-learning pipeline for Fluorescent Label Segmentation that learns from Human experts