bubbleid 0.0.3

BubbleID Framework

---

This package is for analyzing pool boiling images and is from the paper: BubbleID:A deep learning framework for bubble interface dynamics analysis. It combines tracking, segmentation, and classification models and is trained on manually labeled pool boiling data. It is used for departure classification, velocity interface prediction, bubble statistics extraction.

• This is an updated version of BubbleID for the past version please see here.

Installation:

• First download and install the latest Microsoft C++ Build Tools
• Create a new enviroment with python 3.10, we used anaconda
• Update dependences:

  pip install --upgrade pip setuptools wheel
  

• Install detectron2:

  pip install git+https://github.com/facebookresearch/detectron2
  

• Install Additional Dependencies:

  pip install numpy==1.23 opencv-python filterpy super-gradients
  

• Install BubbleID:

  pip install bubbleid
  

Using the BubbleID Framework:

The BubbleID framework has pretrained models for our in lab pool boiling images. This section goes over how to use these models to analyze image data. These models may need finetuning with your own data. More on this is provided later.

Model	Weights	Description
Instance Segmentation	Link	Model weights for the instance segmentation model.
Classification	Link	Model weights for the departure classification model.

For the model both an avi video and corresponding .jpg images of each frame must be provided.

Tutorials

• For convience, tutorials are provided in the github to demonstrate how to use BubbleID to generate your own data.
• The tutorials use the testing data found here:

Training your own model:

1. Annotate image data, Lableme was used for our dataset.
2. Convert labelme dataset to yolo format
3. Run training
4. See Using the BubbleID Framework but use your new model weights