Trackastra

https://github.com/weigertlab/trackastra
Admin
Trackastra is a transformer-based cell tracking approach that links segmented cells in microscopy...
Tokens:1,853
Snippets:26
Trust Score:8.1
License:BSD-3-Clause
Update:5 months ago
Show doc for...
Tokens:
Raw
### Install Trackastra with training support

Source: https://github.com/weigertlab/trackastra/blob/main/README.md

Install Trackastra with all necessary dependencies for training custom models.

```bash
pip install "trackastra[train]"
```

--------------------------------

### Install Trackastra with ILP support

Source: https://github.com/weigertlab/trackastra/blob/main/README.md

Install Trackastra with optional Integer Linear Programming (ILP) support, which requires conda and specific channel installations for optimizers like Gurobi or SCIP.

```bash
conda create --name trackastra python=3.10 --no-default-packages
conda activate trackastra
conda install -c conda-forge -c gurobi -c funkelab ilpy
pip install "trackastra[ilp]"
```

--------------------------------

### Install Trackastra with pip

Source: https://github.com/weigertlab/trackastra/blob/main/README.md

Install the core Trackastra package from PyPI for basic functionality.

```bash
pip install trackastra
```

--------------------------------

### Development installation of Trackastra

Source: https://github.com/weigertlab/trackastra/blob/main/README.md

Set up a development environment for Trackastra, including ILP support and installing the package in editable mode. This is useful for contributing to the project or making modifications.

```bash
conda create --name trackastra python=3.10 --no-default-packages
conda activate trackastra
conda install -c conda-forge -c gurobi -c funkelab ilpy
git clone https://github.com/weigertlab/trackastra.git
pip install -e "./trackastra[all]"
```

--------------------------------

### Install Trackastra with pretrained features (ETUltra)

Source: https://github.com/weigertlab/trackastra/blob/main/README.md

Install Trackastra with support for the new model variant using SAM2 features for improved tracking performance, particularly for bacteria. This option is recommended for machines with a GPU.

```bash
pip install "trackastra[etultra]"
```

--------------------------------

### Trackastra CLI Help

Source: https://github.com/weigertlab/trackastra/blob/main/README.md

Display help information for the Trackastra command-line interface, useful for understanding available tracking options.

```bash
trackastra track --help
```

--------------------------------

### Train Trackastra Model

Source: https://github.com/weigertlab/trackastra/blob/main/README.md

Run the training script with a specified configuration file. Ensure you have cloned the repository and downloaded the dataset.

```bash
python train.py --config example_config.yaml
```

--------------------------------

### Run Trackastra via Docker

Source: https://github.com/weigertlab/trackastra/blob/main/README.md

Execute Trackastra within a Docker container, mounting local directories for data and results. Specify the model tag and input dataset details.

```bash
docker run -it -v <LOCAL_DATA_DIR>:/data -v <LOCAL_RESULTS_DIR>:/results bentaculum/trackastra-track:<MODEL_TAG> --input_test /data/<DATASET_IN_CTC_FORMAT> --detection_folder <TRA/SEG/ETC>
```

```bash
wget http://data.celltrackingchallenge.net/training-datasets/Fluo-N2DH-GOWT1.zip 
chmod -R 775 Fluo-N2DH-GOWT1
docker pull bentaculum/trackastra-track:model.ctc-linking.ilp 
docker run -it -v ./:/data -v ./:/results bentaculum/trackastra-track:model.ctc-linking.ilp --input_test data/Fluo-N2DH-GOWT1/01 --detection_folder TRA
```

--------------------------------

### Track Cells with Trackastra Python API

Source: https://github.com/weigertlab/trackastra/blob/main/README.md

Load pretrained models and track cells using images and masks. Supports different tracking modes like 'greedy' and 'ilp'. Outputs can be converted to CTC or GEFF formats.

```python
import torch
from trackastra.model import Trackastra
from trackastra.tracking import graph_to_ctc, graph_to_napari_tracks, write_to_geff
from trackastra.data import example_data_bacteria

device = "automatic" # explicit choices: [cuda, mps, cpu]

# load some test data images and masks
imgs, masks = example_data_bacteria()

# Load a pretrained model
model = Trackastra.from_pretrained("general_2d", device=device)

# or from a local folder
# model = Trackastra.from_folder('path/my_model_folder/', device=device)

# Track the cells
track_graph, masks_tracked = model.track(imgs, masks, mode="greedy")  # or mode="ilp", or "greedy_nodiv"

# Relabel the masks and write to cell tracking challenge format (CTC), 
ctc_tracks, ctc_masks = graph_to_ctc(
    track_graph,
    masks_tracked,
    outdir="tracked_ctc",
)

# Or write to the graph exchange file format (GEFF)
write_to_geff(
    track_graph,
    masks_tracked,
    outdir="tracked_geff.zarr",
)
```

```python
# Visualise in napari
napari_tracks, napari_tracks_graph, _ = graph_to_napari_tracks(track_graph)

import napari
v = napari.Viewer()
v.add_image(imgs)
v.add_labels(ctc_masks)
v.add_tracks(data=napari_tracks, graph=napari_tracks_graph)
```

--------------------------------

### Trackastra BibTeX Reference

Source: https://github.com/weigertlab/trackastra/blob/main/README.md

BibTeX entry for citing the Trackastra paper. Include this in your LaTeX documents for academic references.

```bibtex
@inproceedings{gallusser2024trackastra,
  title={Trackastra: Transformer-based cell tracking for live-cell microscopy},
  author={Gallusser, Benjamin and Weigert, Martin},
  booktitle={European conference on computer vision},
  pages={467--484},
  year={2024},
  organization={Springer}
}
```
Tokens:
Raw