https://github.com/kirkegaardlab/deeptangle
Code implementation of the detection network capable of dealing with many overlapping spline bodies.
https://github.com/kirkegaardlab/deeptangle
c-elegans computer-vision deep-learning latent-space quantitative-biology single-stage-detector splines
Last synced: 5 months ago
JSON representation
Code implementation of the detection network capable of dealing with many overlapping spline bodies.
- Host: GitHub
- URL: https://github.com/kirkegaardlab/deeptangle
- Owner: kirkegaardlab
- License: mit
- Created: 2023-01-09T13:39:38.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2024-06-01T09:26:26.000Z (about 2 years ago)
- Last Synced: 2024-06-01T10:48:46.620Z (about 2 years ago)
- Topics: c-elegans, computer-vision, deep-learning, latent-space, quantitative-biology, single-stage-detector, splines
- Language: Python
- Homepage:
- Size: 545 KB
- Stars: 33
- Watchers: 4
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# de(ep)tangle
[](https://www.nature.com/articles/s42003-023-05098-1)
[](https://arxiv.org/abs/2301.04460)
This repository contains the implementation of [Fast detection of slender bodies in high density microscopy data](https://www.nature.com/articles/s42003-023-05098-1) paper.
## Installation
To run the code one must first install the dependencies.
You can do this in a virtual environment:
```setup
python3 -m venv venv
source venv/bin/activate
```
Start by installing `jax` following instructions at their [repository](https://github.com/google/jax?tab=readme-ov-file#installation).
Install the remaining dependencies afterwards:
```setup
pip install -r requirements.txt
```
If you need to use the model and the auxiliary functions outside this repository, you can install it from the root folder by
```install
pip install -e .
```
## Train
To train the model, there is a train script used for the model presented in the paper.
The possible arguments can be seen by using the help flag.
```train
python3 train.py --help
```
An example of a training run would be
```train
python3 train.py --batch_size=32 --eval_interval=10 --nworms=100,200 --save
```
## Usage
Example scripts such as detection and tracking can be found in the [examples folder](./examples)
We include a Dockerfile (cpu only). For linux we provide a script to run the relevant commands:
```
(sudo) sh docker_run.sh
```
## Weights
The weights used in the paper can be downloaded from [here](https://sid.erda.dk/share_redirect/cEjIpG1yQl)
or by using the following commmand
```download
wget https://sid.erda.dk/share_redirect/cEjIpG1yQl -O weights.zip
```