Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

MVP here we come #2

Merged
merged 14 commits into from
Mar 10, 2022
4 changes: 4 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,8 @@ example [workflow-deeplabcut](https://github.com/datajoint/workflow-deeplabcut))

This Element currently supports single-animal, single-camera 2D models, and does not yet support multi-animal or multi-camera models.

This element assumes your labeled data is alrady generated via the DLC gui and that your training and inference data pools are separate.

## The Pipeline Architecture

![element-deeplabcut diagram](images/diagram_dlc.svg)
Expand Down Expand Up @@ -49,6 +51,8 @@ A ***Device*** table must be declared elsewhere to uniqely identify cameras.
pip install "element-data-loader @ git+https://github.com/datajoint/element-data-loader"
```

Note that deeplabcut itself requires a dependency called numba as part of `trackingutils.py`. Numba requires numpy<=1.2. This may conflict with installs of other DataJoint elements, which rely on nwb-conversion-tools, itself requiring numpy>=1.21.0.

## Usage

### Element activation
Expand Down
Loading