Deeplabcut

This is the python package of DeepLabCut. This package includes graphical user interfaces to label your data, and take you from data set creation to automatic behavioral analysis. It also introduces an active learning framework to efficiently use DeepLabCut on large experimental projects.

User guide on BioRxiv: https://www.biorxiv.org/content/early/2018/11/24/476531

This is the python package of DeepLabCut. This package includes graphical user interfaces to label your data, and take you from data set creation to automatic behavioral analysis. It also introduces an active learning framework to efficiently use DeepLabCut on large experimental projects.

User guide on BioRxiv: https://www.biorxiv.org/content/early/2018/11/24/476531

- Expanded documentation
- Frames to label are not temporally sorted as in the video
- Frame extraction: Switched to OpenCV (faster and more video codecs supported), kmeans clustering is now no longer color blind (if color=True), further parameters for kmeans are now accessible from deeplabcut.extract_frames, one can selectively select images only for specific videos
- Project creation: bugfix.
- Dependency: fixed to pytables 3.4.3 (later versions cause problems)
- New function to analyze time lapse frames (a folder containing a bunch of frames): deeplabcut.analyze_time_lapse_frames

This is the python package of DeepLabCut. This package includes graphical user interfaces to label your data, and take you from data set creation to automatic behavioral analysis. It also introduces an active learning framework to efficiently use DeepLabCut on large experimental projects.

User guide on BioRxiv: https://www.biorxiv.org/content/early/2018/11/24/476531

This is the python package of DeepLabCut. This package includes graphical user interfaces to label your data, and take you from data set creation to automatic behavioral analysis. It also introduces an active learning framework to efficiently use DeepLabCut on large experimental projects.

- documentation updates
- improved GUIs for different platforms
- variable for stopping training added, usage:
deeplabcut.train_network(config,maxiters=int(10**4))
- save as csv added
- add paths in new projects (pep519)
- split paths for windows corrected (Thanks imagejan )

This is the python package of DeepLabCut. This package includes graphical user interfaces to label your data, and take you from data set creation to automatic behavioral analysis. It also introduces an active learning framework to efficiently use DeepLabCut on large experimental projects.

Improved GUIs, and documentation, various bug fixes (swapped colors for opencv in analysis, cropping tools). Thanks for feedback and help.