Facemap

Facemap is a framework for predicting neural activity from mouse orofacial movements. It includes a pose estimation model for tracking distinct keypoints on the mouse face, a neural network model for predicting neural activity using the pose estimates, and also can be used compute the singular value decomposition (SVD) of behavioral videos.

For more details, please see our paper and twitter thread.

Basics:

• Installation
  • Common installation issues
  • Dependencies
  • MATLAB package installation
• GUI
  • Starting the GUI
  • Command line usage
  • Using the GUI
    • Pose tracking (GUI)
    • SVD processing and ROIs
    • Neural activity prediction
• Inputs
  • Processing multiple movies
  • Batch processing
  • Data acquisition info
    • IR illumination
    • Cameras
• Outputs
  • ROI and SVD processing
    • Loading outputs
  • Keypoints processing
  • Neural activity prediction output
• Tutorials

API Reference:

• Facemap API Guide
  • Pose estimation
    • Pose
      • Pose.load_model()
      • Pose.predict_landmarks()
      • Pose.save_data_to_hdf5()
      • Pose.save_dict_to_hdf5()
      • Pose.save_model()
      • Pose.set_model()
      • Pose.train()
  • SVD processing
    • process_blink_ROIs()
    • process_pupil_ROIs()
    • process_running()
    • run()
  • Transforms
    • adjust_bbox()
    • adjust_keypoints()
    • adjust_keypoints_for_padding()
    • augment_data()
    • crop_image()
    • get_crop_resize_params()
    • get_cropped_imgs()
    • get_random_factor()
    • pad_img_to_square()
    • pad_keypoints()
    • preprocess_img()
    • randomize_bbox_coordinates()
    • rescale_keypoints()
    • resize_image()
    • resize_keypoints()