make_syllable_movies_wrapper¶
- behavenet.plotting.arhmm_utils.make_syllable_movies_wrapper(hparams, save_file, sess_idx=0, dtype='test', max_frames=400, frame_rate=10, min_threshold=0, n_buffer=5, n_pre_frames=3, n_rows=None, single_syllable=None)[source]¶
Present video clips of each individual syllable in separate panels.
This is a high-level function that loads the arhmm model described in the hparams dictionary and produces the necessary states/video frames.
- Parameters:
hparams (
dict) – needs to contain enough information to specify an arhmmsave_file (
str) – full save file (path and filename)sess_idx (
int, optional) – session index into data generatordtype (
str, optional) – types of trials to make video with; ‘train’ | ‘val’ | ‘test’max_frames (
int, optional) – maximum number of frames to animateframe_rate (
float, optional) – frame rate of saved moviemin_threshold (
int, optional) – minimum number of frames in a syllable run to be considered for movien_buffer (
int) – number of blank frames between syllable instancesn_pre_frames (
int) – number of behavioral frames to precede each syllable instancen_rows (
intorNoneType) – number of rows in output moviesingle_syllable (
intorNoneType) – choose only a single state for movie