Output .h5 files only show one instance where GUI shows many

[anaeguiguren]

Hi!
I am seeking to analyze my manual labels from a SLEAP project (v1.5.1). For this, I exported analyses as HDF5 with the user interface. Next, I opened a Jupyter notebook and ran the code below to inspect the file contents. However, when I inspect the .h5 file, they read only a single instance (see output below) in a frame where I marked 48individuals (which do show up in the GUI). I'm mainly looking for a way to extract positions from all the instances across all frames, but I'm not sure how to fix this? Thanks so much in advance for your time, and sorry if this is a very basic question!

**with h5py.File(filename, "r") as f:
dset_names = list(f.keys())
locations = f["tracks"][:].T
node_names = [n.decode() for n in f["node_names"][:]]

print("===filename===")
print(filename)
print()

print("===HDF5 datasets===")
print(dset_names)
print()

print("===locations data shape===")
print(locations.shape)
print()

print("===nodes===")
for i, name in enumerate(node_names):
print(f"{i}: {name}")
print()**

_===filename===
SLEAP_outputs/InterSpecies_Interactions_Formations_v1.5_proofread.000_Gal2023_DJIMini2_20230217_083958.analysis.h5

===HDF5 datasets===
['edge_inds', 'edge_names', 'instance_scores', 'labels_path', 'node_names', 'point_scores', 'provenance', 'track_names', 'track_occupancy', 'tracking_scores', 'tracks', 'video_ind', 'video_path']

===locations data shape===
(16424, 3, 2, 1)

===nodes===
0: snout
1: dorsal
2: fluke_

[eberrigan]

Hello,

This looks ok to me. It looks like the shape of your locations (instances, nodes, x-y, score).

Can you export this as a CSV and let us know if it doesn't give you what you were looking for?

Thanks!

Elizabeth