SLEAP v1.1.4
Release of SLEAP v1.1.4.
Includes minor bug fixes and GUI enhancements.
Full changelog
(sleap) $ sleap-convert -o labels.analysis.h5 --format analysis "labels.slp"
track_names: 27
node_names: 24
tracks: (1100, 24, 2, 27)
track_occupancy: (27, 1100)
point_scores: (1100, 24, 27)
instance_scores: (1100, 27)
tracking_scores: (1100, 27)
Saved as labels.analysis.h5
- Add support for model folder in
sleap-inspect
:
(sleap) $ sleap-inspect models\minimal_instance.UNet.centered_instance
=====
Model: models\minimal_instance.UNet.centered_instance
=====
=====
Heads:
=====
HeadsConfig(single_instance=None, centroid=None, centered_instance=CenteredInstanceConfmapsHeadConfig(anchor_part=None, part_names=['A', 'B'], sigma=1.5, output_stride=2, offset_refinement=True), multi_instance=None)
=====
=====
Backbone:
=====
BackboneConfig(leap=None, unet=UNetConfig(stem_stride=None, max_stride=8, output_stride=2, filters=16, filters_rate=1.5, middle_block=True, up_interpolate=False, stacks=1), hourglass=None, resnet=None, pretrained_encoder=None)
=====
=====
Training set:
=====
Frames: 1 / Instances: 2
Metrics:
Dist (90%/95%/99%): 0.7078190667087902 / 0.7086156922334715 / 0.7092529926532167
OKS VOC (mAP / mAR): 0.9504950495049505 / 0.95
PCK (mean 1.0-10.0 px): 1.0
=====
=====
Validation set:
=====
Frames: 1 / Instances: 2
Metrics:
Dist (90%/95%/99%): 1.377530428143121 / 1.4410399538615883 / 1.4918475744363626
OKS VOC (mAP / mAR): 0.8252475247524752 / 0.85
PCK (mean 1.0-10.0 px): 0.95
=====
=====
Test set:
=====
=====
-
Non-visible points now have text rendered in gray with an asterisk as a clearer visual indicator (#560)
-
Fix color cycle order changing when creating instances from predictions (#518)
Installing
We recommend using Miniconda to install and manage your Python environments. This will also make GPU support work transparently without installing additional dependencies.
See the Installation page in the docs for more info.
Using Conda (Windows/Linux)
- Delete any existing environment and start fresh (recommended):
conda env remove -n sleap
- Create new environment
sleap
(recommended):
conda create -n sleap -c sleap sleap=1.1.4
Or to update inside an existing environment:
conda install -c sleap sleap=1.1.4
Using PyPI (Windows/Linux/Mac)
- Create a new conda environment (recommended):
conda create -n sleap python=3.6
conda activate sleap
- Install from PyPI:
pip install sleap==1.1.4
Or to upgrade an existing installation:
pip install --upgrade --force-reinstall sleap==1.1.4