8000 Release SLEAP v1.1.4 · talmolab/sleap · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

SLEAP v1.1.4

Compare
Choose a tag to compare
@talmo talmo released this 17 Jun 19:31
· 429 commits to main since this release
36366a6

Release of SLEAP v1.1.4.

Includes minor bug fixes and GUI enhancements.

Full changelog

  • Single PR: #562
  • Export scores together with tracks in the analysis HDF5 file (#561)
(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)

  • Add Tracks menu -> Delete All Tracks command
    image

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)

  1. Delete any existing environment and start fresh (recommended):
conda env remove -n sleap
  1. 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)

  1. Create a new conda environment (recommended):
conda create -n sleap python=3.6
conda activate sleap
  1. Install from PyPI:
pip install sleap==1.1.4

Or to upgrade an existing installation:

pip install --upgrade --force-reinstall sleap==1.1.4
0