Hilda-Azimi's picture
Publish v1.0
4f49d38 verified
|
Raw
History Blame Contribute Delete
1.81 kB
metadata
library_name: lightning-pose
tags:
  - lightning-pose
  - pose-estimation
trained_by: Anna Lakunina
published_by: Hilda Azimi
data_name: DATA_NAME
data_address: he S3 path or data asset ID
backbone: resnet50_animal_ap10k
losses_used:
  - pca_singleview
num_keypoints: 18
keypoint_names:
  - eye_top
  - eye_right
  - eye_bottom
  - eye_left
  - pupil_top
  - pupil_right
  - pupil_bottom
  - pupil_left
  - pupil_top_right
  - pupil_bottom_right
  - pupil_bottom_left
  - pupil_top_left
  - reflection
  - nostril
  - nose_tip
  - whisker_1
  - whisker_2
  - whisker_3
num_views: 1
views:
  - single
epochs: 300-300
train_prob: 0.95
val_prob: 0.05
latest_version: v1.0
perf_metric: supervised_rmse
perf_value: 0.64
perf_unit: resized-px
perf_set: validation

Lightning Pose Model

Published by Hilda Azimi · Trained by Anna Lakunina on DATA_NAME (he S3 path or data asset ID).

  • Backbone: resnet50_animal_ap10k
  • Losses used: ['pca_singleview']
  • Keypoints (18): eye_top, eye_right, eye_bottom, eye_left, pupil_top, pupil_right, pupil_bottom, pupil_left, pupil_top_right, pupil_bottom_right, pupil_bottom_left, pupil_top_left, reflection, nostril, nose_tip, whisker_1, whisker_2, whisker_3
  • Epochs: 300-300, train/val split: 0.95/0.05
  • Supervised RMSE (validation): 0.64 resized-px

Performance

Supervised RMSE (from TensorBoard logs, unit: resized-px - measured on the resized training image, not original-frame pixels). Lower is better. No per-keypoint pixel-error file was found; the numbers below come from the training logs instead. Source: events.out.tfevents.1736539402.f2768a15001d.48.0

Set Final RMSE Best RMSE
train 0.34 0.29
validation 0.77 0.64

Changelog

v1.0

what this model is / what changed