Video Analysis with Identity - Lowering memory footprint by n-poulsen · Pull Request #2785 · DeepLabCut/DeepLabCut
Navigation Menu
{{ message }}
DeepLabCut / DeepLabCut Public
- Notifications You must be signed in to change notification settings
- Fork 1.8k
Merged
n-poulsen merged 4 commits intopytorch_dlcfrom
Nov 14, 2024Merged
Video Analysis with Identity - Lowering memory footprint#2785
n-poulsen merged 4 commits intopytorch_dlcfrom
Video Analysis with Identity - Lowering memory footprint#2785
n-poulsen merged 4 commits intopytorch_dlcfrom
Conversation
Copy link
Contributor
n-poulsen
commented
Nov 13, 2024
n-poulsen
commented
This PR fixes a memory issue when running video analysis using a model with an identity head, as reported in #2771.
Improvements
PadOutputs: instead of needing to set"key": 0for outputs we don't want to pad (such asidentity_heatmap), check if each output is present in themax_individualsdict to see if padding is needed.PredictKeypointIdentities: Models with identity heads would output the identity heatmaps, which leads to memory issues when analyzing large videos. Akeep_id_maps=Falseparameter is added, only keep identity heatmaps in the output when explicitly requested.assign_identity: use the pose confidence to weight identity scores when assigning identity, as done in theTensorFlowimplementation
Bug fixes
make_pytorch_test_configwhen there are unique bodyparts for a project. The unique bodyparts need to be included inall_joint_namesandall_joints, otherwise video analysis fails.
n-poulsen added 3 commits
November 11, 2024 17:06
n-poulsen
requested a review
from maximpavliv
n-poulsen
mentioned this pull request
2 tasks
maximpavliv approved these changes Nov 13, 2024
deeplabcut/pose_estimation_pytorch/data/postprocessor.py
Outdated
Show resolved
Hide resolved
deeplabcut/pose_estimation_pytorch/data/postprocessor.py Outdated Show resolved Hide resolved
n-poulsen
merged commit
e4ca5bc
into
pytorch_dlc
n-poulsen
deleted the
niels/analyze_videos_with_id_memory_issue
branch
xiu-cs pushed a commit to xiu-cs/DeepLabCut that referenced this pull request
Nov 25, 2024This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment