New Top-Down Pose Estimation Model - RTMPose#2795
Merged
n-poulsen merged 53 commits intopytorch_dlcfrom Dec 20, 2024
Merged
Conversation
maximpavliv
suggested changes
Dec 10, 2024
deeplabcut/pose_estimation_pytorch/config/rtmpose/rtmpose_x.yaml
Outdated
Show resolved
Hide resolved
This 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
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull requests adds the implementation for RTMPose: Real-Time Multi-Person Pose Estimation.
Full changes:
HuggingFaceWeightsMixinCSPNeXtRTMCCHeadSimCCGeneratorSimCCPredictorRtmposeRandomBBoxTransformaugmentation for top-down models (jitters ground truth bounding boxes)CSPNeXtbackbones:cspnext_s,cspnext_m,cspnext_xRTMPosemodels:rtmpose_s,rtmpose_m,rtmpose_xSequentialLR(to match the RTMPose training schedulers)SequentialLRscheduler for warm-up epochstop_down_crop_size: (crop_w, crop_h)andtop_down_crop_marginin thepytorch_config.yamlfile for an easy way to control the size of the crops for top-down models.bbox_from_keypointswhen there's more than 1 individual (bug had no impact as method was always called in a way it wouldn't fail)DEMO
ski-dlc.mov