SkateFormer-B integration, training stack, and research doc sync#2
Merged
Conversation
Introduce upstream ST-TR (gcn_st_tr, st_tr_vit fusion), skeleton baselines, make_experiment_checkpoint_path, gcn_st_tr/st_tr_vit registry categories, vendored ST-TR code, and EC2 tmux targets for gcn_st_tr and st_tr_vit. Co-authored-by: Cursor <cursoragent@cursor.com>
Integrate MediaPipe 16-frame SkateFormer multitask training, centralize clip/batch/MLflow defaults in training_standards.py, extend run_train_tmux.sh (skateformer, st_tr_prep) with backend/mlruns, and align ST-TR trainers with batch 4. Co-authored-by: Cursor <cursoragent@cursor.com>
…ints on main. Bring hga/rkp/vsr pipeline edits into the qwen-4b/qwen-8b/common layout, add FineBadminton research documentation, ST-TR requirements, and collated baseline model weights. Co-authored-by: Cursor <cursoragent@cursor.com>
Introduce four-stream skeleton + ViT late fusion (train_skateformer_b.py, skateformer_b.py, skeleton_streams.py), tmux skateformer_b alias, registry entries, pose-only and fusion checkpoints, and single-video split fix. Co-authored-by: Cursor <cursoragent@cursor.com>
Delete unused trainers and core modules; drop local videomae checkpoints. Keep loading an older pose-cache filename on disk only for backward compatibility. Co-authored-by: Cursor <cursoragent@cursor.com>
Document four-stream MediaPipe-33 + ViT late fusion, training script, EC2 tmux aliases, and early registry primary (49.7% @ epoch 3). Co-authored-by: Cursor <cursoragent@cursor.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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
1 participant
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.
Summary
SkateFormerBFusion,train_skateformer_b.py), EC2run_train_tmux.shaliases, and registry primary at 49.7% valstroke_typeacc @ epoch 3 (early run).docs/RESEARCH.mdto document fusion taxonomy, results table, and §7 novelty framing (including SkateFormer-B).Test plan
python backend/scripts/verify_training_standards.py(or project test entrypoint) passes on a clean venvpytest backend/tests/test_model_registry.py -qpython backend/pipelines/training/train_skateformer_b.py --helpand confirm EC2./scripts/ec2/run_train_tmux.sh skateformer_bresolvestrain_skateformer_b.pydocs/RESEARCH.md§3–§5.6 andmodel_registry.jsonskateformer_bprimary for consistencylogs/or experimental.pthfiles outside LFS registry pathsMade with Cursor