Merge DeltaFlow into codebase #21
Open
Conversation
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
* conf(optimization-based): update all config files. * todo: update model file, double check with yancong and Qingwen confirm that: icp-flow results can be reproduced and tested.
* hotfix(ssf): bug fixes in seflow+ssf as ssf concat two pc and forget to - index.
* add data with lidar_id and lidar_dt * add flow_instances for afterward easy deltaflow update.
* tested with demo good, need double check the results on av2 and update the training time & weight link also.
* it could be a good reference for users to extract other data into h5 files etc.
- update from DeltaFlow. - align some format with copilot comments. * update other submodule repo to align the lr changed.
… trainining setup.
* add some notes
…ed rm ground mask also.
align with paper.
* checked with trained weight.
update README to show the progress.
to avoid killed during eval.
* update av2_mode to data_mode. * revert back for zod process file * runner metric is good in last version as it's range_bucket have different meaning.
Kin-Zhang
commented
Sep 28, 2025
There was a problem hiding this comment.
this should be have a note to readers as previously it's 100x100 evaluation = 50m evaluation range
| python train.py model=deltaFlow optimizer.lr=2e-3 epochs=20 batch_size=2 num_frames=5 loss_fn=deflowLoss "voxel_size=[0.15, 0.15, 0.15]" "point_cloud_range=[-38.4, -38.4, -3.2, 38.4, 38.4, 3.2]" +optimizer.scheduler.name=WarmupCosLR +optimizer.scheduler.max_lr=2e-3 +optimizer.scheduler.total_steps=20000 | ||
|
|
||
| # Pretrained weight can be downloaded through: | ||
| wget https://huggingface.co/kin-zhang/OpenSceneFlow/resolve/main/flow4d_best.ckpt |
There was a problem hiding this comment.
update the correct weight ckpt link here.
* we only evaluated points on non-ground point. * no need print ssf_metrics since our train range is out of evaluation.
Kin-Zhang
commented
Sep 29, 2025
| * n_frames: the number of frames we use, default is 2: current (pc0), next (pc1); if it's more than 2, then it read the history from current. | ||
| * ssl_label: if attr, it will read the dynamic cluster label. Otherwise, no dynamic cluster label in data dict. | ||
| * eval: if True, use the eval index (only used it for leaderboard evaluation) | ||
| * eval_input_seq: I forgot what it is.... xox... |
There was a problem hiding this comment.
eval_input_seq is previous developed code, maybe deleted it for clear understanding.
Kin-Zhang
commented
Sep 29, 2025
| self.history_frames = n_frames - 2 | ||
| self.vis_name = vis_name if isinstance(vis_name, list) else [vis_name] | ||
| self.transform = transform | ||
| self.flow_num = flow_num |
There was a problem hiding this comment.
same to above, deleveloped code previously.
|
some things need added into tools:
|
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.
DeltaFlow got accepted by NeurIPS 2025 and it's spotlighted! 🎉🎉🎉 Now I'm working on releasing the code.
Please check the progress in the DeltaFlow repo now: https://github.com/Kin-Zhang/DeltaFlow
Once it's ready, I will merge it into the codebase with the full README.