Conversation
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #692 +/- ##
=======================================
Coverage 82.94% 82.94%
=======================================
Files 10 10
Lines 2720 2720
=======================================
Hits 2256 2256
Misses 464 464 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
hombit
force-pushed
the
embed
branch
3 times, most recently
from
46e1e2f to
8c52b8f
Compare
Merging this PR will improve performance by 14.42%
|
| Mode | Benchmark | BASE |
HEAD |
Efficiency | |
|---|---|---|---|---|---|
| ⚡ | Simulation | test_benchmark_lc_py |
769.4 µs | 672.4 µs | +14.42% |
Comparing embed (e4a2b5c) with main (0adec0b)2
Footnotes
-
106 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩
-
No successful run was found on
main(e4a2b5c) during the generation of this report, so 0adec0b was used instead as the comparison base. There might be some changes unrelated to this pull request in this report. ↩
hombit
added a commit
that referenced
this pull request
May 8, 2026
hombit
force-pushed
the
embed
branch
4 times, most recently
from
c52fab6 to
7c175e3
Compare
…base Introduces the core infrastructure for the new `light_curve.embed` module: - `TimeReduction` / `SingleSubsampleTimeReduction` / `MultipleTimeReductions` — abstract base and concrete strategies (Beginning, End, RandomSubsample, NonOverlappingWindows) for mapping variable-length light curves to fixed-length sequences - `EmbeddingSession` / `SingleBandModel` — abstract ONNX session wrappers with preprocessing, masking, padding, and per-band dispatch - `InputTensors` / `AstromerInputs` — typed dataclass containers for model inputs - `Dim` — IntEnum of axis indices for the 4-D output array
- `Astromer1` / `Astromer2` — transformer encoders pretrained on MACHO light curves (Donoso-Oliva et al. 2023/2026), returning 256-d embeddings via ONNX - `create_onnx_session` — helper with actionable ImportError for missing runtimes - `from_hf()` classmethod for one-call download from HuggingFace Hub - Tests covering preprocessing, output shapes, reference-embedding cosine similarity, and round-trip session equivalence - CHANGELOG entry
TimeReduction had no specific connection to time; Reduction is cleaner. - `TimeReduction` → `Reduction` - `SingleSubsampleTimeReduction` → `SingleSubsampleReduction` - `MultipleTimeReductions` → `MultipleReductions` - `time_reduction_from_str` → `reduction_from_str` - `time_reduction` parameter/attribute → `reduction` throughout - `time_reduction.py` → `reduction.py`
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.
No description provided.