Spaces:
Sleeping
Sleeping
File size: 2,593 Bytes
d1ecac0 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 | """Evaluation — caption-quality metrics + per-sample diagnostics.
Available metrics (all corpus-level, 0-100 scale where applicable):
* BLEU-1..4 — :mod:`bleu`
* ROUGE-L — :mod:`rouge`
* METEOR — :mod:`meteor` (requires a JRE on PATH)
* CIDEr — :mod:`cider` (requires >= 2 examples)
:func:`compute_all_metrics` in :mod:`runner` is the single entry point used
by the CLI and by future Phase 3 benchmark comparisons; per-sample
diagnostics live in :mod:`inspection`. Phase 3 latency timing lives in
:mod:`latency`, and the dashboard data export in :mod:`dashboard`.
"""
from captioning.evaluation.benchmark import RunMeta, write_run_artifacts
from captioning.evaluation.bleu import (
BleuBreakdown,
corpus_bleu_breakdown,
corpus_bleu_score,
)
from captioning.evaluation.cider import MIN_SAMPLES_FOR_CIDER, corpus_cider_score
from captioning.evaluation.comparison import (
ComparisonError,
RunRecord,
build_summary,
load_run,
render_markdown,
)
from captioning.evaluation.dashboard import (
DashboardExportError,
build_dashboard_data,
render_dashboard_json,
)
from captioning.evaluation.inspection import (
SampleDiagnostics,
diagnose_many,
diagnose_sample,
format_diagnostic_row,
write_diagnostics_jsonl,
)
from captioning.evaluation.latency import (
BatchLatency,
LatencyBenchmarkError,
LatencySettings,
measure_latency,
runtime_info,
summarize,
time_load,
)
from captioning.evaluation.meteor import corpus_meteor_score
from captioning.evaluation.rouge import corpus_rouge_l_score
from captioning.evaluation.runner import MetricsReport, compute_all_metrics
from captioning.evaluation.slice import EvalSlice, load_eval_slice, slice_fingerprint
__all__ = [
"MIN_SAMPLES_FOR_CIDER",
"BatchLatency",
"BleuBreakdown",
"ComparisonError",
"DashboardExportError",
"EvalSlice",
"LatencyBenchmarkError",
"LatencySettings",
"MetricsReport",
"RunMeta",
"RunRecord",
"SampleDiagnostics",
"build_dashboard_data",
"build_summary",
"compute_all_metrics",
"corpus_bleu_breakdown",
"corpus_bleu_score",
"corpus_cider_score",
"corpus_meteor_score",
"corpus_rouge_l_score",
"diagnose_many",
"diagnose_sample",
"format_diagnostic_row",
"load_eval_slice",
"load_run",
"measure_latency",
"render_dashboard_json",
"render_markdown",
"runtime_info",
"slice_fingerprint",
"summarize",
"time_load",
"write_diagnostics_jsonl",
"write_run_artifacts",
]
|