Repository Analysis

obss/sahi

Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

14.4 Low AI signal View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of obss/sahi, a Python project with 5,450 GitHub stars. SynthScan v2.0 examined 46,641 lines of code across 294 source files, recording 422 pattern matches distributed across 15 syntactic categories. The overall adjusted score of 14.4 places this repository in the Low AI signal band.

The scanner applied 160+ deterministic lexical heuristics, multi-line block detectors, abstract syntax tree depth profilers, and a cross-file Jaccard similarity matrix to construct a statistically normalised synthetic code estimate. All matches are individually weighted by severity coefficient and contextual multiplier before summation, and the resulting headline score is temporally discounted to account for the repository's development history relative to the commercial emergence of large language model coding tooling (November 2022 onward).

14.4
Adjusted Score
14.4
Raw Score
100%
Time Factor
2026-08-07
Last Push
5.5K
Stars
Python
Language
46.6K
Lines of Code
294
Files
422
Pattern Hits
2026-08-09
Scan Date
0.12
HC Hit Rate

What These Metrics Mean

Adjusted Score
Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score
The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor
The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits
Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate
High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files
Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

Longitudinal tracking requires multiple scan runs. Once this repository is re-scanned after new commits land, this chart will visualise how the synthetic code signal evolves over time — enabling you to detect whether AI authorship is growing, stabilising, or being actively corrected by human engineers.

No multi-scan history yet — run the scanner again to build trend data.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 1HIGH 34MEDIUM 41LOW 346

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 422 distinct pattern matches across 15 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Hyper-Verbose Identifiers158 hits · 168 pts
SeverityFileLineSnippetContext
LOWtests/test_coco_utils.py325 def test_split_coco_as_train_val(self) -> None:CODE
LOWtests/test_coco_utils.py391 def test_coco_update_categories(self) -> None:CODE
LOWtests/test_coco_utils.py626 def test_get_area_filtered_coco(self) -> None:CODE
LOWtests/test_import_utils.py38def test_helpers_are_not_generators(func: Callable) -> None:CODE
LOWtests/test_import_utils.py48 def test_get_package_info_installed(self) -> None:CODE
LOWtests/test_import_utils.py53 def test_get_package_info_missing(self) -> None:CODE
LOWtests/test_import_utils.py58 def test_passes_when_all_present(self) -> None:CODE
LOWtests/test_import_utils.py61 def test_passes_for_empty_iterable(self) -> None:CODE
LOWtests/test_import_utils.py64 def test_raises_only_for_missing(self) -> None:CODE
LOWtests/test_import_utils.py74def test_ensure_package_minimum_version(CODE
LOWtests/test_import_utils.py94 def test_no_message_for_single_distribution(self, monkeypatch: pytest.MonkeyPatch) -> None:CODE
LOWtests/test_import_utils.py98 def test_no_message_when_versions_agree(self, monkeypatch: pytest.MonkeyPatch) -> None:CODE
LOWtests/test_import_utils.py102 def test_message_suggests_the_newest_version(self, monkeypatch: pytest.MonkeyPatch) -> None:CODE
LOWtests/test_import_utils.py109 def test_newest_version_is_compared_numerically(self, monkeypatch: pytest.MonkeyPatch) -> None:CODE
LOWtests/test_combine.py136 def test_nms_ios_small_inside_large(self) -> None:CODE
LOWtests/test_combine.py323 def test_greedy_nmm_postprocess(self) -> None:CODE
LOWtests/test_combine.py330 def test_nms_postprocess_single(self) -> None:CODE
LOWtests/test_combine.py488 def test_metric_matrix_no_overlap(self) -> None:CODE
LOWtests/test_combine.py114 def test_nms_equal_scores_deterministic(self) -> None:CODE
LOWtests/test_combine.py148 def test_nms_iou_vs_ios_differ(self) -> None:CODE
LOWtests/test_combine.py228 def test_high_threshold_keeps_all(self) -> None:CODE
LOWtests/test_combine.py309 def test_nms_postprocess_class_agnostic_false(self) -> None:CODE
LOWtests/test_combine.py358 def test_invalid_backend_raises(self) -> None:CODE
LOWtests/test_combine.py365 def test_resolve_cache_invalidation(self) -> None:CODE
LOWtests/test_combine.py384 def test_auto_resolves_gpu_to_torchvision(CODE
LOWtests/test_combine.py407 def test_forced_numpy_backend_dispatch(self) -> None:CODE
LOWtests/test_combine.py527 def test_greedy_nmm_merge_order_parity(self) -> None:CODE
LOWtests/test_detectron2_model.py37 def test_perform_inference_without_mask_output(self) -> None:CODE
LOWtests/test_detectron2_model.py70 def test_convert_original_predictions_without_mask_output(self) -> None:CODE
LOWtests/test_detectron2_model.py117 def test_convert_original_predictions_with_mask_output(self) -> None:CODE
LOWtests/test_huggingface_model.py109def test_convert_original_predictions() -> None:CODE
LOWtests/test_huggingface_model.py155def test_get_prediction_huggingface() -> None:CODE
LOWtests/test_huggingface_model.py196def test_get_prediction_automodel_huggingface() -> None:CODE
LOWtests/test_huggingface_model.py242def test_get_sliced_prediction_huggingface() -> None:CODE
LOWtests/test_table.py14 def test_create_ascii_table_basic(self) -> None:CODE
LOWtests/test_huggingface_segmentation.py75def test_convert_original_predictions(model_path: str, segmentation_type: SegmentationType) -> None:CODE
LOWtests/test_huggingface_segmentation.py85def test_get_sliced_prediction(model_path: str, segmentation_type: SegmentationType) -> None:CODE
LOWtests/test_huggingface_segmentation.py113def test_get_prediction_detects_cars() -> None:CODE
LOWtests/test_file_utils.py20 def test_list_files_recursively(self, tmp_path: Path) -> None:CODE
LOWtests/test_torchvision.py37 def test_load_model_without_config_path(self) -> None:CODE
LOWtests/test_torchvision.py63 def test_perform_inference_without_mask_output(self) -> None:CODE
LOWtests/test_torchvision.py114 def test_convert_original_predictions_without_mask_output(self) -> None:CODE
LOWtests/test_torchvision.py149 def test_convert_original_predictions_with_mask_output(self) -> None:CODE
LOWtests/test_torchvision.py182 def test_get_prediction_torchvision(self) -> None:CODE
LOWtests/test_torchvision.py217 def test_get_sliced_prediction_torchvision(self) -> None:CODE
LOWtests/test_mmdetection_model.py48 def test_perform_inference_with_mask_output(self) -> None:CODE
LOWtests/test_mmdetection_model.py96 def test_perform_inference_without_mask_output(self) -> None:CODE
LOWtests/test_mmdetection_model.py137 def test_convert_original_predictions_with_mask_output(self) -> None:CODE
LOWtests/test_mmdetection_model.py175 def test_convert_original_predictions_without_mask_output(self) -> None:CODE
LOWtests/test_mmdetection_model.py222 def test_perform_inference_without_mask_output_with_automodel(self) -> None:CODE
LOWtests/test_predict.py42def test_get_prediction_mmdet() -> None:CODE
LOWtests/test_predict.py136def test_prediction_category_remapping() -> None:CODE
LOWtests/test_predict.py178def test_get_sliced_prediction_mmdet() -> None:CODE
LOWtests/test_predict.py413def test_get_sliced_prediction_batch_size() -> None:CODE
LOWtests/test_predict.py467def test_mmdet_yolox_tiny_prediction() -> None:CODE
LOWtests/test_match_all_threshold.py70def test_matches_all_pairs_boundary() -> None:CODE
LOWtests/test_match_all_threshold.py100def test_collapses_to_single_keeper(funcs: tuple, match_metric: str) -> None:CODE
LOWtests/test_match_all_threshold.py117def test_tied_top_score_matches_dense_path(funcs: tuple, match_metric: str) -> None:CODE
LOWtests/test_match_all_threshold.py151def test_large_input_allocates_no_matrix(funcs: tuple) -> None:CODE
LOWtests/test_rtdet_model.py96 def test_convert_original_predictions(self) -> None:CODE
98 more matches not shown…
Cross-File Repetition28 hits · 140 pts
SeverityFileLineSnippetContext
HIGHtests/data/models/mmdet_retinanet/default_runtime.py0mmdetection configuration file for default_runtime.py.STRING
HIGH…data/models/mmdet_cascade_mask_rcnn/default_runtime.py0mmdetection configuration file for default_runtime.py.STRING
HIGHtests/data/models/mmdet/_base_/default_runtime.py0mmdetection configuration file for default_runtime.py.STRING
HIGHsahi/models/rtdetr.py0detection model is initialized and set to self.model.STRING
HIGHsahi/models/yolo-world.py0detection model is initialized and set to self.model.STRING
HIGHsahi/models/mmdet.py0detection model is initialized and set to self.model.STRING
HIGHsahi/models/ultralytics.py0detection model is initialized and set to self.model.STRING
HIGHsahi/models/yolov5.py0detection model is initialized and set to self.model.STRING
HIGHsahi/models/torchvision.py0sets the underlying yolov5 model. args: model: any a yolov5 model **kwargs: any additional keyword arguments for model sSTRING
HIGHsahi/models/mmdet.py0sets the underlying yolov5 model. args: model: any a yolov5 model **kwargs: any additional keyword arguments for model sSTRING
HIGHsahi/models/ultralytics.py0sets the underlying yolov5 model. args: model: any a yolov5 model **kwargs: any additional keyword arguments for model sSTRING
HIGHsahi/models/yolov5.py0sets the underlying yolov5 model. args: model: any a yolov5 model **kwargs: any additional keyword arguments for model sSTRING
HIGHsahi/models/torchvision.py0returns if model output contains segmentation mask.STRING
HIGHsahi/models/roboflow.py0returns if model output contains segmentation mask.STRING
HIGHsahi/models/ultralytics.py0returns if model output contains segmentation mask.STRING
HIGHsahi/models/yolov5.py0returns if model output contains segmentation mask.STRING
HIGHsahi/models/torchvision.py0convert predictions to objectprediction list. self._original_predictions is converted to a list of prediction.objectpredSTRING
HIGHsahi/models/mmdet.py0convert predictions to objectprediction list. self._original_predictions is converted to a list of prediction.objectpredSTRING
HIGHsahi/models/detectron2.py0convert predictions to objectprediction list. self._original_predictions is converted to a list of prediction.objectpredSTRING
HIGHsahi/models/huggingface.py0convert predictions to objectprediction list. self._original_predictions is converted to a list of prediction.objectpredSTRING
HIGHsahi/models/ultralytics.py0convert predictions to objectprediction list. self._original_predictions is converted to a list of prediction.objectpredSTRING
HIGHsahi/models/yolov5.py0convert predictions to objectprediction list. self._original_predictions is converted to a list of prediction.objectpredSTRING
HIGHsahi/models/roboflow.py0convert predictions to objectprediction list. self._original_predictions is converted to a list of prediction.objectpredSTRING
HIGHsahi/models/mmdet.py0prediction is performed using self.model and the prediction result is set to self._original_predictions. args: image: npSTRING
HIGHsahi/models/detectron2.py0prediction is performed using self.model and the prediction result is set to self._original_predictions. args: image: npSTRING
HIGHsahi/models/huggingface.py0prediction is performed using self.model and the prediction result is set to self._original_predictions. args: image: npSTRING
HIGHsahi/models/ultralytics.py0prediction is performed using self.model and the prediction result is set to self._original_predictions. args: image: npSTRING
HIGHsahi/models/yolov5.py0prediction is performed using self.model and the prediction result is set to self._original_predictions. args: image: npSTRING
Decorative Section Separators39 hits · 126 pts
SeverityFileLineSnippetContext
MEDIUMtests/test_combine.py128# ===========================================================================COMMENT
MEDIUMtests/test_combine.py130# ===========================================================================COMMENT
MEDIUMtests/test_combine.py338# ===========================================================================COMMENT
MEDIUMtests/test_combine.py340# ===========================================================================COMMENT
MEDIUMtests/test_combine.py498# ===========================================================================COMMENT
MEDIUMtests/test_combine.py500# ===========================================================================COMMENT
MEDIUMtests/test_combine.py53# ===========================================================================COMMENT
MEDIUMtests/test_combine.py55# ===========================================================================COMMENT
MEDIUMtests/test_combine.py206# ===========================================================================COMMENT
MEDIUMtests/test_combine.py208# ===========================================================================COMMENT
MEDIUMtests/test_combine.py270# ===========================================================================COMMENT
MEDIUMtests/test_combine.py272# ===========================================================================COMMENT
MEDIUMtests/test_combine.py432# ===========================================================================COMMENT
MEDIUMtests/test_combine.py434# ===========================================================================COMMENT
MEDIUMtests/test_combine.py588# ===========================================================================COMMENT
MEDIUMtests/test_combine.py590# ===========================================================================COMMENT
MEDIUMscripts/detect_batch.py85 # ── load model ────────────────────────────────────────────COMMENT
MEDIUMscripts/detect_batch.py107 # ── single-image detection + save ─────────────────────────COMMENT
MEDIUMscripts/detect_batch.py127 # ── batch detection + save ────────────────────────────────COMMENT
MEDIUMscripts/detect_batch.py145 # ── speed benchmark ───────────────────────────────────────COMMENT
MEDIUMscripts/detect_batch.py178 # ── consistency ────────────────────────────────────────────COMMENT
MEDIUMsahi/postprocess/combine.py16# ---------------------------------------------------------------------------COMMENT
MEDIUMsahi/postprocess/combine.py18# ---------------------------------------------------------------------------COMMENT
MEDIUMsahi/postprocess/combine.py64# ---------------------------------------------------------------------------COMMENT
MEDIUMsahi/postprocess/combine.py66# ---------------------------------------------------------------------------COMMENT
MEDIUMsahi/postprocess/combine.py128# ---------------------------------------------------------------------------COMMENT
MEDIUMsahi/postprocess/combine.py130# ---------------------------------------------------------------------------COMMENT
MEDIUMsahi/postprocess/combine.py258# ---------------------------------------------------------------------------COMMENT
MEDIUMsahi/postprocess/combine.py260# ---------------------------------------------------------------------------COMMENT
MEDIUMsahi/postprocess/_numpy_backend.py28# ---------------------------------------------------------------------------COMMENT
MEDIUMsahi/postprocess/_numpy_backend.py30# ---------------------------------------------------------------------------COMMENT
MEDIUMsahi/postprocess/_numpy_backend.py219# ---------------------------------------------------------------------------COMMENT
MEDIUMsahi/postprocess/_numpy_backend.py221# ---------------------------------------------------------------------------COMMENT
MEDIUMsahi/postprocess/_numpy_backend.py369# ---------------------------------------------------------------------------COMMENT
MEDIUMsahi/postprocess/_numpy_backend.py371# ---------------------------------------------------------------------------COMMENT
MEDIUMsahi/postprocess/_torchvision_backend.py69# ---------------------------------------------------------------------------COMMENT
MEDIUMsahi/postprocess/_torchvision_backend.py71# ---------------------------------------------------------------------------COMMENT
MEDIUMsahi/postprocess/_numba_backend.py218# ---------------------------------------------------------------------------COMMENT
MEDIUMsahi/postprocess/_numba_backend.py220# ---------------------------------------------------------------------------COMMENT
Unused Imports71 hits · 70 pts
SeverityFileLineSnippetContext
LOWtests/test_import_utils.py1CODE
LOWtests/test_combine.py3CODE
LOWtests/test_postprocess_utils.py3CODE
LOWtests/test_detectron2_model.py3CODE
LOWtests/test_huggingface_model.py3CODE
LOWtests/test_table.py3CODE
LOWtests/test_huggingface_segmentation.py8CODE
LOWtests/test_high_level_api.py3CODE
LOWtests/test_prediction.py3CODE
LOWtests/test_file_utils.py3CODE
LOWtests/test_torchvision.py3CODE
LOWtests/test_mmdetection_model.py3CODE
LOWtests/test_predict.py3CODE
LOWtests/test_match_all_threshold.py9CODE
LOWtests/test_rtdet_model.py3CODE
LOWtests/test_torch_utils.py3CODE
LOWtests/test_shapely_utils.py3CODE
LOWtests/test_annotation.py3CODE
LOWtests/test_sparse_backend.py3CODE
LOWtests/test_ultralytics_model.py3CODE
LOWtests/test_cv_utils.py3CODE
LOWtests/test_huggingface_groundingdino_model.py3CODE
LOWtests/test_roboflow.py3CODE
LOWtests/utils/ultralytics.py3CODE
LOWscripts/detect_batch.py11CODE
LOWsahi/annotation.py6CODE
LOWsahi/auto_model.py3CODE
LOWsahi/__init__.py6CODE
LOWsahi/__init__.py12CODE
LOWsahi/__init__.py13CODE
LOWsahi/__init__.py14CODE
LOWsahi/__init__.py15CODE
LOWsahi/__init__.py16CODE
LOWsahi/__init__.py17CODE
LOWsahi/logger.py3CODE
LOWsahi/prediction.py3CODE
LOWsahi/utils/rtdetr.py3CODE
LOWsahi/utils/compatibility.py3CODE
LOWsahi/utils/file.py3CODE
LOWsahi/utils/mmdet.py3CODE
LOWsahi/utils/cv.py3CODE
LOWsahi/utils/table.py3CODE
LOWsahi/utils/shapely.py3CODE
LOWsahi/utils/import_utils.py3CODE
LOWsahi/utils/yolov5.py3CODE
LOWsahi/utils/torch_utils.py3CODE
LOWsahi/models/rtdetr.py6CODE
LOWsahi/models/torchvision.py7CODE
LOWsahi/models/yolo-world.py6CODE
LOWsahi/models/yoloe.py7CODE
LOWsahi/models/mmdet.py7CODE
LOWsahi/models/detectron2.py7CODE
LOWsahi/models/huggingface.py7CODE
LOWsahi/models/roboflow.py7CODE
LOWsahi/models/huggingface_segmentation.py7CODE
LOWsahi/models/ultralytics.py7CODE
LOWsahi/models/yolov5.py6CODE
LOWsahi/models/base.py7CODE
LOWsahi/scripts/coco_error_analysis.py3CODE
LOWsahi/scripts/coco_evaluation.py3CODE
11 more matches not shown…
Deep Nesting35 hits · 32 pts
SeverityFileLineSnippetContext
LOWtests/test_huggingface_model.py155CODE
LOWtests/test_huggingface_model.py196CODE
LOWtests/test_huggingface_model.py242CODE
LOWsahi/predict.py176CODE
LOWsahi/predict.py496CODE
LOWsahi/slicing.py278CODE
LOWsahi/utils/coco.py1852CODE
LOWsahi/utils/coco.py1937CODE
LOWsahi/utils/coco.py2012CODE
LOWsahi/utils/coco.py859CODE
LOWsahi/utils/coco.py961CODE
LOWsahi/utils/coco.py1010CODE
LOWsahi/utils/coco.py1410CODE
LOWsahi/utils/coco.py1477CODE
LOWsahi/utils/coco.py1521CODE
LOWsahi/utils/coco.py2188CODE
LOWsahi/utils/coco.py2244CODE
LOWsahi/utils/mmdet.py69CODE
LOWsahi/utils/cv.py203CODE
LOWsahi/utils/cv.py517CODE
LOWsahi/utils/torch_utils.py73CODE
LOWsahi/models/mmdet.py221CODE
LOWsahi/models/roboflow.py119CODE
LOWsahi/models/roboflow.py201CODE
LOWsahi/models/ultralytics.py223CODE
LOWsahi/scripts/coco_error_analysis.py49CODE
LOWsahi/scripts/coco_error_analysis.py168CODE
LOWsahi/scripts/coco_error_analysis.py312CODE
LOWsahi/scripts/coco_evaluation.py72CODE
LOWsahi/postprocess/_sparse_backend.py373CODE
LOWsahi/postprocess/_sparse_backend.py432CODE
LOWsahi/postprocess/utils.py137CODE
LOWsahi/postprocess/utils.py164CODE
LOWsahi/postprocess/utils.py61CODE
LOWsahi/postprocess/_numpy_backend.py288CODE
Over-Commented Block24 hits · 24 pts
SeverityFileLineSnippetContext
LOWtests/check_dependencies.sh1#!/bin/bashCOMMENT
LOWtests/data/models/mmdet/_base_/datasets/wider_face.py1"""MMDetection configuration file for wider_face.py."""COMMENT
LOW…models/mmdet/_base_/datasets/objects365v2_detection.py1"""MMDetection configuration file for objects365v2_detection.py."""COMMENT
LOW…ta/models/mmdet/_base_/datasets/cityscapes_instance.py1"""MMDetection configuration file for cityscapes_instance.py."""COMMENT
LOW…ta/models/mmdet/_base_/datasets/cityscapes_instance.py101# persistent_workers=True,COMMENT
LOW…ts/data/models/mmdet/_base_/datasets/coco_detection.py1"""MMDetection configuration file for coco_detection.py."""COMMENT
LOW…ts/data/models/mmdet/_base_/datasets/coco_detection.py81# test_dataloader = dict(COMMENT
LOW…ata/models/mmdet/_base_/datasets/lvis_v0.5_instance.py1"""MMDetection configuration file for lvis_v0.5_instance.py."""COMMENT
LOW…a/models/mmdet/_base_/datasets/openimages_detection.py1"""MMDetection configuration file for openimages_detection.py."""COMMENT
LOW…a/models/mmdet/_base_/datasets/cityscapes_detection.py1"""MMDetection configuration file for cityscapes_detection.py."""COMMENT
LOW…ta/models/mmdet/_base_/datasets/semi_coco_detection.py1"""MMDetection configuration file for semi_coco_detection.py."""COMMENT
LOW…ta/models/mmdet/_base_/datasets/semi_coco_detection.py121 dict(type="PackDetInputs", meta_keys=("img_id", "img_path", "ori_shape", "img_shape", "scale_factor")),COMMENT
LOW…sts/data/models/mmdet/_base_/datasets/coco_instance.py1"""MMDetection configuration file for coco_instance.py."""COMMENT
LOW…sts/data/models/mmdet/_base_/datasets/coco_instance.py81# test_dataloader = dict(COMMENT
LOW…sts/data/models/mmdet/_base_/datasets/coco_panoptic.py1"""MMDetection configuration file for coco_panoptic.py."""COMMENT
LOW…sts/data/models/mmdet/_base_/datasets/coco_panoptic.py81# batch_size=1,COMMENT
LOW…models/mmdet/_base_/datasets/coco_instance_semantic.py1"""MMDetection configuration file for coco_instance_semantic.py."""COMMENT
LOW…models/mmdet/_base_/datasets/objects365v1_detection.py1"""MMDetection configuration file for objects365v1_detection.py."""COMMENT
LOWtests/data/models/mmdet/_base_/datasets/voc0712.py1"""MMDetection configuration file for voc0712.py."""COMMENT
LOWtests/data/models/mmdet/_base_/datasets/deepfashion.py1"""MMDetection configuration file for deepfashion.py."""COMMENT
LOWtests/data/models/mmdet/yolox/yolox_s_8xb8-300e_coco.py61# Method 1: simply set the data root and let the file I/O moduleCOMMENT
LOWdocs/coco.md261COMMENT
LOWdocs/zh/coco.md261## 数据集统计COMMENT
LOWdocs/tr/coco.md261## Veri Kümesi İstatistikleriCOMMENT
AI Slop Vocabulary15 hits · 22 pts
SeverityFileLineSnippetContext
LOWtests/data/models/mmdet/_base_/datasets/wider_face.py7# Method 1: simply set the data root and let the file I/O moduleCOMMENT
LOW…models/mmdet/_base_/datasets/objects365v2_detection.py8# Method 1: simply set the data root and let the file I/O moduleCOMMENT
LOW…ta/models/mmdet/_base_/datasets/cityscapes_instance.py8# Method 1: simply set the data root and let the file I/O moduleCOMMENT
LOW…ts/data/models/mmdet/_base_/datasets/coco_detection.py8# Method 1: simply set the data root and let the file I/O moduleCOMMENT
LOW…ata/models/mmdet/_base_/datasets/lvis_v0.5_instance.py8# Method 1: simply set the data root and let the file I/O moduleCOMMENT
LOW…a/models/mmdet/_base_/datasets/openimages_detection.py8# Method 1: simply set the data root and let the file I/O moduleCOMMENT
LOW…a/models/mmdet/_base_/datasets/cityscapes_detection.py8# Method 1: simply set the data root and let the file I/O moduleCOMMENT
LOW…ta/models/mmdet/_base_/datasets/semi_coco_detection.py8# Method 1: simply set the data root and let the file I/O moduleCOMMENT
LOW…sts/data/models/mmdet/_base_/datasets/coco_instance.py8# Method 1: simply set the data root and let the file I/O moduleCOMMENT
LOW…sts/data/models/mmdet/_base_/datasets/coco_panoptic.py8# Method 1: simply set the data root and let the file I/O moduleCOMMENT
LOW…models/mmdet/_base_/datasets/coco_instance_semantic.py8# Method 1: simply set the data root and let the file I/O moduleCOMMENT
LOW…models/mmdet/_base_/datasets/objects365v1_detection.py8# Method 1: simply set the data root and let the file I/O moduleCOMMENT
LOWtests/data/models/mmdet/_base_/datasets/voc0712.py8# Method 1: simply set the data root and let the file I/O moduleCOMMENT
LOWtests/data/models/mmdet/_base_/datasets/deepfashion.py8# Method 1: simply set the data root and let the file I/O moduleCOMMENT
LOWtests/data/models/mmdet/yolox/yolox_s_8xb8-300e_coco.py61# Method 1: simply set the data root and let the file I/O moduleCOMMENT
Magic Placeholder Names3 hits · 15 pts
SeverityFileLineSnippetContext
HIGHdocs/zh/guides/models.md395 api_key="YOUR_API_KEY", # 也可以设置 ROBOFLOW_API_KEYCODE
HIGHdocs/guides/models.md402 api_key="YOUR_API_KEY", # or set ROBOFLOW_API_KEYCODE
HIGHdocs/tr/guides/models.md381 api_key="YOUR_API_KEY", # or set ROBOFLOW_API_KEYCODE
Docstring Block Structure3 hits · 15 pts
SeverityFileLineSnippetContext
HIGHsahi/auto_model.py44Load a DetectionModel from given path. Args: model_type: str Name of the detection STRING
HIGHsahi/postprocess/combine.py438Apply Locality-Sensitive NMS to suppress overlapping predictions. Args: object_predictions: List ofSTRING
HIGHsahi/postprocess/utils.py339Check whether two predictions overlap above the given threshold. Args: pred1: First object prediction. STRING
Modern Structural Boilerplate15 hits · 15 pts
SeverityFileLineSnippetContext
LOWsahi/__init__.py59__all__ = [CODE
LOWsahi/logger.py98__all__ = ["PKG_INFO_LEVEL", "BaseSahiLogger", "SahiLogger", "SupportsPkgInfo", "logger"]CODE
LOWsahi/utils/coco.py899 def update_categories(self, desired_name2id: dict[str, int], update_image_filenames: bool = False) -> None:CODE
LOWsahi/utils/coco.py1786def update_categories_from_file(desired_name2id: dict, coco_path: str, save_path: str) -> None:CODE
LOWsahi/models/torchvision.py77 def set_model(self, model: Any, **kwargs: Any) -> None:CODE
LOWsahi/models/mmdet.py138 def set_model(self, model: Any, **kwargs: Any) -> None:CODE
LOWsahi/models/huggingface.py117 def set_model(self, model: Any, processor: Any | None = None, **kwargs: Any) -> None:CODE
LOWsahi/models/roboflow.py109 def set_model(self, model: Any, **kwargs: Any) -> None:CODE
LOWsahi/models/huggingface_segmentation.py90 def set_model(self, model: Any, processor: Any = None, **kwargs: Any) -> None:CODE
LOWsahi/models/ultralytics.py70 def set_model(self, model: Any, **kwargs: Any) -> None:CODE
LOWsahi/models/yolov5.py41 def set_model(self, model: Any, **kwargs: Any) -> None:CODE
LOWsahi/models/base.py110 def set_model(self, model: Any, **kwargs: Any) -> None:CODE
LOWsahi/models/base.py124 def set_device(self, device: str | None = None) -> None:CODE
LOWsahi/postprocess/__init__.py5__all__ = ["get_postprocess_backend", "set_postprocess_backend"]CODE
LOWsahi/postprocess/backends.py20def set_postprocess_backend(name: str) -> None:CODE
Excessive Try-Catch Wrapping12 hits · 12 pts
SeverityFileLineSnippetContext
LOWscripts/detect_batch.py95 except Exception as e:CODE
LOWsahi/utils/cv.py21except Exception:CODE
LOWsahi/utils/cv.py153 except Exception as e:CODE
LOWsahi/utils/cv.py238 except Exception as e: # handle large/tiff image readingCODE
LOWsahi/models/rtdetr.py26 except Exception as e:CODE
LOWsahi/models/torchvision.py71 except Exception as e:CODE
LOWsahi/models/yolo-world.py26 except Exception as e:CODE
LOWsahi/models/yoloe.py118 except Exception as e:CODE
LOWsahi/models/detectron2.py48 except Exception as e: # try to load from localCODE
LOWsahi/models/detectron2.py75 except Exception as e:CODE
LOWsahi/models/ultralytics.py67 except Exception as e:CODE
LOWsahi/models/yolov5.py38 except Exception as e:CODE
AI Structural Patterns12 hits · 12 pts
SeverityFileLineSnippetContext
LOWsahi/auto_model.py30CODE
LOWsahi/predict.py176CODE
LOWsahi/predict.py496CODE
LOWsahi/predict.py913CODE
LOWsahi/slicing.py278CODE
LOWsahi/slicing.py435CODE
LOWsahi/utils/cv.py404CODE
LOWsahi/utils/cv.py517CODE
LOWsahi/models/mmdet.py97CODE
LOWsahi/models/huggingface.py26CODE
LOWsahi/models/roboflow.py40CODE
LOWsahi/models/base.py31CODE
Hallucination Indicators1 hit · 10 pts
SeverityFileLineSnippetContext
CRITICALsahi/models/roboflow.py128 from inference.core.exceptions import RoboflowAPINotAuthorizedErrorCODE
Redundant / Tautological Comments4 hits · 6 pts
SeverityFileLineSnippetContext
LOWtests/check_dependencies.sh52 # Check if the command runs without errorsCOMMENT
LOWtests/check_dependencies.sh62# Display the resultsCOMMENT
LOWsahi/models/ultralytics.py196 # Check if model has 'task' attribute (for both .pt and .onnx models)COMMENT
LOWsahi/models/ultralytics.py211 # Check if model has 'task' attribute (for both .pt and .onnx models)COMMENT
Modern AI Meta-Vocabulary2 hits · 4 pts
SeverityFileLineSnippetContext
MEDIUMdocs/guides/models.md195In addition to the [common parameters](#common-parameters), zero-shotCODE
MEDIUMdocs/tr/guides/models.md184[Ortak parametrelere](#ortak-parametreler) ek olarak zero-shot (GroundingDINO) modelleri şunları kabul eder:CODE