Home / ultralytics / yolov3
AI Slop Code RIsk Monitor

ultralytics/yolov3

PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and multi-format export.

21.2 Elevated pattern signal View on GitHub

Maintenance and Governance Review

This report summarizes scanner evidence for ultralytics/yolov3, a Python project with 10,616 GitHub stars. SynthScan examined 14,202 lines of code across 76 source files, recording 159 pattern matches distributed across 15 syntactic categories. The legacy adjusted pattern signal is 21.2 (Elevated pattern signal); it is not an authorship estimate.

Use the findings to ask whether maintainers can explain intent, verify dependencies, simplify unnecessary scaffolding, and focus review effort. Risk Payload v1 adds ownership, supply-chain, over-engineering, and review-effort vectors when available. These are prompts for human verification, not probabilities, security findings, or measured maintenance costs.

21.2
Adjusted Signal
21.2
Raw Pattern Score
100%
Time Factor
2026-10-09
Last Push
10.6K
Stars
Python
Language
14.2K
Lines of Code
76
Files
159
Pattern Hits
2026-10-12
Scan Date
0.42
HC Hit Rate

Risk Review · v3

Use each vector to guide manual verification of the underlying findings.

Cognitive Ownership Risk 53.0/100 · HIGH

Can maintainers explain intent, assumptions, and trade-offs? 93 finding(s).

Hallucinated Dependency & Supply Chain Risk 12.5/100 · LOW

Are imports declared and package/API names verified? 25 finding(s).

Agent Over-Engineering Ratio 19.6/100 · LOW

Are wrappers, guards, and repeated structures necessary? 55 finding(s).

PR Review Velocity Impact 68.4/100 · HIGH

Which changes need focused human review? 159 finding(s).

What These Metrics Mean

Adjusted Signal
Legacy pattern score normalized per 1,000 scanned lines and multiplied by the repository-level time factor. It is not an estimate of AI authorship.
Raw Pattern Score
Sum of severity- and context-weighted pattern findings before applying the time factor.
Time Factor
A coarse multiplier based on repository last-push metadata. It does not identify when individual code was written.
Pattern Hits
Count of configured pattern findings. Review each location and surrounding code before acting.
HC Hit Rate
High- and critical-severity findings per scanned file. Severity is a configured detector weight, not proof of a vulnerability or authorship.
Lines / Files
Scan coverage denominators used by the legacy normalized score.

Pattern-Signal History

This chart tracks the legacy adjusted pattern score across scan runs. Changes can reflect source changes, scan coverage, or detector/scoring versions; they do not measure AI adoption or prove that a team refactored code. Compare runs only when their scoring versions are compatible. The dashed line tracks the raw pattern-hit count.

Severity Breakdown

Groups findings by configured severity weight. Severity is not a confidence estimate, security rating, or proof that a package is missing. Verify imports against the project's manifests and inspect each finding in its local design context.

CRITICAL 1HIGH 31MEDIUM 2LOW 125

Directory Score Breakdown

This horizontal bar chart shows where configured pattern scores accumulate across directories. Treat the bars as locations to inspect, not as evidence of authorship or code quality. Use the file-level findings to decide whether a directory needs a focused ownership, dependency, complexity, or review check.

Pattern Findings

The scanner identified 159 distinct pattern matches across 15 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. 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 configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.

Docstring Block Structure29 hits · 145 pts
SeverityFileLineSnippetContext
HIGHval.py65Saves detection results in a text format, including labels and optionally confidence scores. Args: predn (tSTRING
HIGHval.py107Save detection results in JSON format containing image_id, category_id, bbox, and score per detection. Args: STRING
HIGHval.py148Computes correct prediction matrix for detections against ground truth labels at various IoU thresholds. Args: STRING
HIGHval.py222Validate a trained YOLOv3 detection model on a dataset and optionally save results in the requested formats. Args: STRING
HIGHval.py493Parses and returns command-line options for dataset paths, model parameters, and inference settings. Args: STRING
HIGHval.py566Executes model tasks including training, validation, and speed or study benchmarks based on specified options. ArgsSTRING
HIGHexport.py166Export a YOLOv3 model to TorchScript format, with optional optimization for mobile deployment. Args: model STRING
HIGHexport.py198Export a YOLOv3 model to ONNX format with dynamic shape and simplification options. Args: model (torch.nn.MSTRING
HIGHexport.py269Export a YOLOv3 model to OpenVINO format with optional INT8 quantization and inference metadata. Args: fileSTRING
HIGHexport.py350Export a YOLOv3 model to PaddlePaddle format using X2Paddle, writing model files and a metadata YAML. Args: STRING
HIGHexport.py381Export a YOLOv3 model to CoreML format with optional quantization and Non-Maximum Suppression (NMS). Args: STRING
HIGHexport.py426Export a YOLOv3 model to TensorRT engine format, optimizing it for GPU inference. Args: model (torch.nn.ModSTRING
HIGHexport.py675Export a YOLOv3 PyTorch model to one or more deployment formats (TorchScript, ONNX, CoreML, TensorRT, etc.). Args: STRING
HIGHtrain.py106Train a YOLOv3 model on a custom dataset and manage the training process. Args: hyp (str | dict): Path to hSTRING
HIGHtrain.py534Parse command line arguments for configuring the training of a YOLOv3 model. Args: known (bool): Flag to paSTRING
HIGHtrain.py602Main training/evolution script handling model checks, DDP setup, training, and hyperparameter evolution. Args: STRING
HIGHtrain.py802Run the training process for a YOLOv3 model with the specified configurations. Args: data (str): Path to thSTRING
HIGHhubconf.py17Creates or loads a YOLOv3 model with specified configurations and optional pretrained weights. Args: name (STRING
HIGHhubconf.py90Loads a custom or local YOLOv3 model from a specified path, with options for autoshaping and device assignment. ArgSTRING
HIGHhubconf.py119Instantiates the YOLOv3 model with optional pretrained weights, configurable input channels, classes, autoshaping, aSTRING
HIGHhubconf.py148Instantiates the YOLOv3-SPP model with optional pretrained weights, configurable input channels, classes, autoshapinSTRING
HIGHhubconf.py174Instantiates the YOLOv3-tiny model with optional pretrained weights, configurable input channels, classes, autoshapiSTRING
HIGHdetect.py97Run YOLOv3 detection inference on various input sources such as images, videos, and streams. Args: weights STRING
HIGHdetect.py290Parses and returns command-line options for running YOLOv3 model detection. Args: --weights (list[str]): MoSTRING
HIGHdetect.py367Entry point for running the YOLOv3 model; checks requirements and calls `run` with parsed options. Args: opSTRING
HIGHbenchmarks.py55Run YOLOv3 benchmarks on multiple export formats and validate performance metrics. Args: weights (str | PatSTRING
HIGHbenchmarks.py172Parses command line arguments for YOLOv3 inference and export configurations. Args: --weights (str): Path tSTRING
HIGHbenchmarks.py217Executes the export and benchmarking pipeline for YOLOv3 models, testing multiple export formats and validating perfSTRING
HIGHutils/autoanchor.py68Create k-means evolved anchors from a training dataset. Args: dataset (str | LoadImagesAndLabels): Path to STRING
Excessive Try-Catch Wrapping36 hits · 38 pts
SeverityFileLineSnippetContext
LOWval.py478 except Exception as e:CODE
LOWexport.py157 except Exception as e:CODE
LOWexport.py262 except Exception as e:CODE
LOWexport.py453 except Exception:CODE
LOWhubconf.py66 except Exception:CODE
LOWhubconf.py80 except Exception as e:CODE
LOWbenchmarks.py100 except Exception as e:CODE
LOWbenchmarks.py160 except Exception:CODE
LOWutils/autobatch.py64 except Exception as e:CODE
LOWutils/dataloaders.py484 except Exception as e:CODE
LOWutils/dataloaders.py494 except Exception:CODE
LOWutils/dataloaders.py645 except Exception as e:CODE
LOWutils/dataloaders.py909 except Exception as e:CODE
LOWutils/downloads.py20 except Exception:CODE
LOWutils/downloads.py67 except Exception as e: # url2CODE
LOW⚡utils/downloads.py110 except Exception:CODE
LOW⚡utils/downloads.py113 except Exception:CODE
LOW⚡utils/downloads.py116 except Exception:CODE
LOWutils/plots.py290 except Exception as e:CODE
LOWutils/autoanchor.py143 except Exception:CODE
LOWutils/torch_utils.py149 except Exception:CODE
LOWutils/torch_utils.py160 except Exception: # no backward methodCODE
LOWutils/torch_utils.py170 except Exception as e:CODE
LOWutils/general.py228 except Exception:CODE
LOWutils/general.py305 except Exception as e:CODE
LOWutils/general.py452 except Exception:CODE
LOWutils/general.py890 except Exception:CODE
LOWutils/augmentations.py46 except Exception as e:CODE
LOWutils/loggers/__init__.py113 except Exception:CODE
LOWutils/loggers/__init__.py412 except Exception as e:CODE
LOWutils/loggers/comet/comet_utils.py65 except Exception:CODE
LOWmodels/yolo.py411 except Exception as e:CODE
LOW.github/workflows/merge-main-into-prs.yml71 except Exception as update_error:CODE
LOW.github/workflows/merge-main-into-prs.yml77 except Exception as e:CODE
LOWdata/Objects365.yaml438 except Exception as e:CODE
LOWdata/xView.yaml133 except Exception as e:CODE
Unused Imports23 hits · 23 pts
SeverityFileLineSnippetContext
LOWutils/triton.py4CODE
LOWutils/__init__.py6CODE
LOWutils/__init__.py6CODE
LOWutils/__init__.py6CODE
LOWutils/torch_utils.py13CODE
LOWutils/torch_utils.py13CODE
LOWutils/torch_utils.py13CODE
LOWutils/torch_utils.py13CODE
LOWutils/torch_utils.py13CODE
LOWutils/torch_utils.py13CODE
LOWutils/general.py4CODE
LOWutils/general.py32CODE
LOWutils/general.py33CODE
LOWutils/general.py33CODE
LOWutils/general.py41CODE
LOWutils/general.py42CODE
LOWutils/general.py42CODE
LOWutils/general.py42CODE
LOWutils/general.py45CODE
LOWutils/general.py45CODE
LOWutils/general.py45CODE
LOWutils/general.py55CODE
LOWutils/general.py55CODE
Deep Nesting23 hits · 22 pts
SeverityFileLineSnippetContext
LOWval.py192CODE
LOWval.py565CODE
LOWtrain.py105CODE
LOWtrain.py601CODE
LOWhubconf.py16CODE
LOWdetect.py68CODE
LOWutils/dataloaders.py864CODE
LOWutils/dataloaders.py229CODE
LOWutils/dataloaders.py438CODE
LOWutils/dataloaders.py764CODE
LOWutils/downloads.py82CODE
LOWutils/plots.py82CODE
LOWutils/torch_utils.py123CODE
LOWutils/torch_utils.py207CODE
LOWutils/general.py327CODE
LOWutils/general.py369CODE
LOWutils/general.py490CODE
LOWutils/general.py493CODE
LOWmodels/common.py435CODE
LOWmodels/common.py647CODE
LOWmodels/common.py812CODE
LOWmodels/common.py904CODE
LOWmodels/yolo.py298CODE
Redundant / Tautological Comments10 hits · 15 pts
SeverityFileLineSnippetContext
LOWval.py431 # Print resultsCOMMENT
LOWval.py437 # Print results per classCOMMENT
LOWdetect.py225 # Print resultsCOMMENT
LOWdetect.py277 # Print resultsCOMMENT
LOWbenchmarks.py108 # Print resultsCOMMENT
LOWbenchmarks.py163 # Print resultsCOMMENT
LOWutils/loggers/comet/__init__.py161 # Check if running the Experiment with the Comet OptimizerCOMMENT
LOWutils/loggers/comet/__init__.py456 # Check if running Experiment with Comet OptimizerCOMMENT
LOWutils/loggers/clearml/clearml_utils.py118 # Set data to data_dict because wandb will crash without this information and opt is the best wayCOMMENT
LOW.github/workflows/merge-main-into-prs.yml59 # Check if PR is behind the default branchCOMMENT
Over-Commented Block14 hits · 14 pts
SeverityFileLineSnippetContext
LOWrequirements.txt21# tensorboard>=2.4.1 # Visual logging (scalars, images)COMMENT
LOWrequirements.txt41COMMENT
LOWpyproject.toml1# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/licenseCOMMENT
LOWmodels/common.py441 fp16=False,COMMENT
LOWdata/coco128.yaml1# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/licenseCOMMENT
LOWdata/coco.yaml1# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/licenseCOMMENT
LOWdata/GlobalWheat2020.yaml1# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/licenseCOMMENT
LOWdata/VisDrone.yaml1# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/licenseCOMMENT
LOWdata/SKU-110K.yaml1# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/licenseCOMMENT
LOWdata/Objects365.yaml1# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/licenseCOMMENT
LOWdata/xView.yaml1# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/licenseCOMMENT
LOWdata/Argoverse.yaml1# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/licenseCOMMENT
LOWdata/VOC.yaml1# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/licenseCOMMENT
LOWdata/hyps/hyp.VOC.yaml1# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/licenseCOMMENT
Hallucination Indicators1 hit · 10 pts
SeverityFileLineSnippetContext
CRITICALexport.py634 pipeline.spec.description.metadata.userDefined.update(CODE
AI Structural Patterns9 hits · 8 pts
SeverityFileLineSnippetContext
LOWval.py192CODE
LOWexport.py657CODE
LOWdetect.py68CODE
LOWbenchmarks.py44CODE
LOWbenchmarks.py121CODE
LOWutils/dataloaders.py73CODE
LOWutils/dataloaders.py438CODE
LOWutils/general.py630CODE
LOWutils/augmentations.py137CODE
Hyper-Verbose Identifiers5 hits · 5 pts
SeverityFileLineSnippetContext
LOWutils/triton.py42 def create_input_placeholders() -> list[InferInput]:CODE
LOWutils/torch_utils.py76def torch_distributed_zero_first(local_rank: int):CODE
LOWutils/loggers/__init__.py154 def on_pretrain_routine_start(self):CODE
LOWutils/loggers/comet/__init__.py367 def download_dataset_artifact(self, artifact_path):CODE
LOWutils/loggers/comet/comet_utils.py22def download_model_checkpoint(opt, experiment):CODE
Empty Error Handlers1 hit · 5 pts
SeverityFileLineSnippetContext
HIGHutils/augmentations.py44except ImportError: # package not installed, skipCODE
Magic Placeholder Names1 hit · 5 pts
SeverityFileLineSnippetContext
HIGHutils/loggers/comet/README.md45 api_key=YOUR_API_KEYCODE
AI Slop Vocabulary1 hit · 3 pts
SeverityFileLineSnippetContext
MEDIUMpyproject.toml14# For comprehensive documentation and usage instructions, visit: https://docs.ultralytics.com/models/yolov3COMMENT
Decorative Section Separators1 hit · 3 pts
SeverityFileLineSnippetContext
MEDIUMutils/general.py868# ------------------------------------------------------------------------------------COMMENT
Modern Structural Boilerplate3 hits · 3 pts
SeverityFileLineSnippetContext
LOWutils/loggers/comet/__init__.py10logger = logging.getLogger(__name__)CODE
LOWutils/loggers/comet/comet_utils.py15logger = logging.getLogger(__name__)CODE
LOWutils/loggers/comet/hpo.py13logger = logging.getLogger(__name__)CODE
Example Usage Blocks2 hits · 2 pts
SeverityFileLineSnippetContext
LOWtrain.py123 # Example usageSTRING
LOWutils/autobatch.py32 # Usage:COMMENT