# ibaigorordo/onnx-imagenet-1k-object-detector architecture

> Architecture diagram of the GitHub repository ibaigorordo/onnx-imagenet-1k-object-detector, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-07). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/ibaigorordo/onnx-imagenet-1k-object-detector
- Repository: https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector

## Overview

The product detects class-agnostic object boxes, classifies each crop into ImageNet-1K labels, and displays annotated results for images, videos, or webcam frames. The central pipeline is implemented in `detector1K/detector1K.py`; the README documents automatic model downloads. Relationships below are grounded in the sampled source and README; model runtime internals are not expanded.

Main entry points: [`detector1K/detector1K.py`](https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/blob/main/detector1K/detector1K.py) (Detection pipeline), [`image_object_detection.py`](https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/blob/main/image_object_detection.py) (Image script), [`video_object_detection.py`](https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/blob/main/video_object_detection.py) (Video script), [`webcam_object_detection.py`](https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/blob/main/webcam_object_detection.py) (Webcam script)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_inputs["Input workflows"]
  node_image["Image script"]
  node_video["Video script"]
  node_webcam["Webcam script"]
end

subgraph group_pipeline["Detection pipeline"]
  node_detector["Detection pipeline<br/>[detector1K.py]"]
  node_classifier["ResNet classifier"]
  node_utils["Download helpers<br/>[utils.py]"]
end

subgraph group_assets["Models and labels"]
  node_labelmap["ImageNet labels"]
  node_models["ONNX model files"]
end

node_user(("User media"))
node_google(("Google Drive"))
node_results(("Annotated display"))

node_user -->|"supplies image"| node_image
node_user -->|"supplies video"| node_video
node_user -->|"supplies frames"| node_webcam
node_image -->|"calls detector"| node_detector
node_video -->|"calls detector"| node_detector
node_webcam -->|"calls detector"| node_detector
node_detector -->|"classifies crops"| node_classifier
node_classifier -->|"reads labels"| node_labelmap
node_detector -->|"downloads localizer"| node_utils
node_classifier -->|"downloads classifier"| node_utils
node_utils -->|"downloads models"| node_google
node_utils -->|"writes model files"| node_models
node_image -->|"renders detections"| node_detector
node_video -->|"renders frames"| node_detector
node_webcam -->|"renders frames"| node_detector
node_image -->|"shows image"| node_results
node_video -->|"shows frames"| node_results
node_webcam -->|"shows frames"| node_results

click node_image "https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/blob/main/image_object_detection.py"
click node_video "https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/blob/main/video_object_detection.py"
click node_webcam "https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/blob/main/webcam_object_detection.py"
click node_detector "https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/blob/main/detector1K/detector1K.py"
click node_classifier "https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/blob/main/detector1K/resnet50Classifier.py"
click node_utils "https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/blob/main/detector1K/utils.py"
click node_labelmap "https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/blob/main/detector1K/imagenet1000_clsid_to_human.pkl"
click node_models "https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/tree/main/models"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_image,node_video,node_webcam,node_user toneBlue
class node_detector,node_classifier,node_utils toneAmber
class node_labelmap,node_models toneMint
class node_google,node_results toneIndigo
```

## Components

### Input workflows

- [Image script](https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/blob/main/image_object_detection.py): `image_object_detection.py`
- [Video script](https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/blob/main/video_object_detection.py): `video_object_detection.py`
- [Webcam script](https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/blob/main/webcam_object_detection.py): `webcam_object_detection.py`

### Detection pipeline

- [Detection pipeline](https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/blob/main/detector1K/detector1K.py): `detector1K/detector1K.py`
- [ResNet classifier](https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/blob/main/detector1K/resnet50Classifier.py): `detector1K/resnet50Classifier.py`
- [Download helpers](https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/blob/main/detector1K/utils.py): `detector1K/utils.py`

### Models and labels

- [ImageNet labels](https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/blob/main/detector1K/imagenet1000_clsid_to_human.pkl): `detector1K/imagenet1000_clsid_to_human.pkl`
- [ONNX model files](https://github.com/ibaigorordo/onnx-imagenet-1k-object-detector/tree/main/models): `models`

### Other components

- **User media**
- **Google Drive**
- **Annotated display**

## Connections

- User media → Image script: supplies image (evidence: `README.md`)
- User media → Video script: supplies video (evidence: `README.md`)
- User media → Webcam script: supplies frames (evidence: `webcam_object_detection.py`)
- Image script → Detection pipeline: calls detector (evidence: `image_object_detection.py`)
- Video script → Detection pipeline: calls detector (evidence: `video_object_detection.py`)
- Webcam script → Detection pipeline: calls detector (evidence: `webcam_object_detection.py`)
- Detection pipeline → ResNet classifier: classifies crops (evidence: `detector1K/detector1K.py`)
- ResNet classifier → ImageNet labels: reads labels (evidence: `detector1K/resnet50Classifier.py`)
- Detection pipeline → Download helpers: downloads localizer (evidence: `detector1K/detector1K.py`)
- ResNet classifier → Download helpers: downloads classifier (evidence: `detector1K/resnet50Classifier.py`)
- Download helpers → Google Drive: downloads models (evidence: `detector1K/utils.py`)
- Download helpers → ONNX model files: writes model files (evidence: `detector1K/utils.py`)
- Image script → Detection pipeline: renders detections (evidence: `image_object_detection.py`)
- Video script → Detection pipeline: renders frames (evidence: `video_object_detection.py`)
- Webcam script → Detection pipeline: renders frames (evidence: `webcam_object_detection.py`)
- Image script → Annotated display: shows image (evidence: `image_object_detection.py`)
- Video script → Annotated display: shows frames (evidence: `video_object_detection.py`)
- Webcam script → Annotated display: shows frames (evidence: `webcam_object_detection.py`)
