# leikunx/ai_projects architecture

> Architecture diagram of the GitHub repository leikunx/ai_projects, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-05). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/leikunx/ai_projects
- Repository: https://github.com/leikunx/ai_projects

## Overview

This repository is a collection of independent AI project examples, not one application. Its clearest end-to-end workflow is the YOLOv3 image-detection service: a client submits an image, the server invokes a detector, and the result is returned for client-side display. Other branches cover custom detector training, Mask R-CNN, face recognition, motion detection, and a ResNet parallel-model utility. Relationships are shown only where the supplied excerpts or SOURCE INDEX support them; unsampled project details are not inferred.

Main entry points: [`005_模型部署_在线预测/code/_11_yolov3_server_3.py`](https://github.com/leikunx/ai_projects/blob/master/005_%E6%A8%A1%E5%9E%8B%E9%83%A8%E7%BD%B2_%E5%9C%A8%E7%BA%BF%E9%A2%84%E6%B5%8B/code/_11_yolov3_server_3.py) (Detection service), [`007_人脸识别实践_mxnet版insightFace/code/FaceDetection_mtcnn.py`](https://github.com/leikunx/ai_projects/blob/master/007_%E4%BA%BA%E8%84%B8%E8%AF%86%E5%88%AB%E5%AE%9E%E8%B7%B5_mxnet%E7%89%88insightFace/code/FaceDetection_mtcnn.py) (MTCNN detection), [`007_人脸识别实践_mxnet版insightFace/code/_02_demo.py`](https://github.com/leikunx/ai_projects/blob/master/007_%E4%BA%BA%E8%84%B8%E8%AF%86%E5%88%AB%E5%AE%9E%E8%B7%B5_mxnet%E7%89%88insightFace/code/_02_demo.py) (Recognition demo), [`007_人脸识别实践_mxnet版insightFace/code/_03_application.py`](https://github.com/leikunx/ai_projects/blob/master/007_%E4%BA%BA%E8%84%B8%E8%AF%86%E5%88%AB%E5%AE%9E%E8%B7%B5_mxnet%E7%89%88insightFace/code/_03_application.py) (Face application)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_yolo_train["YOLOv3 training"]
  node_dataset_prep["Image selection"]
  node_label_check["Label validation"]
  node_image_compress["Image compression"]
  node_annotation_list["Annotation lists"]
  node_anchor_cluster["Anchor clustering<br/>[kmeans.py]"]
  node_weight_convert["Weight conversion<br/>[convert.py]"]
  node_yolo_train_run["Model training<br/>[_05_train.py]"]
  node_yolo_train_model["YOLO model<br/>[model.py]"]
  node_yolo_detect["Image detection<br/>[_06_yolo.py]"]
  node_yolo_batch["Batch images"]
  node_yolo_video["Video detection<br/>[yolo_video.py]"]
end

subgraph group_deploy["YOLOv3 deployment"]
  node_image_client["Image client"]
  node_web_service["Detection service"]
  node_deployed_detector["YOLO detector<br/>[_06_yolov3.py]"]
  node_deployed_model["YOLO model<br/>[model.py]"]
end

subgraph group_mask["Mask R-CNN"]
  node_mask_prepare["Data preparation"]
  node_mask_labels["Label checks"]
  node_mask_resize["Image resizing"]
  node_mask_train["Model training<br/>[_05_train.py]"]
  node_mask_infer["Image inference"]
  node_mask_batch["Batch inference"]
end

subgraph group_faces["Face recognition"]
  node_face_detection["MTCNN detection"]
  node_face_alignment["Face alignment<br/>[_01_align_face.py]"]
  node_face_recognizer["Face recognition<br/>[FaceRecognizer.py]"]
  node_face_recognizer2["Recognition variant"]
  node_face_demo["Recognition demo<br/>[_02_demo.py]"]
  node_face_application["Face application<br/>[_03_application.py]"]
end

subgraph group_vision_misc["Other vision examples"]
  node_motion_examples["Motion detection"]
  node_parallel_resnet["Parallel ResNet<br/>[parallel_model.py]"]
end

node_user(("Image user"))
node_detected_result["Detection result"]

node_image_client -->|"POSTs image"| node_web_service
node_web_service -->|"invokes detector"| node_deployed_detector
node_deployed_detector -->|"builds model"| node_deployed_model
node_web_service -.->|"returns detections"| node_detected_result
node_user -.->|"submits image"| node_image_client
node_face_alignment -->|"uses detector"| node_face_detection
node_face_demo -->|"uses detector"| node_face_detection
node_face_demo -->|"uses recognizer"| node_face_recognizer
node_face_application -->|"uses detector"| node_face_detection
node_face_application -->|"uses recognizer"| node_face_recognizer2

click node_dataset_prep "https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_01_select_images.py"
click node_label_check "https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_02_check_labels.py"
click node_image_compress "https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_03_compress_images.py"
click node_annotation_list "https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_04_generate_txtFile.py"
click node_anchor_cluster "https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/kmeans.py"
click node_weight_convert "https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/convert.py"
click node_yolo_train_run "https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_05_train.py"
click node_yolo_train_model "https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/yolo3/model.py"
click node_yolo_detect "https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_06_yolo.py"
click node_yolo_batch "https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_08_detect_multi_images.py"
click node_yolo_video "https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/yolo_video.py"
click node_image_client "https://github.com/leikunx/ai_projects/blob/master/005_%E6%A8%A1%E5%9E%8B%E9%83%A8%E7%BD%B2_%E5%9C%A8%E7%BA%BF%E9%A2%84%E6%B5%8B/code/_12_yolov3_client_3.py"
click node_web_service "https://github.com/leikunx/ai_projects/blob/master/005_%E6%A8%A1%E5%9E%8B%E9%83%A8%E7%BD%B2_%E5%9C%A8%E7%BA%BF%E9%A2%84%E6%B5%8B/code/_11_yolov3_server_3.py"
click node_deployed_detector "https://github.com/leikunx/ai_projects/blob/master/005_%E6%A8%A1%E5%9E%8B%E9%83%A8%E7%BD%B2_%E5%9C%A8%E7%BA%BF%E9%A2%84%E6%B5%8B/code/_06_yolov3.py"
click node_deployed_model "https://github.com/leikunx/ai_projects/blob/master/005_%E6%A8%A1%E5%9E%8B%E9%83%A8%E7%BD%B2_%E5%9C%A8%E7%BA%BF%E9%A2%84%E6%B5%8B/code/yolo3/model.py"
click node_mask_prepare "https://github.com/leikunx/ai_projects/blob/master/002_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88Mask-RCNN%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_01_select_images.py"
click node_mask_labels "https://github.com/leikunx/ai_projects/blob/master/002_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88Mask-RCNN%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_02_check_labels.py"
click node_mask_resize "https://github.com/leikunx/ai_projects/blob/master/002_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88Mask-RCNN%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_03_resize_images.py"
click node_mask_train "https://github.com/leikunx/ai_projects/blob/master/002_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88Mask-RCNN%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_05_train.py"
click node_mask_infer "https://github.com/leikunx/ai_projects/blob/master/002_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88Mask-RCNN%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_06_test_one_image.py"
click node_mask_batch "https://github.com/leikunx/ai_projects/blob/master/002_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88Mask-RCNN%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_07_test_multi_images.py"
click node_face_detection "https://github.com/leikunx/ai_projects/blob/master/007_%E4%BA%BA%E8%84%B8%E8%AF%86%E5%88%AB%E5%AE%9E%E8%B7%B5_mxnet%E7%89%88insightFace/code/FaceDetection_mtcnn.py"
click node_face_alignment "https://github.com/leikunx/ai_projects/blob/master/007_%E4%BA%BA%E8%84%B8%E8%AF%86%E5%88%AB%E5%AE%9E%E8%B7%B5_mxnet%E7%89%88insightFace/code/_01_align_face.py"
click node_face_recognizer "https://github.com/leikunx/ai_projects/blob/master/007_%E4%BA%BA%E8%84%B8%E8%AF%86%E5%88%AB%E5%AE%9E%E8%B7%B5_mxnet%E7%89%88insightFace/code/FaceRecognizer.py"
click node_face_recognizer2 "https://github.com/leikunx/ai_projects/blob/master/007_%E4%BA%BA%E8%84%B8%E8%AF%86%E5%88%AB%E5%AE%9E%E8%B7%B5_mxnet%E7%89%88insightFace/code/FaceRecognizer_2.py"
click node_face_demo "https://github.com/leikunx/ai_projects/blob/master/007_%E4%BA%BA%E8%84%B8%E8%AF%86%E5%88%AB%E5%AE%9E%E8%B7%B5_mxnet%E7%89%88insightFace/code/_02_demo.py"
click node_face_application "https://github.com/leikunx/ai_projects/blob/master/007_%E4%BA%BA%E8%84%B8%E8%AF%86%E5%88%AB%E5%AE%9E%E8%B7%B5_mxnet%E7%89%88insightFace/code/_03_application.py"
click node_motion_examples "https://github.com/leikunx/ai_projects/tree/master/006_%E6%A3%80%E6%B5%8B%E7%A7%BB%E5%8A%A8%E7%89%A9%E4%BD%93/code"
click node_parallel_resnet "https://github.com/leikunx/ai_projects/blob/master/004_%E5%A4%8D%E5%86%99%E4%BB%A3%E7%A0%81_keras%E7%89%88ResNet/code/parallel_model.py"

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_dataset_prep,node_label_check,node_image_compress,node_annotation_list,node_anchor_cluster,node_weight_convert,node_yolo_train_run,node_yolo_train_model,node_yolo_detect,node_yolo_batch,node_yolo_video,node_user toneBlue
class node_image_client,node_web_service,node_deployed_detector,node_deployed_model toneAmber
class node_mask_prepare,node_mask_labels,node_mask_resize,node_mask_train,node_mask_infer,node_mask_batch toneMint
class node_face_detection,node_face_alignment,node_face_recognizer,node_face_recognizer2,node_face_demo,node_face_application toneRose
class node_motion_examples,node_parallel_resnet,node_detected_result toneIndigo
```

## Components

### YOLOv3 training

- [Image selection](https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_01_select_images.py): `001_目标检测实践_keras版YOLOv3训练自己的数据/code/_01_select_images.py`
- [Label validation](https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_02_check_labels.py): `001_目标检测实践_keras版YOLOv3训练自己的数据/code/_02_check_labels.py`
- [Image compression](https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_03_compress_images.py): `001_目标检测实践_keras版YOLOv3训练自己的数据/code/_03_compress_images.py`
- [Annotation lists](https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_04_generate_txtFile.py): `001_目标检测实践_keras版YOLOv3训练自己的数据/code/_04_generate_txtFile.py`
- [Anchor clustering](https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/kmeans.py): `001_目标检测实践_keras版YOLOv3训练自己的数据/code/kmeans.py`
- [Weight conversion](https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/convert.py): `001_目标检测实践_keras版YOLOv3训练自己的数据/code/convert.py`
- [Model training](https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_05_train.py): `001_目标检测实践_keras版YOLOv3训练自己的数据/code/_05_train.py`
- [YOLO model](https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/yolo3/model.py): `001_目标检测实践_keras版YOLOv3训练自己的数据/code/yolo3/model.py`
- [Image detection](https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_06_yolo.py): `001_目标检测实践_keras版YOLOv3训练自己的数据/code/_06_yolo.py`
- [Batch images](https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_08_detect_multi_images.py): `001_目标检测实践_keras版YOLOv3训练自己的数据/code/_08_detect_multi_images.py`
- [Video detection](https://github.com/leikunx/ai_projects/blob/master/001_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88YOLOv3%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/yolo_video.py): `001_目标检测实践_keras版YOLOv3训练自己的数据/code/yolo_video.py`

### YOLOv3 deployment

- [Image client](https://github.com/leikunx/ai_projects/blob/master/005_%E6%A8%A1%E5%9E%8B%E9%83%A8%E7%BD%B2_%E5%9C%A8%E7%BA%BF%E9%A2%84%E6%B5%8B/code/_12_yolov3_client_3.py): `005_模型部署_在线预测/code/_12_yolov3_client_3.py`
- [Detection service](https://github.com/leikunx/ai_projects/blob/master/005_%E6%A8%A1%E5%9E%8B%E9%83%A8%E7%BD%B2_%E5%9C%A8%E7%BA%BF%E9%A2%84%E6%B5%8B/code/_11_yolov3_server_3.py): `005_模型部署_在线预测/code/_11_yolov3_server_3.py`
- [YOLO detector](https://github.com/leikunx/ai_projects/blob/master/005_%E6%A8%A1%E5%9E%8B%E9%83%A8%E7%BD%B2_%E5%9C%A8%E7%BA%BF%E9%A2%84%E6%B5%8B/code/_06_yolov3.py): `005_模型部署_在线预测/code/_06_yolov3.py`
- [YOLO model](https://github.com/leikunx/ai_projects/blob/master/005_%E6%A8%A1%E5%9E%8B%E9%83%A8%E7%BD%B2_%E5%9C%A8%E7%BA%BF%E9%A2%84%E6%B5%8B/code/yolo3/model.py): `005_模型部署_在线预测/code/yolo3/model.py`

### Mask R-CNN

- [Data preparation](https://github.com/leikunx/ai_projects/blob/master/002_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88Mask-RCNN%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_01_select_images.py): `002_目标检测实践_keras版Mask-RCNN训练自己的数据/code/_01_select_images.py`
- [Label checks](https://github.com/leikunx/ai_projects/blob/master/002_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88Mask-RCNN%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_02_check_labels.py): `002_目标检测实践_keras版Mask-RCNN训练自己的数据/code/_02_check_labels.py`
- [Image resizing](https://github.com/leikunx/ai_projects/blob/master/002_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88Mask-RCNN%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_03_resize_images.py): `002_目标检测实践_keras版Mask-RCNN训练自己的数据/code/_03_resize_images.py`
- [Model training](https://github.com/leikunx/ai_projects/blob/master/002_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88Mask-RCNN%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_05_train.py): `002_目标检测实践_keras版Mask-RCNN训练自己的数据/code/_05_train.py`
- [Image inference](https://github.com/leikunx/ai_projects/blob/master/002_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88Mask-RCNN%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_06_test_one_image.py): `002_目标检测实践_keras版Mask-RCNN训练自己的数据/code/_06_test_one_image.py`
- [Batch inference](https://github.com/leikunx/ai_projects/blob/master/002_%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E5%AE%9E%E8%B7%B5_keras%E7%89%88Mask-RCNN%E8%AE%AD%E7%BB%83%E8%87%AA%E5%B7%B1%E7%9A%84%E6%95%B0%E6%8D%AE/code/_07_test_multi_images.py): `002_目标检测实践_keras版Mask-RCNN训练自己的数据/code/_07_test_multi_images.py`

### Face recognition

- [MTCNN detection](https://github.com/leikunx/ai_projects/blob/master/007_%E4%BA%BA%E8%84%B8%E8%AF%86%E5%88%AB%E5%AE%9E%E8%B7%B5_mxnet%E7%89%88insightFace/code/FaceDetection_mtcnn.py): `007_人脸识别实践_mxnet版insightFace/code/FaceDetection_mtcnn.py`
- [Face alignment](https://github.com/leikunx/ai_projects/blob/master/007_%E4%BA%BA%E8%84%B8%E8%AF%86%E5%88%AB%E5%AE%9E%E8%B7%B5_mxnet%E7%89%88insightFace/code/_01_align_face.py): `007_人脸识别实践_mxnet版insightFace/code/_01_align_face.py`
- [Face recognition](https://github.com/leikunx/ai_projects/blob/master/007_%E4%BA%BA%E8%84%B8%E8%AF%86%E5%88%AB%E5%AE%9E%E8%B7%B5_mxnet%E7%89%88insightFace/code/FaceRecognizer.py): `007_人脸识别实践_mxnet版insightFace/code/FaceRecognizer.py`
- [Recognition variant](https://github.com/leikunx/ai_projects/blob/master/007_%E4%BA%BA%E8%84%B8%E8%AF%86%E5%88%AB%E5%AE%9E%E8%B7%B5_mxnet%E7%89%88insightFace/code/FaceRecognizer_2.py): `007_人脸识别实践_mxnet版insightFace/code/FaceRecognizer_2.py`
- [Recognition demo](https://github.com/leikunx/ai_projects/blob/master/007_%E4%BA%BA%E8%84%B8%E8%AF%86%E5%88%AB%E5%AE%9E%E8%B7%B5_mxnet%E7%89%88insightFace/code/_02_demo.py): `007_人脸识别实践_mxnet版insightFace/code/_02_demo.py`
- [Face application](https://github.com/leikunx/ai_projects/blob/master/007_%E4%BA%BA%E8%84%B8%E8%AF%86%E5%88%AB%E5%AE%9E%E8%B7%B5_mxnet%E7%89%88insightFace/code/_03_application.py): `007_人脸识别实践_mxnet版insightFace/code/_03_application.py`

### Other vision examples

- [Motion detection](https://github.com/leikunx/ai_projects/tree/master/006_%E6%A3%80%E6%B5%8B%E7%A7%BB%E5%8A%A8%E7%89%A9%E4%BD%93/code): `006_检测移动物体/code`
- [Parallel ResNet](https://github.com/leikunx/ai_projects/blob/master/004_%E5%A4%8D%E5%86%99%E4%BB%A3%E7%A0%81_keras%E7%89%88ResNet/code/parallel_model.py): `004_复写代码_keras版ResNet/code/parallel_model.py`

### Other components

- **Image user**
- **Detection result**

## Connections

- Image client → Detection service: POSTs image (evidence: `005_模型部署_在线预测/code/_12_yolov3_client_3.py`)
- Detection service → YOLO detector: invokes detector (evidence: `005_模型部署_在线预测/code/_11_yolov3_server_3.py`)
- YOLO detector → YOLO model: builds model (evidence: `005_模型部署_在线预测/code/_06_yolov3.py`)
- Detection service → Detection result: returns detections
- Image user → Image client: submits image
- Face alignment → MTCNN detection: uses detector (evidence: `007_人脸识别实践_mxnet版insightFace/code/_01_align_face.py`)
- Recognition demo → MTCNN detection: uses detector (evidence: `007_人脸识别实践_mxnet版insightFace/code/_02_demo.py`)
- Recognition demo → Face recognition: uses recognizer (evidence: `007_人脸识别实践_mxnet版insightFace/code/_02_demo.py`)
- Face application → MTCNN detection: uses detector (evidence: `007_人脸识别实践_mxnet版insightFace/code/_03_application.py`)
- Face application → Recognition variant: uses recognizer (evidence: `007_人脸识别实践_mxnet版insightFace/code/_03_application.py`)
