chore(local-tool): models.json 只保留有實體 .nef 的 7 個預設模型
使用者要求：前端模型庫只保留有適配裝置的模型（KL520 4 個 + KL720 3 個）。
原本 models.json 有 15 筆：
- 8 筆 ONNX framework 的 demo 模型（yolov5-face-detection /
imagenet-classification / person-detection / vehicle-classification /
hand-gesture-recognition / coco-object-detection / face-mask-detection /
license-plate-detection）— 都沒有實體 .nef 檔，是 placeholder metadata
- 7 筆 NEF framework 的實體模型（每個都有 filePath 指向 data/nef/）
現在只保留 7 筆實體模型：
KL520（4 個）：
- kl520-yolov5-detection (yolov5 no-upsample 640x640)
- kl520-fcos-detection (fcos-drk53s 512x512)
- kl520-ssd-face-detection (ssd_fd_lm 320x240)
- kl520-tiny-yolov3 (tiny_yolo_v3 416x416)
KL720（3 個）：
- kl720-yolov5-detection (yolov5 no-upsample 640x640)
- kl720-resnet18-classification (resnet18 224x224)
- kl720-fcos-detection (fcos-drk53s 512x512)
server/data/models.json 是 runtime 讀取，三平台（macOS/Windows/Linux）
共用同一份，改一次三平台全部生效。
驗證：
- python3 json.load 解析正常，7 筆 entries
- 每筆 filePath 指向的 .nef 實體檔都存在於 server/data/nef/{kl520,kl720}/
- 檔案大小：1-13 MB，合計 ~64 MB
- macOS dmg 重 build 163MB OK
- Bundle 內 Contents/Resources/data/models.json 更新為 7 筆
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
parent
ad9beab0ca
commit
9793a2efc1
@ -1,181 +1,4 @@
|
||||
[
|
||||
{
|
||||
"id": "yolov5-face-detection",
|
||||
"name": "YOLOv5 Face Detection",
|
||||
"description": "Real-time face detection model based on YOLOv5 architecture, optimized for edge deployment on Kneron KL720. Detects faces with high accuracy in various lighting conditions.",
|
||||
"thumbnail": "/images/models/yolov5-face.png",
|
||||
"taskType": "object_detection",
|
||||
"categories": ["face", "security", "people"],
|
||||
"framework": "ONNX",
|
||||
"inputSize": {"width": 640, "height": 640},
|
||||
"modelSize": 14200000,
|
||||
"quantization": "INT8",
|
||||
"accuracy": 0.92,
|
||||
"latencyMs": 33,
|
||||
"fps": 30,
|
||||
"supportedHardware": ["KL720", "KL730"],
|
||||
"labels": ["face"],
|
||||
"version": "1.0.0",
|
||||
"author": "Kneron",
|
||||
"license": "Apache-2.0",
|
||||
"createdAt": "2024-01-15T00:00:00Z",
|
||||
"updatedAt": "2024-06-01T00:00:00Z"
|
||||
},
|
||||
{
|
||||
"id": "imagenet-classification",
|
||||
"name": "ImageNet Classification (ResNet18)",
|
||||
"description": "ResNet18-based image classification model trained on ImageNet. Supports 1000 object categories with efficient inference on KL520 edge devices.",
|
||||
"thumbnail": "/images/models/imagenet-cls.png",
|
||||
"taskType": "classification",
|
||||
"categories": ["general", "image-classification"],
|
||||
"framework": "ONNX",
|
||||
"inputSize": {"width": 224, "height": 224},
|
||||
"modelSize": 12000000,
|
||||
"quantization": "INT8",
|
||||
"accuracy": 0.78,
|
||||
"latencyMs": 15,
|
||||
"fps": 60,
|
||||
"supportedHardware": ["KL520", "KL720", "KL730"],
|
||||
"labels": ["airplane", "automobile", "bird", "cat", "deer", "dog", "frog", "horse", "ship", "truck"],
|
||||
"filePath": "data/nef/kl520/kl520_20001_resnet18_w224h224.nef",
|
||||
"version": "2.1.0",
|
||||
"author": "Kneron",
|
||||
"license": "MIT",
|
||||
"createdAt": "2024-02-10T00:00:00Z",
|
||||
"updatedAt": "2024-07-15T00:00:00Z"
|
||||
},
|
||||
{
|
||||
"id": "person-detection",
|
||||
"name": "Person Detection",
|
||||
"description": "Lightweight person detection model optimized for real-time surveillance and people counting. Low latency with high accuracy on person class.",
|
||||
"thumbnail": "/images/models/person-det.png",
|
||||
"taskType": "object_detection",
|
||||
"categories": ["people", "security", "surveillance"],
|
||||
"framework": "ONNX",
|
||||
"inputSize": {"width": 416, "height": 416},
|
||||
"modelSize": 11800000,
|
||||
"quantization": "INT8",
|
||||
"accuracy": 0.89,
|
||||
"latencyMs": 28,
|
||||
"fps": 35,
|
||||
"supportedHardware": ["KL720", "KL730"],
|
||||
"labels": ["person"],
|
||||
"version": "1.2.0",
|
||||
"author": "Kneron",
|
||||
"license": "Apache-2.0",
|
||||
"createdAt": "2024-03-01T00:00:00Z",
|
||||
"updatedAt": "2024-08-01T00:00:00Z"
|
||||
},
|
||||
{
|
||||
"id": "vehicle-classification",
|
||||
"name": "Vehicle Classification",
|
||||
"description": "Vehicle type classification model that identifies cars, trucks, buses, motorcycles, and bicycles. Ideal for traffic monitoring and smart parking.",
|
||||
"thumbnail": "/images/models/vehicle-cls.png",
|
||||
"taskType": "classification",
|
||||
"categories": ["vehicle", "traffic", "transportation"],
|
||||
"framework": "ONNX",
|
||||
"inputSize": {"width": 224, "height": 224},
|
||||
"modelSize": 6200000,
|
||||
"quantization": "INT8",
|
||||
"accuracy": 0.85,
|
||||
"latencyMs": 12,
|
||||
"fps": 75,
|
||||
"supportedHardware": ["KL520", "KL720", "KL730"],
|
||||
"labels": ["car", "truck", "bus", "motorcycle", "bicycle"],
|
||||
"version": "1.0.0",
|
||||
"author": "Kneron",
|
||||
"license": "MIT",
|
||||
"createdAt": "2024-03-20T00:00:00Z",
|
||||
"updatedAt": "2024-05-10T00:00:00Z"
|
||||
},
|
||||
{
|
||||
"id": "hand-gesture-recognition",
|
||||
"name": "Hand Gesture Recognition",
|
||||
"description": "Recognizes 10 common hand gestures in real-time. Suitable for touchless interfaces and gesture-based control systems.",
|
||||
"thumbnail": "/images/models/hand-gesture.png",
|
||||
"taskType": "classification",
|
||||
"categories": ["gesture", "hand", "interaction"],
|
||||
"framework": "ONNX",
|
||||
"inputSize": {"width": 224, "height": 224},
|
||||
"modelSize": 5800000,
|
||||
"quantization": "INT8",
|
||||
"accuracy": 0.88,
|
||||
"latencyMs": 18,
|
||||
"fps": 50,
|
||||
"supportedHardware": ["KL520", "KL720"],
|
||||
"labels": ["thumbs_up", "thumbs_down", "open_palm", "fist", "peace", "ok", "pointing", "wave", "grab", "pinch"],
|
||||
"version": "1.1.0",
|
||||
"author": "Kneron",
|
||||
"license": "Apache-2.0",
|
||||
"createdAt": "2024-04-05T00:00:00Z",
|
||||
"updatedAt": "2024-09-01T00:00:00Z"
|
||||
},
|
||||
{
|
||||
"id": "coco-object-detection",
|
||||
"name": "COCO Object Detection",
|
||||
"description": "General-purpose object detection model trained on COCO dataset. Detects 80 common object categories including people, animals, vehicles, and household items.",
|
||||
"thumbnail": "/images/models/coco-det.png",
|
||||
"taskType": "object_detection",
|
||||
"categories": ["general", "multi-object", "coco"],
|
||||
"framework": "ONNX",
|
||||
"inputSize": {"width": 640, "height": 640},
|
||||
"modelSize": 23500000,
|
||||
"quantization": "INT8",
|
||||
"accuracy": 0.82,
|
||||
"latencyMs": 45,
|
||||
"fps": 22,
|
||||
"supportedHardware": ["KL720", "KL730"],
|
||||
"labels": ["person", "bicycle", "car", "motorcycle", "airplane", "bus", "train", "truck", "boat", "traffic light", "fire hydrant", "stop sign", "parking meter", "bench", "bird", "cat", "dog", "horse", "sheep", "cow"],
|
||||
"version": "3.0.0",
|
||||
"author": "Kneron",
|
||||
"license": "Apache-2.0",
|
||||
"createdAt": "2024-01-01T00:00:00Z",
|
||||
"updatedAt": "2024-10-01T00:00:00Z"
|
||||
},
|
||||
{
|
||||
"id": "face-mask-detection",
|
||||
"name": "Face Mask Detection",
|
||||
"description": "Detects whether a person is wearing a face mask, wearing it incorrectly, or not wearing one. Built for health compliance monitoring.",
|
||||
"thumbnail": "/images/models/face-mask.png",
|
||||
"taskType": "object_detection",
|
||||
"categories": ["face", "health", "safety"],
|
||||
"framework": "ONNX",
|
||||
"inputSize": {"width": 320, "height": 320},
|
||||
"modelSize": 9800000,
|
||||
"quantization": "INT8",
|
||||
"accuracy": 0.91,
|
||||
"latencyMs": 22,
|
||||
"fps": 45,
|
||||
"supportedHardware": ["KL720", "KL730"],
|
||||
"labels": ["mask_on", "mask_off", "mask_incorrect"],
|
||||
"version": "1.3.0",
|
||||
"author": "Kneron",
|
||||
"license": "MIT",
|
||||
"createdAt": "2024-02-28T00:00:00Z",
|
||||
"updatedAt": "2024-07-20T00:00:00Z"
|
||||
},
|
||||
{
|
||||
"id": "license-plate-detection",
|
||||
"name": "License Plate Detection",
|
||||
"description": "Detects and localizes license plates in images and video streams. Optimized for various plate formats and viewing angles.",
|
||||
"thumbnail": "/images/models/license-plate.png",
|
||||
"taskType": "object_detection",
|
||||
"categories": ["vehicle", "traffic", "ocr"],
|
||||
"framework": "ONNX",
|
||||
"inputSize": {"width": 416, "height": 416},
|
||||
"modelSize": 12400000,
|
||||
"quantization": "INT8",
|
||||
"accuracy": 0.87,
|
||||
"latencyMs": 30,
|
||||
"fps": 33,
|
||||
"supportedHardware": ["KL720", "KL730"],
|
||||
"labels": ["license_plate"],
|
||||
"version": "1.0.0",
|
||||
"author": "Kneron",
|
||||
"license": "Apache-2.0",
|
||||
"createdAt": "2024-05-15T00:00:00Z",
|
||||
"updatedAt": "2024-08-30T00:00:00Z"
|
||||
},
|
||||
{
|
||||
"id": "kl520-yolov5-detection",
|
||||
"name": "YOLOv5 Detection (KL520)",
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user