where can we download yolov5s.640-640.v.6.0.onnx

[MyraBaba]

Hi,

I couldn't find the model for std::string onnx_path = "../../../hub/onnx/cv/yolov5s.640-640.v.6.0.onnx";

thx

[DefTruth]

See the latest README.md, you can download the all the onnx files from docker hub now.

Model Zoo.

Lite.AI.ToolKit contains 70+ AI models with 500+ frozen pretrained files now. Most of the files are converted by myself. You can use it through lite::cv::Type::Class syntax, such as lite::cv::detection::YoloV5. More details can be found at Examples for Lite.AI.ToolKit. Note, for Google Drive, I can not upload all the *.onnx files because of the storage limitation (15G).

File	Baidu Drive	Google Drive	Docker Hub	Hub (Docs)
ONNX	Baidu Drive code: 8gin	Google Drive	ONNX Docker v0.1.22.01.08 (28G)	ONNX Hub
MNN	Baidu Drive code: 9v63	❔	MNN Docker v0.1.22.01.08 (11G)	MNN Hub
NCNN	Baidu Drive code: sc7f	❔	NCNN Docker v0.1.22.01.08 (9G)	NCNN Hub
TNN	Baidu Drive code: 6o6k	❔	TNN Docker v0.1.22.01.08 (11G)	TNN Hub

  docker pull qyjdefdocker/lite.ai.toolkit-onnx-hub:v0.1.22.01.08  # (28G)
  docker pull qyjdefdocker/lite.ai.toolkit-mnn-hub:v0.1.22.01.08   # (11G)
  docker pull qyjdefdocker/lite.ai.toolkit-ncnn-hub:v0.1.22.01.08  # (9G)
  docker pull qyjdefdocker/lite.ai.toolkit-tnn-hub:v0.1.22.01.08   # (11G)

🔑️ How to download Model Zoo from Docker Hub?

• Firstly, pull the image from docker hub.

  docker pull qyjdefdocker/lite.ai.toolkit-mnn-hub:v0.1.22.01.08 # (11G)
  docker pull qyjdefdocker/lite.ai.toolkit-ncnn-hub:v0.1.22.01.08 # (9G)
  docker pull qyjdefdocker/lite.ai.toolkit-tnn-hub:v0.1.22.01.08 # (11G)
  docker pull qyjdefdocker/lite.ai.toolkit-onnx-hub:v0.1.22.01.08 # (28G)

• Secondly, run the container with local share dir using docker run -idt xxx. A minimum example will show you as follows.

  • make a share dir in your local device.

    mkdir share # any name is ok.

  • write run_mnn_docker_hub.sh script like:

    
    #!/bin/bash  
    PORT1=6072
    PORT2=6084
    SERVICE_DIR=/Users/xxx/Desktop/your-path-to/share
    CONRAINER_DIR=/home/hub/share
    CONRAINER_NAME=mnn_docker_hub_d

  docker run -idt -p ${PORT2}:${PORT1} -v ${SERVICE_DIR}:${CONRAINER_DIR} --shm-size=16gb --name ${CONRAINER_NAME} qyjdefdocker/lite.ai.toolkit-mnn-hub:v0.1.22.01.08

• Finally, copy the model weights from /home/hub/mnn/cv to your local share dir.

  # activate mnn docker.
  sh ./run_mnn_docker_hub.sh
  docker exec -it mnn_docker_hub_d /bin/bash
  # copy the models to the share dir.
  cd /home/hub 
  cp -rf mnn/cv share/

[MyraBaba]

@DefTruth hi ,

I couldnt find the yolov5face-s-640x640.onnx model. is it added ? Other yolov5face models will be added also ?

[DefTruth]

@DefTruth hi ,

I couldnt find the yolov5face-s-640x640.onnx model. is it added ? Other yolov5face models will be added also ?

it can be download from Baidu Driver now, but not include into the docker images. i will update the docker images some days latter.

or you can download the nano version of converted YOLO5Face from my demo project:

• https://github.com/DefTruth/YOLO5Face.lite.ai.toolkit/tree/main/examples/hub

[MyraBaba]

@DefTruth When we can download yolov5face models ? We cant reach baidu drive.

Best

[DefTruth]

@DefTruth When we can download yolov5face models ? We cant reach baidu drive.

Best

Hello, currrently, my family and I are celebrating Chinese New Year. When I'm free, I'll upload all the model files to docker hub ~ however, you can download the nano version of yolov5face onnx/mnn/ncnn/tnn model files from my demo project:

• https://github.com/DefTruth/YOLO5Face.lite.ai.toolkit/tree/main/examples/hub

[DefTruth]

you can download the converted ONNX/MNN/NCNN/TNN files of YOLO5Face from docker hub now ~

  docker pull qyjdefdocker/lite.ai.toolkit-onnx-hub:v0.1.22.02.02  # (400M) + YOLO5Face
  docker pull qyjdefdocker/lite.ai.toolkit-mnn-hub:v0.1.22.02.02   # (213M) + YOLO5Face
  docker pull qyjdefdocker/lite.ai.toolkit-ncnn-hub:v0.1.22.02.02  # (197M) + YOLO5Face
  docker pull qyjdefdocker/lite.ai.toolkit-tnn-hub:v0.1.22.02.02   # (217M) + YOLO5Face

[MyraBaba]

@DefTruth thanks for models. I make a speed test wit "s" models and ncnn is x4 time , tnn is x2 times slower than mnn and onnx. ncnn should be faster i assume.

[MyraBaba]

@DefTruth Hi I hope all is good at your end.

I saw yolov5m-face.pt model at https://github.com/deepcam-cn/yolov5-face and the size is 169MB . Yours onnx converted one is yolov5face-m-640x640.onnx 87 MB. What are the differences ? Both are same quality or something different ?

Best

[MyraBaba]

@DefTruth

Hi,

I noticed that the yolov5Face models allways return score : 0.98....

same score. Do you know this ? or are you already updated ?