Skip to content

Latest commit

 

History

History

nanodet

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 
 
 

NanoDet

Input

Input

(Image from https://github.com/RangiLyu/nanodet/blob/main/demo_mnn/imgs/000252.jpg)

Ailia input shape: (1, 3, 320, 320), (1, 3, 416, 416), (1, 3, 512, 512)

Output

Output

Usage

Automatically downloads the onnx and prototxt files on the first run. It is necessary to be connected to the Internet while downloading.

For the sample image,

$ python3 nanodet.py

If you want to specify the input image, put the image path after the --input option.
You can use --savepath option to change the name of the output file to save.

$ python3 nanodet.py --input IMAGE_PATH --savepath SAVE_IMAGE_PATH

By adding the --video option, you can input the video.
If you pass 0 as an argument to VIDEO_PATH, you can use the webcam input instead of the video file.

$ python3 nanodet.py --video VIDEO_PATH

The default setting is to use the optimized model and weights, but you can also switch to the normal model by using the --normal option.

Reference

NanoDet

Framework

Pytorch

Model Format

ONNX opset = 11

Netron

nanodet_m.opt.onnx.prototxt

nanodet_m_416.opt.onnx.prototxt

nanodet_t.opt.onnx.prototxt

nanodet-EfficientNet-Lite0_320.opt.onnx.prototxt

nanodet-EfficientNet-Lite1_416.opt.onnx.prototxt

nanodet-EfficientNet-Lite2_512.opt.onnx.prototxt

nanodet-RepVGG-A0_416.opt.onnx.prototxt