Skip to content

Latest commit

 

History

History

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 

VOLO

Input

Input

Shape : (1,3,224,224)

Output

class_count=3
+ idx=0
  category=963[pizza, pizza pie ]
  prob=12.82837963104248
+ idx=1
  category=923[plate ]
  prob=3.2662553787231445
+ idx=2
  category=572[goblet ]
  prob=2.8674607276916504
Script finished successfully.

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 volo.py

If you want to specify the input image, put the image path after the --input option.

$ python3 volo.py --input 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 volo.py --video VIDEO_PATH

Reference

VOLO: Vision Outlooker for Visual Recognition

Model Format

ONNX opset = 11

Framework

Pytorch 2.2.0

Netron

volo_d1_224.onnx.prototxt

volo_d1_384.onnx.prototxt

volo_d2_224.onnx.prototxt

volo_d2_384.onnx.prototxt

volo_d3_224.onnx.prototxt

volo_d3_448.onnx.prototxt

volo_d4_224.onnx.prototxt

volo_d4_448.onnx.prototxt

volo_d5_224.onnx.prototxt