Skip to content

Latest commit

 

History

History
 
 

dewarpnet

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 

DewarpNet

Input

(from https://github.com/cvlab-stonybrook/DewarpNet/tree/master/eval/inp)

Ailia input shape: (1, 3, 256, 256)
Range: [0, 1]

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 dewarpnet.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 dewarpnet.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 dewarpnet.py --video VIDEO_PATH

Reference

DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks

Framework

PyTorch 1.3.1

Model Format

ONNX opset = 10

Netron

bm_model.onnx.prototxt

wc_model.opt.onnx.prototxt