Ailia input shape : (1,3,256,256)
Range : [0.0, 1.0]
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 noise2noise.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 noise2noise.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 noise2noise.py --video VIDEO_PATH
If you want to try this model on a normal image, --add_noise
will automatically add noise to the image before loading it.
The noise-added image will be saved as noise_image.png
in the current directory.
Learning Image Restoration without Clean Data
Pytorch 1.2.0
ONNX opset = 10