waifu2x-ncnn-py 2.0.0

No project description provided

waifu2x-ncnn-py

Python Binding for waifu2x-ncnn-vulkan with PyBind11

Image Super-Resolution for Anime-style art using Deep Convolutional Neural Networks. And it supports photo. This wrapper provides an easy-to-use interface for running the pre-trained Waifu2x model.

Current building status matrix

System	Status	CPU (32bit)	CPU (64bit)	GPU (32bit)	GPU (64bit)
Linux (Clang)		—	:white_check_mark:	—	:white_check_mark:
Linux (GCC)		—	:white_check_mark:	—	:white_check_mark:
Windows		—	:white_check_mark:	—	:white_check_mark:
MacOS		—	:white_check_mark:	—	:white_check_mark:
MacOS (ARM)		—	:white_check_mark:	—	:white_check_mark:

Usage

To use this package, simply install it via pip:

pip install waifu2x-ncnn-py

For Linux user:

apt install -y libomp5 libvulkan-dev

Then, import the Waifu2x class from the package:

from src.waifu2x_ncnn_py import Waifu2x

To initialize the model:

waifu2x = Waifu2x(gpuid: int = 0, tta_mode: bool = False, num_threads: int = 1, noise: int = 0, scale: int = 2, tilesize: int = 0, model: str = "models-cunet")
# model can be "models-cunet", "models-upconv_7_anime_style_art_rgb" and "models-upconv_7_photo"
# or an absolute path to the models' directory

Here, gpuid specifies the GPU device to use (-1 means use CPU), tta_mode enables test-time augmentation, num_threads sets the number of threads for processing, noise specifies the level of noise to apply to the image (-1 to 3), scale is the scaling factor for super-resolution (1 to 4), tilesize specifies the tile size for processing (0 or >= 32), and model specifies the name of the pre-trained model to use.

Once the model is initialized, you can use the upscale method to super-resolve your images:

Pillow

from PIL import Image
waifu2x = Waifu2x(gpuid=0, scale=2, noise=3)
with Image.open("input.jpg") as image:
    image = waifu2x.process_pil(image)
    image.save("output.jpg", quality=95)

opencv-python

import cv2
waifu2x = Waifu2x(gpuid=0, scale=2, noise=3)
image = cv2.imdecode(np.fromfile("input.jpg", dtype=np.uint8), cv2.IMREAD_COLOR)
image = waifu2x.process_cv2(image)
cv2.imencode(".jpg", image)[1].tofile("output_cv2.jpg")

ffmpeg

import subprocess as sp
# your ffmpeg parameters
command_out = [FFMPEG_BIN,........]
command_in = [FFMPEG_BIN,........]
pipe_out = sp.Popen(command_out, stdout=sp.PIPE, bufsize=10 ** 8)
pipe_in = sp.Popen(command_in, stdin=sp.PIPE)
waifu2x = Waifu2x(gpuid=0, scale=2, noise=3)
while True:
    raw_image = pipe_out.stdout.read(src_width * src_height * 3)
    if not raw_image:
        break
    raw_image = waifu2x.process_bytes(raw_image, src_width, src_height, 3)
    pipe_in.stdin.write(raw_image)

Build

here

The project just only been tested in Ubuntu 18+ and Debian 9+ environments on Linux, so if the project does not work on your system, please try building it.

References

The following references were used in the development of this project:

nihui/waifu2x-ncnn-vulkan - This project was the main inspiration for our work. It provided the core implementation of the Waifu2x algorithm using the ncnn and Vulkan libraries.

Waifu2x - Waifu2x is an Image Super-Resolution algorithm for Anime-style art using Deep Convolutional Neural Networks. And it supports photo.

media2x/waifu2x-ncnn-vulkan-python - This project was used as a reference for implementing the wrapper. Special thanks to the original author for sharing the code.

ncnn - ncnn is a high-performance neural network inference framework developed by Tencent AI Lab.

License

This project is licensed under the BSD 3-Clause - see the LICENSE file for details.