Skip to main content

self-use toolkits

Project description

kiui kit

A toolkit for personal use.

Install

# released
pip install kiui # install the minimal package
pip install kiui[full] # install optional dependencies

# latest
pip install git+https://github.com/ashawkey/kiuikit.git # only the minimal package

Usage

import kiui

### auto import
kiui.env() # os, glob, math, time, random, argparse
kiui.env('data') # above + np, plt, cv2, Image, ...
kiui.env('torch') # above + torch, nn, F, ...

### quick inspection of array-like object
x = torch.tensor(...)
y = np.array(...)

kiui.lo(x)
kiui.lo(x, y) # support multiple objects

kiui.lo(kiui) # or any other object (just print with name)

### io utils
# read image as-is in RGB order
img = kiui.read_image('image.png', mode='float') # mode: float (default), pil, uint8, tensor
# write image
kiui.write_image('image.png', img)

### visualization tools
img_tensor = torch.rand(3, 256, 256) 
# tensor of [3, H, W], [1, H, W], [H, W] / array of [H, W ,3], [H, W, 1], [H, W] in [0, 1]
kiui.vis.plot_image(img)
kiui.vis.plot_image(img_tensor)

### mesh utils
from kiui.mesh import Mesh
mesh = Mesh.load('model.obj')
kiui.lo(mesh.v, mesh.f) # CUDA torch.Tensor suitable for nvdiffrast
mesh.write('new.obj')
mesh.write('new.glb') # support exporting to GLB/GLTF too (texture embedded).

# perceptual loss (from https://github.com/richzhang/PerceptualSimilarity)
from kiui.lpips import LPIPS
lpips = LPIPS(net='vgg').cuda()
loss = lpips(input, target) # [B, 3, H, W] image in [-1, 1]

CLI tools:

# background removal utils
python -m kiui.cli.bg --help
python -m kiui.cli.bg input.png output.png
python -m kiui.cli.bg input_folder output_folder

# openpose detector
python -m kiui.cli.pose --help

# hed edge detector
python -m kiui.cli.hed --help

# open a GUI to render a mesh (extra dependency: nvdiffrast)
python -m kiui.render --help
python -m kiui.render mesh.obj
python -m kiui.render mesh.obj --save_video out.mp4 --wogui # save 360 degree rotating video

# sr (Real-ESRGAN from https://github.com/ai-forever/Real-ESRGAN/tree/main)
python -m kiui.sr --help
python -m kiui.sr image.jpg --scale 2 # save to image_2x.jpg

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

kiui-0.1.8.tar.gz (29.6 kB view details)

Uploaded Source

Built Distribution

kiui-0.1.8-py3-none-any.whl (31.2 kB view details)

Uploaded Python 3

File details

Details for the file kiui-0.1.8.tar.gz.

File metadata

  • Download URL: kiui-0.1.8.tar.gz
  • Upload date:
  • Size: 29.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.4

File hashes

Hashes for kiui-0.1.8.tar.gz
Algorithm Hash digest
SHA256 1b05382dd25e436d450720050e4d247d6b323f70bf1d57157a242fcf9aa5f07b
MD5 21930b285be716a5864eb64fbce327d2
BLAKE2b-256 0e860be5added71bc45fd1ac46ba4bced61462ef123291cf2a28c0f8b566300b

See more details on using hashes here.

File details

Details for the file kiui-0.1.8-py3-none-any.whl.

File metadata

  • Download URL: kiui-0.1.8-py3-none-any.whl
  • Upload date:
  • Size: 31.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.4

File hashes

Hashes for kiui-0.1.8-py3-none-any.whl
Algorithm Hash digest
SHA256 2ffde8ddf362d9f16e4f28c5182620e7d83ea83369fe4b4284710b20de2c2ea8
MD5 d9d675cb03b6902e0c438c3fcefdfaac
BLAKE2b-256 14774cb89c9b5955bbd0ae1019fbdf4422efe6134a67fb905b4af92126b7b632

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page