YYDongRo/TouhouCharClassifier
PyTorch-based Touhou character image classifier with automatic Pixiv data crawling, dataset updates, training, and fast inference.
This tool helps Touhou Project fans identify characters in images and manage their fan art collections. You input an image, and it tells you which of 21 supported Touhou characters is present, even explaining its reasoning. It's designed for enthusiasts who want to quickly sort fan art or curate datasets for personal use.
Use this if you're a Touhou Project fan who wants to quickly identify characters in images or build a categorized collection of fan art from Pixiv.
Not ideal if you need to classify characters outside of the 21 supported Touhou characters or require classification for general anime images.
Stars
7
Forks
—
Language
Python
License
GPL-3.0
Category
Last pushed
Feb 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/YYDongRo/TouhouCharClassifier"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
qubvel/efficientnet
Implementation of EfficientNet model. Keras and TensorFlow Keras.
KichangKim/DeepDanbooru
AI based multi-label girl image classification system, implemented by using TensorFlow.
matlab-deep-learning/Image-Classification-in-MATLAB-Using-TensorFlow
This example shows how to call a TensorFlow model from MATLAB using co-execution with Python.
AFAgarap/cnn-svm
An Architecture Combining Convolutional Neural Network (CNN) and Linear Support Vector Machine...
harvitronix/five-video-classification-methods
Code that accompanies my blog post outlining five video classification methods in Keras and TensorFlow