Anime-Face-Detector

A Faster-RCNN based anime face detector.

This repo is a fork, the original repo can be found here

This detector in trained on 6000 training samples and 641 testing samples, randomly selected from the dataset which is crawled from top 100 pixiv daily ranking.

Thanks to OpenCV based Anime face detector written by nagadomi, which helps labelling the data.

The original implementation of Faster-RCNN using Tensorflow can be found here

Dependencies

Python 3.6.x
tensorflow
opencv-python
cython
Pre-trained ResNet101 model

Usage

Download the pre-trained model
Google Drive: here
Baidu Netdisk: here
Unzip the model file into model directory
Build the CPU NMS model (skip this step if use PY_NMS with argument: -nms-type PY_NMS)
```
make clean
make
```

Run the demo as you want

Visualize the result (without output path):
```
python main.py -i /path/to/image.jpg
```

Save results to a json file

python main.py -i /path/to/image.jpg -o /path/to/output.json

Sample output file:

{"/path/to/image.jpg": [{"score": 0.9999708, "bbox": [551.3375, 314.50253, 729.2599, 485.25674]}]}

Detecting a whole directory with recursion

python main.py -i /path/to/dir -o /path/to/output.json

Customize threshold

python main.py -i /path/to/image.jpg -nms 0.3 -conf 0.8

Customize model path

python main.py -i /path/to/image.jpg -model /path/to/model.ckpt

Customize nms type (supports CPU_NMS and PY_NMS, not supports GPU_NMS because of the complicated build process for Windows platform)
```
python main.py -i /path/to/image.jpg -nms-type PY_NMS
```

Results

Mean AP for this model: 0.9086

couver-v/anime-face-detector

Anime-Face-Detector

Dependencies

Usage

Results