Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/rockyzhengwu/nsfw
Not Suitable for Work (NSFW) classification
https://github.com/rockyzhengwu/nsfw
Last synced: about 1 month ago
JSON representation
Not Suitable for Work (NSFW) classification
- Host: GitHub
- URL: https://github.com/rockyzhengwu/nsfw
- Owner: rockyzhengwu
- License: apache-2.0
- Created: 2019-01-21T02:57:26.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2019-01-21T03:05:12.000Z (almost 6 years ago)
- Last Synced: 2024-08-03T09:12:19.093Z (4 months ago)
- Language: Python
- Homepage:
- Size: 2.76 MB
- Stars: 554
- Watchers: 31
- Forks: 205
- Open Issues: 7
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-github-star - nsfw
README
# NSFW Model
This repo contains code for running Not Suitable for Work (NSFW) classification.
[online demo](http://ai.midday.me/)
## Usage
#### script
```bash
python nsfw_predict.py /tmp/test/test.jpeg
```result :
```bash
{'class': 'sexy', 'probability': {'drawings': 0.008320281, 'hentai': 0.0011919827, 'neutral': 0.13077603, 'porn': 0.13146976, 'sexy': 0.72824186}}
```can find the meaning of every label at repo [nsfw_data_scrapper](https://github.com/alexkimxyz/nsfw_data_scrapper)
#### Deploy by TensorFlow Serving
your have to install [Tensorflow Serving](https://www.tensorflow.org/serving/) first
start the server
```bash
./start_tensorflow_serving.sh
```test server
```bash
python serving_client.py /tmp/test/test.jpeg
```## Train
train code at [resnet](./resnet)
train a new model
1. convert source to tfrecord user ```convert_image_to_tfrecord.py```
2. train a model from scratch or fine tunethe model code copy from [Tensorflow offical model](https://github.com/tensorflow/models/tree/master/official/resnet)
## Data
you can find the detail at repo [nsfw_data_scrapper](https://github.com/alexkimxyz/nsfw_data_scrapper)