TensorFlow 2 implementation of the Yahoo Open-NSFW model

Overview

ci License MIT 1.0

Introduction

Detecting Not-Suitable-For-Work (NSFW) images is a high demand task in computer vision. While there are many types of NSFW images, here we focus on the pornographic images.

The Yahoo Open-NSFW model originally developed with the Caffe framework has been a favourite choice, but the work is now discontinued and Caffe is also becoming less popular. Please see the description on the Yahoo project page for the context, definitions, and model training details.

This Open-NSFW 2 project provides a TensorFlow 2 implementation of the Yahoo model, with references to its previous third-party TensorFlow 1 implementation.

Installation

Python 3.7 or above is required. Tested for 3.7, 3.8, and 3.9.

The best way to install Open-NSFW 2 with its dependencies is from PyPI:

python3 -m pip install --upgrade opennsfw2

Alternatively, to obtain the latest version from this repository:

git clone [email protected]:bhky/opennsfw2.git
cd opennsfw2
python3 -m pip install .

Usage

import numpy as np
import opennsfw2 as n2
from PIL import Image

# Load and preprocess image.
image_path = "path/to/your/image.jpg"
pil_image = Image.open(image_path)
image = n2.preprocess_image(pil_image, n2.Preprocessing.YAHOO)
# The preprocessed image is a NumPy array of shape (224, 224, 3).

# Create the model.
# By default, this call will search for the pre-trained weights file from path:
# $HOME/.opennsfw2/weights/open_nsfw_weights.h5
# If not exists, the file will be downloaded from this repository.
# The model is a `tf.keras.Model` object.
model = n2.make_open_nsfw_model()

# Make predictions.
inputs = np.expand_dims(image, axis=0)  # Add batch axis (for single image).
predictions = model.predict(inputs)

# The shape of predictions is (batch_size, 2).
# Each row gives [sfw_probability, nsfw_probability] of an input image, e.g.:
sfw_probability, nsfw_probability = predictions[0]

Alternatively, the end-to-end pipeline function can be used:

import opennsfw2 as n2

image_paths = [
    "path/to/your/image1.jpg",
    "path/to/your/image2.jpg",
    # ...
]

predictions = n2.predict(
    image_paths, batch_size=4, preprocessing=n2.Preprocessing.YAHOO
)

API

preprocess_image

Apply necessary preprocessing to the input image.

  • Parameters:
    • pil_image (PIL.Image): Input as a Pillow image.
    • preprocessing (Preprocessing enum, default Preprocessing.YAHOO): See preprocessing details.
  • Return:
    • NumPy array of shape (224, 224, 3).

Preprocessing

Enum class for preprocessing options.

  • Preprocessing.YAHOO
  • Preprocessing.SIMPLE

make_open_nsfw_model

Create an instance of the NSFW model, optionally with pre-trained weights from Yahoo.

  • Parameters:
    • input_shape (Tuple[int, int, int], default (224, 224, 3)): Input shape of the model, this should not be changed.
    • weights_path (Optional[str], default $HOME/.opennsfw/weights/open_nsfw_weights.h5): Path to the weights in HDF5 format to be loaded by the model. The weights file will be downloaded if not exists. Users can provide path if the default is not preferred. If None, no weights will be downloaded nor loaded to the model.
  • Return:
    • tf.keras.Model object.

predict

End-to-end pipeline function from input image paths to predictions.

  • Parameters:
    • image_paths (Sequence[str]): List of paths to input image files.
    • batch_size (int, default 32): Batch size to be used for model inference.
    • preprocessing: Same as that in preprocess_image.
    • weights_path: Same as that in make_open_nsfw_model.
  • Return:
    • NumPy array of shape (batch_size, 2), each row gives [sfw_probability, nsfw_probability] of an input image.

Preprocessing details

Options

This implementation provides the following preprocessing options.

  • YAHOO: The default option which was used in the original Yahoo's Caffe and the later TensorFlow 1 implementations. The key steps are:
    • Resize the input Pillow image to (256, 256).
    • Save the image as JPEG bytes and reload again to a NumPy image (this step is mysterious, but somehow it really makes a difference).
    • Crop the centre part of the NumPy image with size (224, 224).
    • Swap the colour channels to BGR.
    • Subtract the training dataset mean value of each channel: [104, 117, 123].
  • SIMPLE: A simpler and probably more intuitive preprocessing option is also provided, but note that the model output probabilities will be different. The key steps are:
    • Resize the input Pillow image to (224, 224).
    • Convert to a NumPy image.
    • Swap the colour channels to BGR.
    • Subtract the training dataset mean value of each channel: [104, 117, 123].

Comparison

Using 521 private images, the NSFW probabilities given by three different settings are compared:

  • TensorFlow 1 implementation with YAHOO preprocessing.
  • TensorFlow 2 implementation with YAHOO preprocessing.
  • TensorFlow 2 implementation with SIMPLE preprocessing.

The following figure shows the result:

NSFW probabilities comparison

The current TensorFlow 2 implementation with YAHOO preprocessing can totally reproduce the well-tested TensorFlow 1 result, with small floating point errors only.

With SIMPLE preprocessing the results are different, where the model tends to give lower probabilities.

You might also like...
Deploy tensorflow graphs for fast evaluation and export to tensorflow-less environments running numpy.
Deploy tensorflow graphs for fast evaluation and export to tensorflow-less environments running numpy.

Deploy tensorflow graphs for fast evaluation and export to tensorflow-less environments running numpy. Now with tensorflow 1.0 support. Evaluation usa

TensorFlow Ranking is a library for Learning-to-Rank (LTR) techniques on the TensorFlow platform
TensorFlow Ranking is a library for Learning-to-Rank (LTR) techniques on the TensorFlow platform

TensorFlow Ranking is a library for Learning-to-Rank (LTR) techniques on the TensorFlow platform

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

Robust Video Matting (RVM) English | 中文 Official repository for the paper Robust High-Resolution Video Matting with Temporal Guidance. RVM is specific

Open-AI's DALL-E for large scale training in mesh-tensorflow.

DALL-E in Mesh-Tensorflow [WIP] Open-AI's DALL-E in Mesh-Tensorflow. If this is similarly efficient to GPT-Neo, this repo should be able to train mode

Using Tensorflow Object Detection API to detect Waymo open dataset
Using Tensorflow Object Detection API to detect Waymo open dataset

Waymo-2D-Object-Detection Using Tensorflow Object Detection API to detect Waymo open dataset Result CenterNet Training Loss SSD ResNet Training Loss C

Implementation of STAM (Space Time Attention Model), a pure and simple attention model that reaches SOTA for video classification
Implementation of STAM (Space Time Attention Model), a pure and simple attention model that reaches SOTA for video classification

STAM - Pytorch Implementation of STAM (Space Time Attention Model), yet another pure and simple SOTA attention model that bests all previous models in

😇A pyTorch implementation of the DeepMoji model: state-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc

------ Update September 2018 ------ It's been a year since TorchMoji and DeepMoji were released. We're trying to understand how it's being used such t

Mesh TensorFlow: Model Parallelism Made Easier

Mesh TensorFlow - Model Parallelism Made Easier Introduction Mesh TensorFlow (mtf) is a language for distributed deep learning, capable of specifying

Comments
  • ERROR WITH NO ERROR

    ERROR WITH NO ERROR

    Hi, I don't understand what happened with opennsfw2 code. My installation is OK. I install Keras and Tensorflow 2.0 with CUDA but nothing, Any idea ? I attached a screenshot. Thank you to help me 0008_2022-09-10_17_heures_18

    opened by fog88 7
  • Which NSFW Area is this AI covering?

    Which NSFW Area is this AI covering?

    Hi,

    very cool project, I am looking for an AI, which can cover on the one side nudity, but doesn't judge sexy images and also bans traumatic images, like horror and the crazy things, like NSFW 4 things, is it possible with this AI?

    nsfw-chart

    I found this image online, which is your AI covering?

    Thanks!

    opened by Flori00123 5
  • small demo website

    small demo website

    would be nice to have a small website that allows users to demo the model instead of having to run it all, such as https://maybeshewill-cv.github.io/nsfw_classification/

    opened by DankMemeGuy 1
Releases(v0.10.2)
Owner
Bosco Yung
Machine Learning Engineer, Lecturer, Astrophysicist
Bosco Yung
ReConsider is a re-ranking model that re-ranks the top-K (passage, answer-span) predictions of an Open-Domain QA Model like DPR (Karpukhin et al., 2020).

ReConsider ReConsider is a re-ranking model that re-ranks the top-K (passage, answer-span) predictions of an Open-Domain QA Model like DPR (Karpukhin

Facebook Research 47 Jul 26, 2022
In this project we investigate the performance of the SetCon model on realistic video footage. Therefore, we implemented the model in PyTorch and tested the model on two example videos.

Contrastive Learning of Object Representations Supervisor: Prof. Dr. Gemma Roig Institutions: Goethe University CVAI - Computational Vision & Artifici

Dirk Neuhäuser 6 Dec 8, 2022
Step by Step on how to create an vision recognition model using LOBE.ai, export the model and run the model in an Azure Function

Step by Step on how to create an vision recognition model using LOBE.ai, export the model and run the model in an Azure Function

El Bruno 3 Mar 30, 2022
An efficient and effective learning to rank algorithm by mining information across ranking candidates. This repository contains the tensorflow implementation of SERank model. The code is developed based on TF-Ranking.

SERank An efficient and effective learning to rank algorithm by mining information across ranking candidates. This repository contains the tensorflow

Zhihu 44 Oct 20, 2022
Unofficial TensorFlow implementation of the Keyword Spotting Transformer model

Keyword Spotting Transformer This is the unofficial TensorFlow implementation of the Keyword Spotting Transformer model. This model is used to train o

Intelligent Machines Limited 8 May 11, 2022
Tensorflow implementation of Swin Transformer model.

Swin Transformer (Tensorflow) Tensorflow reimplementation of Swin Transformer model. Based on Official Pytorch implementation. Requirements tensorflow

null 167 Jan 8, 2023
Tensorflow 2.x implementation of Vision-Transformer model

Vision Transformer Unofficial Tensorflow 2.x implementation of the Transformer based Image Classification model proposed by the paper AN IMAGE IS WORT

Soumik Rakshit 16 Jul 20, 2022
Tensorflow Implementation for "Pre-trained Deep Convolution Neural Network Model With Attention for Speech Emotion Recognition"

Tensorflow Implementation for "Pre-trained Deep Convolution Neural Network Model With Attention for Speech Emotion Recognition" Pre-trained Deep Convo

Ankush Malaker 5 Nov 11, 2022
Unofficial TensorFlow implementation of the Keyword Spotting Transformer model

Keyword Spotting Transformer This is the unofficial TensorFlow implementation of the Keyword Spotting Transformer model. This model is used to train o

Intelligent Machines Limited 8 May 11, 2022
The official TensorFlow implementation of the paper Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition

Action Transformer A Self-Attention Model for Short-Time Human Action Recognition This repository contains the official TensorFlow implementation of t

PIC4SeRCentre 20 Jan 3, 2023